Linear belief functions are an extension of the Dempster–Shafer theory of belief functions to the case when variables of interest are continuous. Examples of such variables include financial asset prices, portfolio performance, and other antecedent and consequent variables. The theory was originally proposed by Arthur P. Dempster in the context of Kalman Filters and later was elaborated, refined, and applied to knowledge representation in artificial intelligence and decision making in finance and accounting by Liping Liu. == Concept == A linear belief function intends to represent our belief regarding the location of the true value as follows: We are certain that the truth is on a so-called certainty hyperplane but we do not know its exact location; along some dimensions of the certainty hyperplane, we believe the true value could be anywhere from –∞ to +∞ and the probability of being at a particular location is described by a normal distribution; along other dimensions, our knowledge is vacuous, i.e., the true value is somewhere from –∞ to +∞ but the associated probability is unknown. A belief function in general is defined by a mass function over a class of focal elements, which may have nonempty intersections. A linear belief function is a special type of belief function in the sense that its focal elements are exclusive, parallel sub-hyperplanes over the certainty hyperplane and its mass function is a normal distribution across the sub-hyperplanes. Based on the above geometrical description, Shafer and Liu propose two mathematical representations of a LBF: a wide-sense inner product and a linear functional in the variable space, and as their duals over a hyperplane in the sample space. Monney proposes still another structure called Gaussian hints. Although these representations are mathematically neat, they tend to be unsuitable for knowledge representation in expert systems. == Knowledge representation == A linear belief function can represent both logical and probabilistic knowledge for three types of variables: deterministic such as an observable or controllable, random whose distribution is normal, and vacuous on which no knowledge bears. Logical knowledge is represented by linear equations, or geometrically, a certainty hyperplane. Probabilistic knowledge is represented by a normal distribution across all parallel focal elements. In general, assume X is a vector of multiple normal variables with mean μ and covariance Σ. Then, the multivariate normal distribution can be equivalently represented as a moment matrix: M ( X ) = ( μ Σ ) . {\displaystyle M(X)=\left({\begin{array}{{20}c}\mu \\\Sigma \end{array}}\right).} If the distribution is non-degenerate, i.e., Σ has a full rank and its inverse exists, the moment matrix can be fully swept: M ( X → ) = ( μ Σ − 1 − Σ − 1 ) {\displaystyle M({\vec {X}})=\left({\begin{array}{{20}c}\mu \Sigma ^{-1}\\-\Sigma ^{-1}\end{array}}\right)} Except for normalization constant, the above equation completely determines the normal density function for X. Therefore, M ( X → ) {\displaystyle M({\vec {X}})} represents the probability distribution of X in the potential form. These two simple matrices allow us to represent three special cases of linear belief functions. First, for an ordinary normal probability distribution M(X) represents it. Second, suppose one makes a direct observation on X and obtains a value μ. In this case, since there is no uncertainty, both variance and covariance vanish, i.e., Σ = 0. Thus, a direct observation can be represented as: M ( X ) = ( μ 0 ) {\displaystyle M(X)=\left({\begin{array}{{20}c}\mu \\0\end{array}}\right)} Third, suppose one is completely ignorant about X. This is a very thorny case in Bayesian statistics since the density function does not exist. By using the fully swept moment matrix, we represent the vacuous linear belief functions as a zero matrix in the swept form follows: M ( X → ) = [ 0 0 ] {\displaystyle M({\vec {X}})=\left[{\begin{array}{{20}c}0\\0\end{array}}\right]} One way to understand the representation is to imagine complete ignorance as the limiting case when the variance of X approaches to ∞, where one can show that Σ−1 = 0 and hence M ( X → ) {\displaystyle M({\vec {X}})} vanishes. However, the above equation is not the same as an improper prior or normal distribution with infinite variance. In fact, it does not correspond to any unique probability distribution. For this reason, a better way is to understand the vacuous linear belief functions as the neutral element for combination (see later). To represent the remaining three special cases, we need the concept of partial sweeping. Unlike a full sweeping, a partial sweeping is a transformation on a subset of variables. Suppose X and Y are two vectors of normal variables with the joint moment matrix: M ( X , Y ) = [ μ 1 Σ 11 Σ 21 μ 2 Σ 12 Σ 22 ] {\displaystyle M(X,Y)=\left[{\begin{array}{{20}c}{\begin{array}{{20}c}\mu _{1}\\\Sigma _{11}\\\Sigma _{21}\end{array}}&{\begin{array}{{20}c}\mu _{2}\\\Sigma _{12}\\\Sigma _{22}\end{array}}\end{array}}\right]} Then M(X, Y) may be partially swept. For example, we can define the partial sweeping on X as follows: M ( X → , Y ) = [ μ 1 ( Σ 11 ) − 1 − ( Σ 11 ) − 1 Σ 21 ( Σ 11 ) − 1 μ 2 − μ 1 ( Σ 11 ) − 1 Σ 12 ( Σ 11 ) − 1 Σ 12 Σ 22 − Σ 21 ( Σ 11 ) − 1 Σ 12 ] {\displaystyle M({\vec {X}},Y)=\left[{\begin{array}{{20}c}{\begin{array}{{20}c}\mu _{1}(\Sigma _{11})^{-1}\\-(\Sigma _{11})^{-1}\\\Sigma _{21}(\Sigma _{11})^{-1}\end{array}}&{\begin{array}{{20}c}\mu _{2}-\mu _{1}(\Sigma _{11})^{-1}\Sigma _{12}\\(\Sigma _{11})^{-1}\Sigma _{12}\\\Sigma _{22}-\Sigma _{21}(\Sigma _{11})^{-1}\Sigma _{12}\end{array}}\end{array}}\right]} If X is one-dimensional, a partial sweeping replaces the variance of X by its negative inverse and multiplies the inverse with other elements. If X is multidimensional, the operation involves the inverse of the covariance matrix of X and other multiplications. A swept matrix obtained from a partial sweeping on a subset of variables can be equivalently obtained by a sequence of partial sweepings on each individual variable in the subset and the order of the sequence does not matter. Similarly, a fully swept matrix is the result of partial sweepings on all variables. We can make two observations. First, after the partial sweeping on X, the mean vector and covariance matrix of X are respectively μ 1 ( Σ 11 ) − 1 {\displaystyle \mu _{1}(\Sigma _{11})^{-1}} and − ( Σ 11 ) − 1 {\displaystyle -(\Sigma _{11})^{-1}} , which are the same as that of a full sweeping of the marginal moment matrix of X. Thus, the elements corresponding to X in the above partial sweeping equation represent the marginal distribution of X in potential form. Second, according to statistics, μ 2 − μ 1 ( Σ 11 ) − 1 Σ 12 {\displaystyle \mu _{2}-\mu _{1}(\Sigma _{11})^{-1}\Sigma _{12}} is the conditional mean of Y given X = 0; Σ 22 − Σ 21 ( Σ 11 ) − 1 Σ 12 {\displaystyle \Sigma _{22}-\Sigma _{21}(\Sigma _{11})^{-1}\Sigma _{12}} is the conditional covariance matrix of Y given X = 0; and ( Σ 11 ) − 1 Σ 12 {\displaystyle (\Sigma _{11})^{-1}\Sigma _{12}} is the slope of the regression model of Y on X. Therefore, the elements corresponding to Y indices and the intersection of X and Y in M ( X → , Y ) {\displaystyle M({\vec {X}},Y)} represents the conditional distribution of Y given X = 0. These semantics render the partial sweeping operation a useful method for manipulating multivariate normal distributions. They also form the basis of the moment matrix representations for the three remaining important cases of linear belief functions, including proper belief functions, linear equations, and linear regression models. === Proper linear belief functions === For variables X and Y, assume there exists a piece of evidence justifying a normal distribution for variables Y while bearing no opinions for variables X. Also, assume that X and Y are not perfectly linearly related, i.e., their correlation is less than 1. This case involves a mix of an ordinary normal distribution for Y and a vacuous belief function for X. Thus, we represent it using a partially swept matrix as follows: M ( X → , Y ) = [ 0 0 0 μ 2 0 Σ 22 ] {\displaystyle M({\vec {X}},Y)=\left[{\begin{array}{{20}c}{\begin{array}{{20}c}0\\0\\0\end{array}}&{\begin{array}{{20}c}\mu _{2}\\0\\\Sigma _{22}\\\end{array}}\end{array}}\right]} This is how we could understand the representation. Since we are ignorant on X, we use its swept form and set μ 1 ( Σ 11 ) − 1 = 0 {\displaystyle \mu _{1}(\Sigma _{11})^{-1}=0} and − ( Σ 11 ) − 1 = 0 {\displaystyle -(\Sigma _{11})^{-1}=0} . Since the correlation between X and Y is less than 1, the regression coefficient of X on Y approaches to 0 when the variance of X approaches to ∞. Therefore, ( Σ 11 ) − 1 Σ 12 = 0 {\displaystyle (\Sigma _{11})^{-1}\Sigma _{12}=0} . Similarly, one can prove that μ 1 ( Σ 11 ) − 1 Σ 12 = 0 {\displaystyle \mu _{1}(\Sigma _{11})^{-1}\Sigma _{12}=0} and Σ 21 ( Σ 11 ) −
Text Retrieval Conference
The Text REtrieval Conference (TREC) is an ongoing series of workshops focusing on a list of different information retrieval (IR) research areas, or tracks. It is co-sponsored by the National Institute of Standards and Technology (NIST) and the Intelligence Advanced Research Projects Activity (part of the office of the Director of National Intelligence), and began in 1992 as part of the TIPSTER Text program. Its purpose is to support and encourage research within the information retrieval community by providing the infrastructure necessary for large-scale evaluation of text retrieval methodologies and to increase the speed of lab-to-product transfer of technology. TREC's evaluation protocols have improved many search technologies. A 2010 study estimated that "without TREC, U.S. Internet users would have spent up to 3.15 billion additional hours using web search engines between 1999 and 2009." Hal Varian the Chief Economist at Google wrote that "The TREC data revitalized research on information retrieval. Having a standard, widely available, and carefully constructed set of data laid the groundwork for further innovation in this field." Each track has a challenge wherein NIST provides participating groups with data sets and test problems. Depending on track, test problems might be questions, topics, or target extractable features. Uniform scoring is performed so the systems can be fairly evaluated. After evaluation of the results, a workshop provides a place for participants to collect together thoughts and ideas and present current and future research work.Text Retrieval Conference started in 1992, funded by DARPA (US Defense Advanced Research Project) and run by NIST. Its purpose was to support research within the information retrieval community by providing the infrastructure necessary for large-scale evaluation of text retrieval methodologies. == Goals == Encourage retrieval search based on large text collections Increase communication