AI Detector Eraser

AI Detector Eraser — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

Text Database and Dictionary of Classic Mayan

The project Text Database and Dictionary of Classic Mayan (abbr. TWKM) promotes research on the writing and language of pre-Hispanic Maya culture. It is housed in the Faculty of Arts at the University of Bonn and was established with funding from the North Rhine-Westphalian Academy of Sciences, Humanities and the Arts. The project has a projected run-time of fifteen years and is directed by Nikolai Grube from the Department of Anthropology of the Americas at the University of Bonn. The goal of the project is to conduct computer-based studies of all extant Maya hieroglyphic texts from an epigraphic and cultural-historical standpoint, and to produce and publish a database and a comprehensive dictionary of the Classic Mayan language. == Subject of the Project == The text database, as well as the dictionary that will be compiled by the conclusion of the project, will be assembled based on all known texts from the pre-Hispanic Maya culture. These texts were produced and used between approximately the third century B.C. through A.D. 1500, in a region that today includes parts of the countries of Mexico, Guatemala, Belize, and Honduras. The thousands of hieroglyphic inscriptions on monuments, ceramics, or daily objects that have survived into the present offer insight into the language's vocabulary and structure. The project's database and dictionary will digitally represent original spellings using the logo-syllabic Maya hieroglyphs, as well as their transcription and transliteration in the Roman alphabet. The data will be additionally annotated with various epigraphic analyses, translations, and further object-specific information. == Project Partners == TWKM will employ digital technologies in order to compile and make available the data and metadata, as well as to publish the project's research results. The project thereby methodologically positions itself in the field of the digital humanities. The project will be conducted in cooperation with the project partners (below), the research association for the eHumanities TextGrid, as well as the University and Regional Library of Bonn (ULB). The working environment that is currently under construction, in which the data and metadata will be compiled and annotated, will be realized in theTextGrid Laboratory, a software of the virtual research environment. A further component of this software, the TextGrid Repository, will make the data that are authorized for publication freely available online and ensure their long-term storage. The tools for data compilation and annotation attained from the modularly constructed and extended TextGrid lab thereby provide all the necessary materials for facilitating the research team's the typical epigraphic workflow. The workflow usually begins by documenting the texts and the objects on which they are preserved, and by compiling descriptive data. It then continues with the various levels of epigraphic and linguistic analysis, and concludes in the best case scenario with a translation of the analyzed inscription and a corresponding publication. In cooperation with the ULB, selected data will additionally be made available. The project's Virtual Inscription Archive will present online, in the Digital Collections of the ULB, hieroglyphic inscriptions selected from the published data in the repository, including an image of and brief information about the texts and the objects on which they are written, epigraphic analysis, and translation. == Project Goal == One of the project's goals is to produce a dictionary of Classic Mayan, in both digital and print form, towards the end of the project run-time. Additionally, a database with a corpus of inscriptions, including their translations and epigraphic analyses, will be made freely available online. The database furthermore will provide an ontology-like link of the contextual object data with the inscriptions and with each other, thereby allowing a cultural-historical arrangement of all contents within the periods of pre-Hispanic Maya culture. The contents of the database are additionally linked to citations of relevant literature. As a result, the database will also make freely available to both the scientific community and other interested parties a bibliography representing the research history and a base of knowledge concerning ancient Maya culture and script. In addition, the Classic Maya script, in its temporally defined stages of language development, will be gathered into and documented in a comprehensive language corpus with the aid of the information gathered by the project. In collaboration with all project participants, the corpus data can be used, together with the aid of various comparable analyses and also computational linguistic methods, such as inference-based methods, to confirm readings of some hieroglyphs that are currently only partially confirmed, and to eventually completely decipher the Classic Maya script.
Read more →
AI Photo Editors: Free vs Paid (2026)

Trying to pick the best AI photo editor? An AI photo editor is software that uses machine learning to help you get more done — it scales effortlessly from a single task to thousands. The best picks balance beginner-friendly simplicity with the depth power users need, and they ship updates often. Whether you are a beginner or a pro, the right AI photo editor slots into your workflow and pays for itself fast. Read on for hands-on impressions, pricing tiers, and the standout features that matter.
Read more →
Top 10 AI Bug Finders Compared (2026)

Trying to pick the best AI bug finder? An AI bug finder is software that uses machine learning to help you get more done — it scales effortlessly from a single task to thousands. The best picks balance beginner-friendly simplicity with the depth power users need, and they ship updates often. Whether you are a beginner or a pro, the right AI bug finder slots into your workflow and pays for itself fast. This guide breaks down the top picks, their pros and cons, and who each one is best for.
Read more →
AI Text-to-video Tools Reviews: What Actually Works in 2026

Looking for the best AI text-to-video tool? An AI text-to-video tool is software that uses machine learning to help you get more done — it can save you hours every week by automating repetitive work. Most options offer a generous free tier, with paid plans unlocking higher limits, faster processing, and team features. Whether you are a beginner or a pro, the right AI text-to-video tool slots into your workflow and pays for itself fast. This guide breaks down the top picks, their pros and cons, and who each one is best for.
Read more →
Hugging Face

Hugging Face, Inc., is an American company based in New York City that develops computation tools for building applications using machine learning. Its transformers library built for natural language processing applications and its platform allow users to share machine learning models and datasets and showcase their work. == History == === Founding === The company was founded in 2016 by French entrepreneurs Clément Delangue, Julien Chaumond, and Thomas Wolf in New York City, originally as a company that developed a chatbot app targeted at teenagers. The company was named after the U+1F917 🤗 HUGGING FACE emoji. After open sourcing the model behind the chatbot, the company pivoted to focus on being a platform for machine learning. === AI boom === On April 28, 2021, the company launched the BigScience Research Workshop in collaboration with several other research groups to release an open large language model. In 2022, the workshop concluded with the announcement of BLOOM, a multilingual large language model with 176 billion parameters. In February 2023, the company announced partnership with Amazon Web Services (AWS) which would allow Hugging Face's products to be available to AWS customers to use them as the building blocks for their custom applications. The company also said the next generation of BLOOM will be run on Trainium, a proprietary machine learning chip created by AWS. In June 2024, the company announced, along with Meta and Scaleway, their launch of a new AI accelerator program for European startups. The initiative aimed to help startups integrate open foundation models into their products, accelerating the EU AI ecosystem. The program, based at STATION F in Paris, ran from September 2024 to February 2025. Selected startups received mentoring, and access to AI models and tools and Scaleway's computing power. On September 23, 2024, to further the International Decade of Indigenous Languages, Hugging Face teamed up with Meta and UNESCO to launch a new online language translator. It was built on Meta's No Language Left Behind open-source AI model, enabling free text translation across 200 languages, including many low-resource languages. In April 2025, Hugging Face announced that they acquired a humanoid robotics startup, Pollen Robotics, based in France and founded by Matthieu Lapeyre and Pierre Rouanet in 2016. In an X tweet, Delangue shared his vision to "make Artificial Intelligence robotics Open Source". === Cyberattacks === In early 2026, hackers hijacked the Hugging Face platform to launch Android-targeted attacks involving "powerful malware" which could completely take over a compromised target.
Read more →
$Markov switching multifractal$