among industry, academia, and government by creating an open forum for the exchange of research ideas Speed the transfer of technology from research labs into commercial products by demonstrating substantial improvements retrieval methodologies on real world problems To increase the availability of appropriate evaluation techniques for use by industry and academia including development of new evaluation techniques more applicable to current systems TREC is overseen by a program committee consisting of representatives from government, industry, and academia. For each TREC, NIST provide a set of documents and questions. Participants run their own retrieval system on the data and return to NIST a list of retrieved top-ranked documents. NIST pools the individual result judges the retrieved documents for correctness and evaluates the results. The TREC cycle ends with a workshop that is a forum for participants to share their experiences. == Relevance judgments in TREC == TREC defines relevance as: "If you were writing a report on the subject of the topic and would use the information contained in the document in the report, then the document is relevant." Most TREC retrieval tasks use binary relevance: a document is either relevant or not relevant. Some TREC tasks use graded relevance, capturing multiple degrees of relevance. Most TREC collections are too large to perform complete relevance assessment; for these collections it is impossible to calculate the absolute recall for each query. To decide which documents to assess, TREC usually uses a method call pooling. In this method, the top-ranked n documents from each contributing run are aggregated, and the resulting document set is judged completely. == Various TRECs == In 1992 TREC-1 was held at NIST. The first conference attracted 28 groups of researchers from academia and industry. It demonstrated a wide range of different approaches to the retrieval of text from large document collections .Finally TREC1 revealed the facts that automatic construction of queries from natural language query statements seems to work. Techniques based on natural language processing were no better no worse than those based on vector or probabilistic approach. TREC2 Took place in August 1993. 31 group of researchers participated in this. Two types of retrieval were examined. Retrieval using an ‘ad hoc’ query and retrieval using a ‘routing' query In TREC-3 a small group experiments worked with Spanish language collection and others dealt with interactive query formulation in multiple databases TREC-4 they made even shorter to investigate the problems with very short user statements TREC-5 includes both short and long versions of the topics with the goal of carrying out deeper investigation into which types of techniques work well on various lengths of topics In TREC-6 Three new tracks speech, cross language, high precision information retrieval were introduced. The goal of cross language information retrieval is to facilitate research on system that are able to retrieve relevant document regardless of language of the source document TREC-7 contained seven tracks out of which two were new Query track and very large corpus track. The goal of the query track was to create a large query collection TREC-8 contain seven tracks out of which two –question answering and web tracks were new. The objective of QA query is to explore the possibilities of providing answers to specific natural language queries TREC-9 Includes seven tracks In TREC-10 Video tracks introduced Video tracks design to promote research in content based retrieval from digital video In TREC-11 Novelty tracks introduced. The goal of novelty track is to investigate systems abilities to locate relevant and new information within the ranked set of documents returned by a traditional document retrieval system TREC-12 held in 2003 added three new tracks; Genome track, robust retrieval track, HARD (Highly Accurate Retrieval from Documents) == Tracks == === Current tracks === New tracks are added as new research needs are identified, this list is current for TREC 2018. CENTRE Track – Goal: run in parallel CLEF 2018, NTCIR-14, TREC 2018 to develop and tune an IR reproducibility evaluation protocol (new track for 2018). Common Core Track – Goal: an ad hoc search task over news documents. Complex Answer Retrieval (CAR) – Goal: to develop systems capable of answering complex information needs by collating information from an entire corpus. Incident Streams Track – Goal: to research technologies to automatically process social media streams during emergency situations (new track for TREC 2018). The News Track – Goal: partnership with The Washington Post to develop test collections in news environment (new for 2018). Precision Medicine Track – Goal: a specialization of the Clinical Decision Support track to focus on linking oncology patient data to clinical trials. Real-Time Summarization Track (RTS) – Goal: to explore techniques for real-time update summaries from social media streams. === Past tracks === Chemical Track – Goal: to develop and evaluate technology for large scale search in chemistry-related documents, including academic papers and patents, to better meet the needs of professional searchers, and specifically patent searchers and chemists. Clinical Decision Support Track – Goal: to investigate techniques for linking medical cases to information relevant for patient care Contextual Suggestion Track – Goal: to