Markov switching multifractal

In financial econometrics (the application of statistical methods to economic data), the Markov-switching multifractal (MSM) is a model of asset returns developed by Laurent E. Calvet and Adlai J. Fisher that incorporates stochastic volatility components of heterogeneous durations. MSM captures the outliers, log-memory-like volatility persistence and power variation of financial returns. In currency and equity series, MSM compares favorably with standard volatility models such as GARCH(1,1) and FIGARCH both in- and out-of-sample. MSM is used by practitioners in the financial industry for different types of forecasts. == MSM specification == The MSM model can be specified in both discrete time and continuous time. === Discrete time === Let P t {\displaystyle P_{t}} denote the price of a financial asset, and let r t = ln ⁡ ( P t / P t − 1 ) {\displaystyle r_{t}=\ln(P_{t}/P_{t-1})} denote the return over two consecutive periods. In MSM, returns are specified as r t = μ + σ ¯ ( M 1 , t M 2 , t . . . M k ¯ , t ) 1 / 2 ϵ t , {\displaystyle r_{t}=\mu +{\bar {\sigma }}(M_{1,t}M_{2,t}...M_{{\bar {k}},t})^{1/2}\epsilon _{t},} where μ {\displaystyle \mu } and σ {\displaystyle \sigma } are constants and { ϵ t {\displaystyle \epsilon _{t}} } are independent standard Gaussians. Volatility is driven by the first-order latent Markov state vector: M t = ( M 1 , t M 2 , t … M k ¯ , t ) ∈ R + k ¯ . {\displaystyle M_{t}=(M_{1,t}M_{2,t}\dots M_{{\bar {k}},t})\in R_{+}^{\bar {k}}.} Given the volatility state M t {\displaystyle M_{t}} , the next-period multiplier M k , t + 1 {\displaystyle M_{k,t+1}} is drawn from a fixed distribution M with probability γ k {\displaystyle \gamma _{k}} , and is otherwise left unchanged. The transition probabilities are specified by γ k = 1 − ( 1 − γ 1 ) ( b k − 1 ) {\displaystyle \gamma _{k}=1-(1-\gamma _{1})^{(b^{k-1})}} . The sequence γ k {\displaystyle \gamma _{k}} is approximately geometric γ k ≈ γ 1 b k − 1 {\displaystyle \gamma _{k}\approx \gamma _{1}b^{k-1}} at low frequency. The marginal distribution M has a unit mean, has a positive support, and is independent of k. ==== Binomial MSM ==== In empirical applications, the distribution M is often a discrete distribution that can take the values m 0 {\displaystyle m_{0}} or 2 − m 0 {\displaystyle 2-m_{0}} with equal probability. The return process r t {\displaystyle r_{t}} is then specified by the parameters θ = ( m 0 , μ , σ ¯ , b , γ 1 ) {\displaystyle \theta =(m_{0},\mu ,{\bar {\sigma }},b,\gamma _{1})} . Note that the number of parameters is the same for all k ¯ > 1 {\displaystyle {\bar {k}}>1} . === Continuous time === MSM is similarly defined in continuous time. The price process follows the diffusion: d P t P t = μ d t + σ ( M t ) d W t , {\displaystyle {\frac {dP_{t}}{P_{t}}}=\mu dt+\sigma (M_{t})\,dW_{t},} where σ ( M t ) = σ ¯ ( M 1 , t … M k ¯ , t ) 1 / 2 {\displaystyle \sigma (M_{t})={\bar {\sigma }}(M_{1,t}\dots M_{{\bar {k}},t})^{1/2}} , W t {\displaystyle W_{t}} is a standard Brownian motion, and μ {\displaystyle \mu } and σ ¯ {\displaystyle {\bar {\sigma }}} are constants. Each component follows the dynamics: The intensities vary geometrically with k: γ k = γ 1 b k − 1 . {\displaystyle \gamma _{k}=\gamma _{1}b^{k-1}.} When the number of components k ¯ {\displaystyle {\bar {k}}} goes to infinity, continuous-time MSM converges to a multifractal diffusion, whose sample paths take a continuum of local Hölder exponents on any finite time interval. == Inference and closed-form likelihood == When M {\displaystyle M} has a discrete distribution, the Markov state vector M t {\displaystyle M_{t}} takes finitely many values m 1 , . . . , m d ∈ R + k ¯ {\displaystyle m^{1},...,m^{d}\in R_{+}^{\bar {k}}} . For instance, there are d = 2 k ¯ {\displaystyle d=2^{\bar {k}}} possible states in binomial MSM. The Markov dynamics are characterized by the transition matrix A = ( a i , j ) 1 ≤ i , j ≤ d {\displaystyle A=(a_{i,j})_{1\leq i,j\leq d}} with components a i , j = P ( M t + 1 = m j | M t = m i ) {\displaystyle a_{i,j}=P\left(M_{t+1}=m^{j}|M_{t}=m^{i}\right)} . Conditional on the volatility state, the return r t {\displaystyle r_{t}} has Gaussian density f ( r t | M t = m i ) = 1 2 π σ 2 ( m i ) exp ⁡ [ − ( r t − μ ) 2 2 σ 2 ( m i ) ] . {\displaystyle f(r_{t}|M_{t}=m^{i})={\frac {1}{\sqrt {2\pi \sigma ^{2}(m^{i})}}}\exp \left[-{\frac {(r_{t}-\mu )^{2}}{2\sigma ^{2}(m^{i})}}\right].} === Conditional distribution === === Closed-form Likelihood === The log likelihood function has the following analytical expression: ln ⁡ L ( r 1 , … , r T ; θ ) = ∑ t = 1 T ln ⁡ [ ω ( r t ) . ( Π t − 1 A ) ] . {\displaystyle \ln L(r_{1},\dots ,r_{T};\theta )=\sum _{t=1}^{T}\ln[\omega (r_{t}).(\Pi _{t-1}A)].} Maximum likelihood provides reasonably precise estimates in finite samples. === Other estimation methods === When M {\displaystyle M} has a continuous distribution, estimation can proceed by simulated method of moments, or simulated likelihood via a particle filter. == Forecasting == Given r 1 , … , r t {\displaystyle r_{1},\dots ,r_{t}} , the conditional distribution of the latent state vector at date t + n {\displaystyle t+n} is given by: Π ^ t , n = Π t A n . {\displaystyle {\hat {\Pi }}_{t,n}=\Pi _{t}A^{n}.\,} MSM often provides better volatility forecasts than some of the best traditional models both in and out of sample. Calvet and Fisher report considerable gains in exchange rate volatility forecasts at horizons of 10 to 50 days as compared with GARCH(1,1), Markov-Switching GARCH, and Fractionally Integrated GARCH. Lux obtains similar results using linear predictions. == Applications == === Multiple assets and value-at-risk === Extensions of MSM to multiple assets provide reliable estimates of the value-at-risk in a portfolio of securities. === Asset pricing === In financial economics, MSM has been used to analyze the pricing implications of multifrequency risk. The models have had some success in explaining the excess volatility of stock returns compared to fundamentals and the negative skewness of equity returns. They have also been used to generate multifractal jump-diffusions. == Related approaches == MSM is a stochastic volatility model with arbitrarily many frequencies. MSM builds on the convenience of regime-switching models, which were advanced in economics and finance by James D. Hamilton. MSM is closely related to the Multifractal Model of Asset Returns. MSM improves on the MMAR's combinatorial construction by randomizing arrival times, guaranteeing a strictly stationary process. MSM provides a pure regime-switching formulation of multifractal measures, which were pioneered by Benoit Mandelbrot.
Read more →
François Chollet

François Chollet (French: [fʁɑ̃swa ʃoˈlɛ]; born 20 October 1989) is a French software engineer, artificial intelligence (AI) researcher, and former Senior Staff Engineer at Google. Chollet is the creator of the Keras deep-learning library released in 2015. His research focuses on computer vision, the application of machine learning to formal reasoning, abstraction, and how to achieve greater generality in artificial intelligence (AGI). == Education and career == In 2012, Chollet graduated with a Diplôme d'Ingénieur (Master of Engineering) from ENSTA Paris, a school of the Polytechnic Institute of Paris. In 2015, Chollet started working at Google shortly after releasing Keras. In 2019, he published the Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) benchmark, which measures the ability of AI systems to solve novel reasoning problems. In 2024, Chollet launched ARC Prize, a US$1 million competition to solve the ARC-AGI benchmark. He left Google in November 2024 after more than 9 years with the company to found with Zapier co-founder Mike Knoop a new startup focused on developing AGI with program synthesis. In early 2025, Chollet announced the expansion of ARC Prize into a full-fledged non-profit foundation, to further the mission of guiding and accelerating research progress towards artificial general intelligence. == Books and publications == Chollet's research papers in artificial intelligence have been published at major conferences in the field, including the Conference on Computer Vision and Pattern Recognition (CVPR), the Conference on Neural Information Processing Systems (NeurIPS), and the International Conference on Learning Representations (ICLR). Chollet is the author of Xception: Deep Learning with Depthwise Separable Convolutions, which is among the top ten most cited papers in CVPR proceedings at more than 18,000 citations. Chollet is the author of the book Deep Learning with Python, which sold over 100,000 copies, and the co-author with Tomasz Kalinowski of Deep Learning With R. == Awards == On December 1, 2021, Chollet won the Global Swiss AI Award for breakthroughs in AI. In September 2024, Chollet was named by TIME as one of the 100 most influential people in AI.
Read more →
Stephen Muggleton

Stephen H. Muggleton (born 6 December 1959, son of Louis Muggleton) is Professor of Machine Learning and Head of the Computational Bioinformatics Laboratory at Imperial College London. == Education == Muggleton received his Bachelor of Science degree in computer science (1982) and Doctor of Philosophy in artificial intelligence (1986) supervised by Donald Michie at the University of Edinburgh. == Career == Following his PhD, Muggleton went on to work as a postdoctoral research associate at the Turing Institute in Glasgow (1987–1991) and later an EPSRC Advanced Research Fellow at Oxford University Computing Laboratory (OUCL) (1992–1997) where he founded the Machine Learning Group. In 1997 he moved to the University of York and in 2001 to Imperial College London. From 2025, Muggleton has joined Nanjing University as a full-time professor. == Research == Muggleton's research interests are primarily in Artificial intelligence. From 1997 to 2001 he held the Chair of Machine Learning at the University of York and from 2001 to 2006 the EPSRC Chair of Computational Bioinformatics at Imperial College in London. Since 2013 he holds the Syngenta/Royal Academy of Engineering Research Chair as well as the post of Director of Modelling for the Imperial College Centre for Integrated Systems Biology. He is known for founding the field of Inductive logic programming. In this field he has made contributions to theory introducing predicate invention, inverse entailment and stochastic logic programs. He has also played a role in systems development where he was instrumental in the systems Duce, Cigol, Golem, Progol and Metagol and applications – especially biological prediction tasks. He worked on a Robot Scientist together with Ross D. King that is capable of combining Inductive Logic Programming with active learning. His present work concentrates on the development of Meta-Interpretive Learning, a new form of Inductive Logic Programming which supports predicate invention and learning of recursive programs.
Read more →
Hekaton (database)