investigate search techniques for complex information needs that are highly dependent on context and user interests. Crowdsourcing Track – Goal: to provide a collaborative venue for exploring crowdsourcing methods both for evaluating search and for performing search tasks. Genomics Track – Goal: to study the retrieval of genomic data, not just gene sequences but also supporting documentation such as research papers, lab reports, etc. Last ran on TREC 2007. Dynamic Domain Track – Goal: to investigate domain-specific search algorithms that adapt to the dynamic information needs of professional users as they explore in complex domains. Enterprise Track – Goal: to study search over the data of an organization to complete some task. Last ran on TREC 2008. Entity Track – Goal: to perform entity-related search on Web data. These search tasks (such as finding entities and properties of entities) address common information needs that are not that well modeled as ad hoc document search. Cross-Language Track – Goal: to investigate the ability of retrieval systems to find documents topically regardless of source language. After 1999, this track spun off into CLEF. FedWeb Track – Goal: to select best resources to forward a query to, and merge the results so that most relevant are on the top. Federated Web Search Track – Goal: to investigate techniques for the selection and combination of search results from a large number of real on-line web search services. Filtering Track – Goal: to binarily decide retrieval of new
Celia (virtual assistant)
Celia is an artificially intelligent virtual assistant developed by Huawei for their latest HarmonyOS and Android-based EMUI smartphones that lack Google Services and a Google Assistant. The assistant can perform day-to-day tasks, which include making a phone call, setting a reminder and checking the weather. It was unveiled on 7 April 2020 and got publicly released on 27 April 2020 via an OTA update solely to selected devices that can update their software to EMUI 10.1. Huawei had initially referred to the new assistant in late 2019 by having announced that there would be an English version of their already 2018 Chinese speaker assistant—Xiaoyi—to be released into the European markets. Due to the on-going China–United States trade war, the company's newly released smartphones were left without any Google services, including the loss of Google Assistant. This subsequently led to the development and release of Celia. AI technology is integrated into the software of Celia, which allows it to translate text using a phones camera and to identify everyday objects — similar to that of Google Lens. == Features == Celia has many features that are similar to that of its rivals: the Google Assistant and Siri. It can be triggered by the words, 'Hey Celia' or be summoned by pressing and holding down on the power button. The default search engine for Celia is Bing, but this can be changed in settings. Celia can make calls, check the agenda, send a message, show the weather, set alarms and control home appliances. The assistant also has the ability to integrate itself with the stock apps of the EMUI software and toggle with the device's settings, such as by turning on the flashlight and playing multimedia content, but with the users command. With the AI that is installed in Celia, it can identify food, everyday objects and translate text using the phones camera. In China, Chinese Xiaoyi packs with an LLM model called PanGu-Σ 3.0 AI on HarmonyOS 4.0 major upgrade improvements from Celia, making the assistant smarter and more advanced compared to when it was launched in 2020 on EMUI handsets in China and internationally, surpassing Apple and Google by the being the first in the AI industry, with a dedicated AI system framework of APIs on the latest operating system that evolves to a complete large dedicated AI software stack called Harmony Intelligence of Pangu Embedded variant model and MindSpore AI framework with Neural Network Runtime on OpenHarmony-based HarmonyOS NEXT base system to replace the dual framework system with a single frame HarmonyOS 5.0 version by Q4 2024, first introduced on June 21, 2024, in Developer Beta 1 preview release at HDC 2024. == Availability by country and language == Currently, Celia is available only in German, English, French and Spanish, and has been released in Germany, the UK, France, Spain, Chile, Mexico and Colombia. Huawei has said, that there will be more regions and languages to come. == Compatible devices == Celia only became available with the EMUI 10.1 update that was released in April, which means that a limited number of devices are compatible with it. More devices will be added to the list throughout the coming months as Celia's availability increases. The current list is shown below: === Huawei P series === Huawei P50 (Pro) Huawei P40 (Lite, Pro & Pro+) Huawei P30 (Pro) === Huawei Mate series === Huawei Mate 40 Huawei Mate 30 (Lite, Pro & RS Porche Design) Huawei MatePad Pro Huawei Mate 20 (Pro, 20X 4G, 20X 5G and RS Porche Design) Huawei Mate X & Xs === Huawei Nova series === Huawei Nova 6 (Nova 6 5G & Nova 6 SE) Huawei Nova 5 (Nova 5 Pro, Nova 5i Pro & Nova 5Z) Huawei Nova Y60 === Huawei Enjoy series === Huawei Enjoy 10S == Issues == Technology news website Engadget has noted that when saying, 'Hey Celia', out aloud in the presence of an iPhone, Siri will respond along with Celia; this is apparently because 'Celia' sounds similar to 'Siri'.