Hekaton (also known as SQL Server In-Memory OLTP) is an in-memory database for OLTP workloads built into Microsoft SQL Server. Hekaton was designed in collaboration with Microsoft Research and was released in SQL Server 2014. Traditional RDBMS systems were designed when memory resources were expensive, and were optimized for disk storage. Hekaton is instead optimized for a working set stored entirely in main memory, but is still accessible via T-SQL like normal tables. It is fundamentally different from the "DBCC PINTABLE" feature in earlier SQL Server versions. Hekaton was announced at the Professional Association for SQL Server (PASS) conference 2012.
Read more →
Simon Godsill

Simon John Godsill (born 2 December 1965) is professor of statistical signal processing at the University of Cambridge, and a professorial fellow at Corpus Christi College. He is also a member of the Centre for Science and Policy. His main area of research is Bayesian statistics and stochastic sampling methodologies, particularly particle filtering. == Education == Godsill obtained both undergraduate and Ph.D. degrees from the Department of Engineering at Cambridge University, whilst a member of Selwyn College. He obtained a first class degree in the Electrical and Information Sciences Tripos. The title of his 1993 Ph.D. thesis was "The Restoration of Degraded Audio Signals" and his Ph.D. supervisor was Peter Rayner, whom he shared with Michael Richard Lynch. == Career == Godsill has published over 250 articles in peer reviewed journals, along with the books Digital audio restoration: a statistical model based approach and Compressed sensing & sparse filtering. == Business interests == Godsill is currently a director of CEDAR Audio Ltd, a Cambridge-based company that applies Bayesian mathematics for purposes of noise reduction in audio data. In February 2005, the company received a Sci-Tech Academy Award (a 'Technical Oscar') for its services to the movie industry, and a stream of innovations appeared over the following years with corresponding recognition including induction into the Audio Technology Hall of Fame (2008), a Cinema Audio Society Award (2009). Godsill is also a director at Input Dynamics Ltd, a Cambridge-based company that applies Bayesian techniques to touch screen technology. Godsill is involved with the research effort at BMLL Technologies, a Cambridge spin-off working in the field of machine learning application in the financial sector.
Read more →
Best AI Voice Assistants in 2026

Trying to pick the best AI voice assistant? An AI voice assistant is software that uses machine learning to help you get more done — it scales effortlessly from a single task to thousands. The best picks balance beginner-friendly simplicity with the depth power users need, and they ship updates often. Whether you are a beginner or a pro, the right AI voice assistant slots into your workflow and pays for itself fast. This guide breaks down the top picks, their pros and cons, and who each one is best for.
Read more →
Stephen Muggleton

Stephen H. Muggleton (born 6 December 1959, son of Louis Muggleton) is Professor of Machine Learning and Head of the Computational Bioinformatics Laboratory at Imperial College London. == Education == Muggleton received his Bachelor of Science degree in computer science (1982) and Doctor of Philosophy in artificial intelligence (1986) supervised by Donald Michie at the University of Edinburgh. == Career == Following his PhD, Muggleton went on to work as a postdoctoral research associate at the Turing Institute in Glasgow (1987–1991) and later an EPSRC Advanced Research Fellow at Oxford University Computing Laboratory (OUCL) (1992–1997) where he founded the Machine Learning Group. In 1997 he moved to the University of York and in 2001 to Imperial College London. From 2025, Muggleton has joined Nanjing University as a full-time professor. == Research == Muggleton's research interests are primarily in Artificial intelligence. From 1997 to 2001 he held the Chair of Machine Learning at the University of York and from 2001 to 2006 the EPSRC Chair of Computational Bioinformatics at Imperial College in London. Since 2013 he holds the Syngenta/Royal Academy of Engineering Research Chair as well as the post of Director of Modelling for the Imperial College Centre for Integrated Systems Biology. He is known for founding the field of Inductive logic programming. In this field he has made contributions to theory introducing predicate invention, inverse entailment and stochastic logic programs. He has also played a role in systems development where he was instrumental in the systems Duce, Cigol, Golem, Progol and Metagol and applications – especially biological prediction tasks. He worked on a Robot Scientist together with Ross D. King that is capable of combining Inductive Logic Programming with active learning. His present work concentrates on the development of Meta-Interpretive Learning, a new form of Inductive Logic Programming which supports predicate invention and learning of recursive programs.
Read more →
WaveNet