Phase congruency
Phase congruency is a measure of feature significance in computer images, a method of edge detection that is particularly robust against changes in illumination and contrast. == Foundations == Phase congruency reflects the behaviour of the image in the frequency domain. It has been noted that edgelike features have many of their frequency components in the same phase. The concept is similar to coherence, except that it applies to functions of different wavelength. For example, the Fourier decomposition of a square wave consists of sine functions, whose frequencies are odd multiples of the fundamental frequency. At the rising edges of the square wave, each sinusoidal component has a rising phase; the phases have maximal congruency at the edges. This corresponds to the human-perceived edges in an image where there are sharp changes between light and dark. == Definition == Phase congruency compares the weighted alignment of the Fourier components of a signal A n {\displaystyle A_{\rm {n}}} with the sum of the Fourier components. P C ( t ) = max ϕ ¯ ∑ n A n cos ( ϕ n ( t ) − ϕ ¯ ) ∑ n A n {\displaystyle PC(t)=\max _{\bar {\phi }}{\frac {\sum _{\rm {n}}A_{\rm {n}}\cos(\phi _{\rm {n}}(t)-{\bar {\phi }})}{\sum _{\rm {n}}A_{n}}}} where ϕ n {\displaystyle \phi _{\rm {n}}} is the local or instantaneous phase as can be calculated using the Hilbert transform and A n {\displaystyle A_{\rm {n}}} are the local amplitude, or energy, of the signal. When all the phases are aligned, this is equal to 1. Several ways of implementing phase congruency have been developed, of which two versions are available in open source, one written for MATLAB and the other written in Java as a plugin for the ImageJ software. Given the different notations used for its formulation, a unified version has been recently presented, where a methodology for the parameter tuning is also presented. == Advantages == The square-wave example is naive in that most edge detection methods deal with it equally well. For example, the first derivative has a maximal magnitude at the edges. However, there are cases where the perceived edge does not have a sharp step or a large derivative. The method of phase congruency applies to many cases where other methods fail. A notable example is an image feature consisting of a single line, such as the letter "l". Many edge-detection algorithms will pick up two adjacent edges: the transitions from white to black, and black to white. On the other hand, the phase congruency map has a single line. A simple Fourier analogy of this case is a triangle wave. In each of its crests there is a congruency of crests from different sinusoidal functions. == Disadvantages == Calculating the phase congruency map of an image is very computationally intensive, and sensitive to image noise. Techniques of noise reduction are usually applied prior to the calculation.
Pronunciation assessment
Automatic pronunciation assessment uses computer speech recognition to determine how accurately speech has been pronounced, instead of relying on a human instructor or proctor. It is also called speech verification, pronunciation evaluation, and pronunciation scoring. This technology is used to grade speech quality, for language testing, for computer-aided pronunciation teaching (CAPT) in computer-assisted language learning (CALL), for speaking skill remediation, and for accent reduction. Pronunciation assessment is different from dictation or automatic transcription, because instead of determining unknown speech, it verifies learners' pronunciation of known word(s), often from prior transcription of the same utterance; ideally scoring the intelligibility of the learners' speech. Sometimes pronunciation assessment evaluates the prosody of the learners' speech, such as intonation, pitch, tempo, rhythm, and syllable and word stress, although those are usually not essential for being understood in most languages. Pronunciation assessment is also used in reading tutoring, for example in products from Google, Microsoft, and Amira Learning. Automatic pronunciation assessment can also be used to help diagnose and treat speech disorders such as apraxia. == Intelligibility == Intelligibility refers to how well a learner's utterance is understood by a listener, rather than how much it sounds like a native speaker. This is separate from measures of fluency, such as so-called "Goodness of Pronunciation" (GoP) scores, which estimate how closely an utterance aligns with those of native speakers. Intelligibility is widely regarded as the most important communicative goal in pronunciation teaching and assessment. For example, in the Common European Framework of Reference for Languages (CEFR) assessment criteria for "overall phonological control", intelligibility outweighs formally correct pronunciation at all levels. Studies in applied linguistics have shown that accent reduction does not always increase intelligibility because listeners can often comprehend heavily accented speech without difficulty. Pronunciation assessment systems often rely on acoustic methods such as GoP which compare learner speech to reference models to produce phoneme-level scores, which are in turn aggregated to produce word and phrase scores. While these methods are effective for identifying deviations from native speakers' utterances, they do not effectively measure how understandable speech is to human listeners. Intelligibility is influenced by broader linguistic and contextual factors such as stress placement, speech rate, and coarticulation, which are not represented in purely segmental scores. The earliest work on pronunciation assessment avoided measuring genuine listener intelligibility, a shortcoming corrected in 2011 at the Toyohashi University of Technology, and included in the Versant high-stakes English fluency assessment from Pearson and mobile apps from 17zuoye Education & Technology, but still missing in 2023 products from Google Search, Microsoft, Educational Testing Service, Speechace, and ELSA. Assessing authentic listener intelligibility is essential for avoiding inaccuracies from accent bias, especially in high-stakes assessments; from words with multiple correct pronunciations; and from phoneme coding errors in machine-readable pronunciation dictionaries. In 2022, researchers found that some newer speech-to-text systems, based on end-to-end reinforcement learning to map audio signals directly into words, produce word and phrase confidence scores (from 10-25ms audio frame logit aggregation) closely correlated with genuine listener intelligibility. Others have been able to assess intelligibility using Levenshtein or dynamic time warping distance measures from Wav2Vec2 representation of good speech. Further work through 2025 has focused specifically on measuring intelligibility. A 2025 study of 42 pronunciation and speech coaching apps (32 mobile and 10 web) found that none offered intelligibility assessment. Instead, most provided only segmental and accent-focused scoring. About two-thirds of the apps provided some form of specific pronunciation feedback, usually with phonetic transcriptions, but accompanied by visual cues (such as animations of the vocal tract or the lips and tongue from the front) in only about 5% of the apps. Less than a third provided feedback on learner perception of exemplar speech. == Evaluation == Although there are as yet no industry-standard benchmarks for evaluating pronunciation assessment accuracy, researchers occasionally release evaluation speech corpuses for others to use for improving assessment quality. Such evaluation databases often emphasize formally unaccented pronunciation to the exclusion of genuine intelligibility evident from blinded listener transcriptions. As of mid-2025, state of the art approaches for automatically transcribing phonemes typically achieve an error rate of about 10% from known good speech. The International Speech Communication Association (ISCA) 2025 Workshop on Speech and Language Technology in Education (SLaTE) administered a Speak & Improve Challenge: Spoken Language Assessment and Feedback, introducing benchmarks for evaluating pronunciation assessment and remediation systems across languages, accents, and learner populations. The challenge emphasized cross-lingual generalization and alignment with human intelligibility judgments, for more robust and interpretable assessment systems. Ethical issues in pronunciation assessment are present in both human and automatic methods. Authentic validity, fairness, and mitigating bias in evaluation are all crucial. Diverse speech data should be included in automatic pronunciation assessment models. Combining human judgments, especially blinded transcriptions from a wide diversity of listeners, with automated feedback can improve accuracy and fairness. Second language learners benefit substantially from their use of widely available speech recognition systems for dictation, virtual assistants, and AI chatbots. In such systems, users naturally try to correct their own errors evident in speech recognition results that they notice. Such use improves their grammar and vocabulary development along with their pronunciation skills. The extent to which explicit pronunciation assessment and remediation approaches improve on such self-directed interactions remains an open question. Similarly, automatic dictation results have been shown to reflect intelligibility about as well as human scorers. == Recent developments == During 2021–22, a smartphone-based CAPT system was used to sense articulation through both audible and inaudible signals, providing feedback at the phoneme level. Some promising areas for improvement which were being developed in 2024 include articulatory feature extraction and transfer learning to suppress unnecessary corrections. Other interesting advances under development include "augmented reality" interfaces for mobile devices using optical character recognition to provide pronunciation training on text found in user environments. In 2024, audio multimodal large language models were first described as assessing pronunciation. That work has been carried forward by other researchers in 2025 who report positive results. Subsequently, researchers demonstrated pronunciation scoring by providing a language model with textual descriptions of speech, including the speech-to-text transcript, phoneme sequences, pauses, and phoneme sequence matching; this approach can achieve performance similar to multimodal LLMs that analyze raw audio while avoiding their higher computational cost. In 2025, the Duolingo English Test authors published a description of their pronunciation assessment method, purportedly built to measure intelligibility rather than accent imitation. While achieving a correlation of 0.82 with expert human ratings, very close to inter-rater agreement and outperforming alternative methods, the method is nonetheless based on experts' scores along the six-point CEFR common reference levels scale, instead of actual blinded listener transcriptions. Further promising work in 2025 includes assessment feedback aligning learner speech to synthetic utterances using interpretable features, identifying continuous spans of words for remediation feedback; synthesizing corrected speech matching learners' self-perceived voices, which they prefer and imitate more accurately as corrections; and streaming such interactions. On January 21, 2026, Educational Testing Service's TOEFL iBT high-stakes English language test, required by US university admissions and employers from English as a foreign language applicants more often than all other internet-based tests combined, changed its speaking assessments. While official rubrics claim that the new scoring will be based primarily on intelligibility, the new test's technical description indicates that it ju
Lexical choice