WaveNet is a deep neural network for generating raw audio. It was created by researchers at London-based AI firm DeepMind. The technique, outlined in a paper in September 2016, is able to generate relatively realistic-sounding human-like voices by directly modelling waveforms using a neural network method trained with recordings of real speech. Tests with US English and Mandarin reportedly showed that the system outperforms Google's best existing text-to-speech (TTS) systems, although as of 2016 its text-to-speech synthesis still was less convincing than actual human speech. WaveNet's ability to generate raw waveforms means that it can model any kind of audio, including music. == History == Generating speech from text is an increasingly common task thanks to the popularity of software such as Apple's Siri, Microsoft's Cortana, Amazon Alexa and the Google Assistant. Most such systems use a variation of a technique that involves concatenated sound fragments together to form recognisable sounds and words. The most common of these is called concatenative TTS. It consists of large library of speech fragments, recorded from a single speaker that are then concatenated to produce complete words and sounds. The result sounds unnatural, with an odd cadence and tone. The reliance on a recorded library also makes it difficult to modify or change the voice. Another technique, known as parametric TTS, uses mathematical models to recreate sounds that are then assembled into words and sentences. The information required to generate the sounds is stored in the parameters of the model. The characteristics of the output speech are controlled via the inputs to the model, while the speech is typically created using a voice synthesiser known as a vocoder. This can also result in unnatural sounding audio. == Design and ongoing research == === Background === WaveNet is a type of feedforward neural network known as a deep convolutional neural network (CNN). In WaveNet, the CNN takes a raw signal as an input and synthesises an output one sample at a time. It does so by sampling from a softmax (i.e. categorical) distribution of a signal value that is encoded using μ-law companding transformation and quantized to 256 possible values. === Initial concept and results === According to the original September 2016 DeepMind research paper WaveNet: A Generative Model for Raw Audio, the network was fed real waveforms of speech in English and Mandarin. As these pass through the network, it learns a set of rules to describe how the audio waveform evolves over time. The trained network can then be used to create new speech-like waveforms at 16,000 samples per second. These waveforms include realistic breaths and lip smacks – but do not conform to any language. WaveNet is able to accurately model different voices, with the accent and tone of the input correlating with the output. For example, if it is trained with German, it produces German speech. The capability also means that if the WaveNet is fed other inputs – such as music – its output will be musical. At the time of its release, DeepMind showed that WaveNet could produce waveforms that sound like classical music. === Content (voice) swapping === According to the June 2018 paper Disentangled Sequential Autoencoder, DeepMind has successfully used WaveNet for audio and voice "content swapping": the network can swap the voice on an audio recording for another, pre-existing voice while maintaining the text and other features from the original recording. "We also experiment on audio sequence data. Our disentangled representation allows us to convert speaker identities into each other while conditioning on the content of the speech." (p. 5) "For audio, this allows us to convert a male speaker into a female speaker and vice versa [...]." (p. 1) According to the paper, a two-digit minimum amount of hours (c. 50 hours) of pre-existing speech recordings of both source and target voice are required to be fed into WaveNet for the program to learn their individual features before it is able to perform the conversion from one voice to another at a satisfying quality. The authors stress that "[a]n advantage of the model is that it separates dynamical from static features [...]." (p. 8), i. e. WaveNet is capable of distinguishing between the spoken text and modes of delivery (modulation, speed, pitch, mood, etc.) to maintain during the conversion from one voice to another on the one hand, and the basic features of both source and target voices that it is required to swap on the other. The January 2019 follow-up paper Unsupervised speech representation learning using WaveNet autoencoders details a method to successfully enhance the proper automatic recognition and discrimination between dynamical and static features for "content swapping", notably including swapping voices on existing audio recordings, in order to make it more reliable. Another follow-up paper, Sample Efficient Adaptive Text-to-Speech, dated September 2018 (latest revision January 2019), states that DeepMind has successfully reduced the minimum amount of real-life recordings required to sample an existing voice via WaveNet to "merely a few minutes of audio data" while maintaining high-quality results. Its ability to clone voices has raised ethical concerns about WaveNet's ability to mimic the voices of living and dead persons. According to a 2016 BBC article, companies working on similar voice-cloning technologies (such as Adobe Voco) intend to insert watermarking inaudible to humans to prevent counterfeiting, while maintaining that voice cloning satisfying, for instance, the needs of entertainment-industry purposes would be of a far lower complexity and use different methods than required to fool forensic evidencing methods and electronic ID devices, so that natural voices and voices cloned for entertainment-industry purposes could still be easily told apart by technological analysis. == Applications == At the time of its release, DeepMind said that WaveNet required too much computational processing power to be used in real world applications. As of October 2017, Google announced a 1,000-fold performance improvement along with better voice quality. WaveNet was then used to generate Google Assistant voices for US English and Japanese across all Google platforms. In November 2017, DeepMind researchers released a research paper detailing a proposed method of "generating high-fidelity speech samples at more than 20 times faster than real-time", called "Probability Density Distillation". At the annual I/O developer conference in May 2018, it was announced that new Google Assistant voices were available and made possible by WaveNet; WaveNet greatly reduced the number of audio recordings that were required to create a voice model by modeling the raw audio of the voice actor samples.
Read more →
Probabilistic context-free grammar

In theoretical linguistics and computational linguistics, probabilistic context free grammars (PCFGs) extend context-free grammars, similar to how hidden Markov models extend regular grammars. Each production is assigned a probability. The probability of a derivation (parse) is the product of the probabilities of the productions used in that derivation. These probabilities can be viewed as parameters of the model, and for large problems it is convenient to learn these parameters via machine learning. A probabilistic grammar's validity is constrained by context of its training dataset. PCFGs originated from grammar theory, and have application in areas as diverse as natural language processing to the study the structure of RNA molecules and design of programming languages. Designing efficient PCFGs has to weigh factors of scalability and generality. Issues such as grammar ambiguity must be resolved. The grammar design affects results accuracy. Grammar parsing algorithms have various time and memory requirements. == Definitions == Derivation: The process of recursive generation of strings from a grammar. Parsing: Finding a valid derivation using an automaton. Parse Tree: The alignment of the grammar to a sequence. An example of a parser for PCFG grammars is the pushdown automaton. The algorithm parses grammar nonterminals from left to right in a stack-like manner. This brute-force approach is not very efficient. In RNA secondary structure prediction variants of the Cocke–Younger–Kasami (CYK) algorithm provide more efficient alternatives to grammar parsing than pushdown automata. Another example of a PCFG parser is the Stanford Statistical Parser which has been trained using Treebank. == Formal definition == Similar to a CFG, a probabilistic context-free grammar G can be defined by a quintuple: G = ( M , T , R , S , P ) {\displaystyle G=(M,T,R,S,P)} where M is the set of non-terminal symbols T is the set of terminal symbols R is the set of production rules S is the start symbol P is the set of probabilities on production rules == Relation with hidden Markov models == PCFGs models extend context-free grammars the same way as hidden Markov models extend regular grammars. The Inside-Outside algorithm is an analogue of the Forward-Backward algorithm. It computes the total probability of all derivations that are consistent with a given sequence, based on some PCFG. This is equivalent to the probability of the PCFG generating the sequence, and is intuitively a measure of how consistent the sequence is with the given grammar. The Inside-Outside algorithm is used in model parametrization to estimate prior frequencies observed from training sequences in the case of RNAs. Dynamic programming variants of the CYK algorithm find the Viterbi parse of a RNA sequence for a PCFG model. This parse is the most likely derivation of the sequence by the given PCFG. == Grammar construction == Context-free grammars are represented as a set of rules inspired from attempts to model natural languages. The rules are absolute and have a typical syntax representation known as Backus–Naur form. The production rules consist of terminal { a , b } {\displaystyle \left\{a,b\right\}} and non-terminal S symbols and a blank ϵ {\displaystyle \epsilon } may also be used as an end point. In the production rules of CFG and PCFG the left side has only one nonterminal whereas the right side can be any string of terminal or nonterminals. In PCFG nulls are excluded. An example of a grammar: S → a S , S → b S , S → ϵ {\displaystyle S\to aS,S\to bS,S\to \epsilon } This grammar can be shortened using the '|' ('or') character into: S → a S | b S | ϵ {\displaystyle S\to aS|bS|\epsilon } Terminals in a grammar are words and through the grammar rules a non-terminal symbol is transformed into a string of either terminals and/or non-terminals. The above grammar is read as "beginning from a non-terminal S the emission can generate either a or b or ϵ {\displaystyle \epsilon } ". Its derivation is: S ⇒ a S ⇒ a b S ⇒ a b b S ⇒ a b b {\displaystyle S\Rightarrow aS\Rightarrow abS\Rightarrow abbS\Rightarrow abb} Ambiguous grammar may result in ambiguous parsing if applied on homographs since the same word sequence can have more than one interpretation. Pun sentences such as the newspaper headline "Iraqi Head Seeks Arms" are an example of ambiguous parses. One strategy of dealing with ambiguous parses (originating with grammarians as early as Pāṇini) is to add yet more rules, or prioritize them so that one rule takes precedence over others. This, however, has the drawback of proliferating the rules, often to the point where they become difficult to manage. Another difficulty is overgeneration, where unlicensed structures are also generated. Probabilistic grammars circumvent these problems by ranking various productions on frequency weights, resulting