Lexical choice is the subtask of Natural language generation that involves choosing the content words (nouns, non-auxiliary verbs, adjectives, and adverbs) in a generated text. Function words (determiners, for example) are usually chosen during realisation. == Examples == The simplest type of lexical choice involves mapping a domain concept (perhaps represented in an ontology) to a word. For example, the concept Finger might be mapped to the word finger. A more complex situation is when a domain concept is expressed using different words in different situations. For example, the domain concept Value-Change can be expressed in many ways: The temperature rose: the verb rose is used for a Value-Change in temperature which increases the value. The temperature fell: the verb fell is used for a Value-Change in temperature which decreases the value. The rain got heavier: the phrase got heavier is used for a Value-Change in precipitation amount when the precipitation is rain. Sometimes words can communicate additional contextual information, for example: The temperature plummeted: the verb plummeted is used for a Value-Change in temperature which decreases the value, when the change is rapid and large. Contextual information is especially significant for vague terms such as tall. For example, a 2m tall man is tall, but a 2m tall horse is small. == Linguistic perspective == Lexical choice modules must be informed by linguistic knowledge of how the system's input data maps onto words. This is a question of semantics, but it is also influenced by syntactic factors (such as collocation effects) and pragmatic factors (such as context). Hence NLG systems need linguistic models of how meaning is mapped to words in the target domain (genre) of the NLG system. Genre tends to be very important; for example the verb veer has a very specific meaning in weather forecasts (wind direction is changing in a clockwise direction) which it does not have in general English, and a weather-forecast generator must be aware of this genre-specific meaning. In some cases there are major differences in how different people use the same word; for example, some people use by evening to mean 6PM and others use it to mean midnight. Psycholinguists have shown that when people speak to each other, they agree on a common interpretation via lexical alignment; this is not something which NLG systems can yet do. Ultimately, lexical choice must deal with the fundamental issue of how language relates to the non-linguistic world. For example, a system which chose colour terms such as red to describe objects in a digital image would need to know which RGB pixel values could generally be described as red; how this was influenced by visual (lighting, other objects in the scene) and linguistic (other objects being discussed) context; what pragmatic connotations were associated with red (for example, when an apple is called red, it is assumed to be ripe as well as have the colour red); and so forth. == Algorithms and models == A number of algorithms and models have been developed for lexical choice in the research community, for example Edmonds developed a model for choosing between near-synonyms (words with similar core meanings but different connotations). However such algorithms and models have not been widely used in applied NLG systems; such systems have instead often used quite simple computational models, and invested development effort in linguistic analysis instead of algorithm development.
Saliency map
In computer vision, a saliency map is an image that highlights either the region on which people's eyes focus first or the most relevant regions for machine learning models. The goal of a saliency map is to reflect the degree of importance of a pixel to the human visual system or an otherwise opaque ML model. For example, in this image, a person first looks at the fort and light clouds, so they should be highlighted on the saliency map. == Application == === Overview === Saliency maps have applications in a variety of different problems. Some general applications: ==== Human eye ==== Image and video compression: The human eye focuses only on a small region of interest in the frame. Therefore, it is not necessary to compress the entire frame with uniform quality. According to the authors, using a salience map reduces the final size of the video with the same visual perception. Image and video quality assessment: The main task for an image or video quality metric is a high correlation with user opinions. Differences in salient regions are given more importance and thus contribute more to the quality score. Image retargeting: It aims at resizing an image by expanding or shrinking the noninformative regions. Therefore, retargeting algorithms rely on the availability of saliency maps that accurately estimate all the salient image details. Object detection and recognition: Instead of applying a computationally complex algorithm to the whole image, we can use it to the most salient regions of an image most likely to contain an object. the primary visual cortex (V1) appears to be responsible for the saliency map, according to the V1 Saliency Hypothesis. ==== Explainable artificial intelligence ==== Saliency maps are a prominent tool in explainable artificial intelligence, providing visual explanations of the decision-making process of machine learning models, particularly deep neural networks. These maps highlight the regions in input data that are most influential on the model's output, effectively indicating where the model is "looking" when making a prediction. In image classification tasks, for example, saliency maps can identify pixels or regions that contribute most to a specific class decision. Developed for convolutional neural networks, saliency mapping techniques range from simply taking the gradient of the class score with respect to the input data to more complex algorithms, such as integrated gradients and class activation mapping. In transformer architecture, attention mechanisms led to analogous saliency maps, such as attention maps, attention rollouts, and class-discriminative attention maps. === Saliency as a