in a "most likely" (winner-take-all) interpretation. As usage patterns are altered in diachronic shifts, these probabilistic rules can be re-learned, thus updating the grammar. Assigning probability to production rules makes a PCFG. These probabilities are informed by observing distributions on a training set of similar composition to the language to be modeled. On most samples of broad language, probabilistic grammars where probabilities are estimated from data typically outperform hand-crafted grammars. CFGs when contrasted with PCFGs are not applicable to RNA structure prediction because while they incorporate sequence-structure relationship they lack the scoring metrics that reveal a sequence structural potential == Weighted context-free grammar == A weighted context-free grammar (WCFG) is a more general category of context-free grammar, where each production has a numeric weight associated with it. The weight of a specific parse tree in a WCFG is the product (or sum ) of all rule weights in the tree. Each rule weight is included as often as the rule is used in the tree. A special case of WCFGs are PCFGs, where the weights are (logarithms of ) probabilities. An extended version of the CYK algorithm can be used to find the "lightest" (least-weight) derivation of a string given some WCFG. When the tree weight is the product of the rule weights, WCFGs and PCFGs can express the same set of probability distributions. == Applications == === RNA structure prediction === Since the 1990s, PCFG has been applied to model RNA structures. Energy minimization and PCFG provide ways of predicting RNA secondary structure with comparable performance. However structure prediction by PCFGs is scored probabilistically rather than by minimum free energy calculation. PCFG model parameters are directly derived from frequencies of different features observed in databases of RNA structures rather than by experimental determination as is the case with energy minimization methods. The types of various structure that can be modeled by a PCFG include long range interactions, pairwise structure and other nested structures. However, pseudoknots can not be modeled. PCFGs extend CFG by assigning probabilities to each production rule. A maximum probability parse tree from the grammar implies a maximum probability structure. Since RNAs preserve their structures over their primary sequence, RNA structure prediction can be guided by combining evolutionary information from comparative sequence analysis with biophysical knowledge about a structure plausibility based on such probabilities. Also search results for structural homologs using PCFG rules are scored according to PCFG derivations probabilities. Therefore, building grammar to model the behavior of base-pairs and single-stranded regions starts with exploring features of structural multiple sequence alignment of related RNAs. S → a S a | b S b | a a | b b {\displaystyle S\to aSa|bSb|aa|bb} The above grammar generates a string in an outside-in fashion, that is the basepair on the furthest extremes of the terminal is derived first. So a string such as a a b a a b a a {\displaystyle aabaabaa} is derived by first generating the distal a's on both sides before moving inwards: S ⇒ a S a ⇒ a a S a a ⇒ a a b S b a a ⇒ a a b a a b a a {\displaystyle S\Rightarrow aSa\Rightarrow aaSaa\Rightarrow aabSbaa\Rightarrow aabaabaa} A PCFG model extendibility allows constraining structure prediction by incorporating expectations about different features of an RNA . Such expectation may reflect for example the propensity for assuming a certain structure by an RNA. However incorporation of too much information may increase PCFG space and memory complexity and it is desirable that a PCFG-based model be as simple as possible. Every possible string x a grammar generates is assigned a probability weight P ( x | θ ) {\displaystyle P(x|\theta )} given the PCFG model θ {\displaystyle \theta } . It follows that the sum of all probabilities to all possible grammar productions is ∑ x P ( x | θ ) = 1 {\displaystyle \sum _{\text{x}}P(x|\theta )=1} . The scores
Read more →
SNNS

SNNS (Stuttgart Neural Network Simulator) is a neural network simulator originally developed at the University of Stuttgart. While it was originally built for X11 under Unix, there are Windows ports. Its successor JavaNNS never reached the same popularity. == Features == SNNS is written around a simulation kernel to which user written activation functions, learning procedures and output functions can be added. It has support for arbitrary network topologies and the standard release contains support for a number of standard neural network architectures and training algorithms. == Status == There is currently no ongoing active development of SNNS. In July 2008 the license was changed to the GNU LGPL.
Read more →