segmentation problem === Saliency estimation may be viewed as an instance of image segmentation. In computer vision, image segmentation is the process of partitioning a digital image into multiple segments (sets of pixels, also known as superpixels). The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. More precisely, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain characteristics. == Algorithms == === Overview === There are three forms of classic saliency estimation algorithms implemented in OpenCV: Static saliency: Relies on image features and statistics to localize the regions of interest of an image. Motion saliency: Relies on motion in a video, detected by optical flow. Objects that move are considered salient. Objectness: Objectness reflects how likely an image window covers an object. These algorithms generate a set of bounding boxes of where an object may lie in an image. In addition to classic approaches, neural-network-based are also popular. There are examples of neural networks for motion saliency estimation: TASED-Net: It consists of two building blocks. First, the encoder network extracts low-resolution spatiotemporal features, and then the following prediction network decodes the spatially encoded features while aggregating all the temporal information. STRA-Net: It emphasizes two essential issues. First, spatiotemporal features integrated via appearance and optical flow coupling, and then multi-scale saliency learned via attention mechanism. STAViS: It combines spatiotemporal visual and auditory information. This approach employs a single network that learns to localize sound sources and to fuse the two saliencies to obtain a final saliency map. There's a new static saliency in the literature with name visual distortion sensitivity. It is based on the idea that the true edges, i.e. object contours, are more salient than the other complex textured regions. It detects edges in a different way from the classic edge detection algorithms. It uses a fairly small threshold for the gradient magnitudes to consider the mere presence of the gradients. So, it obtains 4 binary maps for vertical, horizontal and two diagonal directions. The morphological closing and opening are applied to the binary images to close the small gaps. To clear the blob-like shapes, it utilizes the distance transform. After all, the connected pixel groups are individual edges (or contours). A threshold of size of connected pixel set is used to determine whether an image block contains a perceivable edge (salient region) or not. === Example implementation === First, we should calculate the distance of each pixel to the rest of pixels in the same frame: S A L S ( I k ) = ∑ i = 1 N | I k − I i | {\displaystyle \mathrm {SALS} (I_{k})=\sum _{i=1}^{N}|I_{k}-I_{i}|} I i {\displaystyle I_{i}} is the value of pixel i {\displaystyle i} , in the range of [0,255]. The following equation is the expanded form of this equation. SALS(Ik) = |Ik - I1| + |Ik - I2| + ... + |Ik - IN| Where N is the total number of pixels in the current frame. Then we can further restructure our formula. We put the value that has same I together. SALS(Ik) = Σ Fn × |Ik - In| Where Fn is the frequency of In. And the value of n belongs to [0,255]. The frequencies is expressed in the form of histogram, and the computational time of histogram is O ( N ) {\displaystyle O(N)} time complexity. ==== Time complexity ==== This saliency map algorithm has O ( N ) {\displaystyle O(N)} time complexity. Since the computational time of histogram is O ( N ) {\displaystyle O(N)} time complexity which N is the number of pixel's number of a frame. Besides, the minus part and multiply part of this equation need 256 times operation. Consequently, the time complexity of this algorithm is O ( N + 256 ) {\displaystyle O(N+256)} which equals to O ( N ) {\displaystyle O(N)} . ==== Pseudocode ==== All of the following code is pseudo MATLAB code. First, read data from video sequences. After we read data, we do superpixel process to each frame. Spnum1 and Spnum2 represent the pixel number of current frame and previous pixel. Then we calculate the color distance of each pixel, this process we call it contract function. After this two process, we will get a saliency map, and then store all of these maps into a new FileFolder. ==== Difference in algorithms ==== The major difference between function one and two is the difference of contract function. If spnum1 and spnum2 both represent the current frame's pixel number, then this contract function is for the first saliency function. If spnum1 is the current frame's pixel number and spnum2 represent the previous frame's pixel number, then this contract function is for second saliency function. If we use the second contract function which using the pixel of the same frame to get center distance to get a saliency map, then we apply this saliency function to each frame and use current frame's saliency map minus previous frame's saliency map to get a new image which is the new saliency result of the third saliency function. == Datasets == The saliency dataset usually contains human eye movements on some image sequences. It is valuable for new saliency algorithm creation or benchmarking the existing one. The most valuable dataset parameters are spatial resolution, size, and eye-tracking equipment. Here is part of the large datasets table from MIT/Tübingen Saliency Benchmark datasets, for example. To collect a saliency dataset, image or video sequences and eye-tracking equipment must be prepared, and observers must be invited. Observers must have normal or corrected to normal vision and must be at the same distance from the screen. At the beginning of each recording session, the eye-tracker recalibrates. To do this, the observer fixates their gaze on the screen center. The session is then started, and saliency data are collected by showing sequences and recording eye gazes. The eye-tracking device is a high-speed camera, capable of recording eye movements at least 250 fr