Hidden Markov modelA hidden Markov model (HMM) is a statistical Markov model in which the system being modeled is assumed to be a Markov process — call it — with unobservable ("hidden") states. As part of the definition, HMM requires that there be an observable process whose outcomes are "influenced" by the outcomes of in a known way.
Received PronunciationReceived Pronunciation (RP) is the accent traditionally regarded as the standard and most prestigious form of spoken British English. For over a century, there has been argument over such questions as the definition of RP, whether it is geographically neutral, how many speakers there are, whether sub-varieties exist, how appropriate a choice it is as a standard and how the accent has changed over time. The name itself is controversial.
Japanese phonologyThe phonology of Japanese features about 15 consonant phonemes, the cross-linguistically typical five-vowel system of /a, e, i, o, u/, and a relatively simple phonotactic distribution of phonemes allowing few consonant clusters. It is traditionally described as having a mora as the unit of timing, with each mora taking up about the same length of time, so that the disyllabic [ɲip.poɴ] ("Japan") may be analyzed as /niQpoN/ and dissected into four moras, /ni/, /Q/, /po/, and /N/.
Speech recognitionSpeech recognition is an interdisciplinary subfield of computer science and computational linguistics that develops methodologies and technologies that enable the recognition and translation of spoken language into text by computers. It is also known as automatic speech recognition (ASR), computer speech recognition or speech to text (STT). It incorporates knowledge and research in the computer science, linguistics and computer engineering fields. The reverse process is speech synthesis.
Discriminative modelDiscriminative models, also referred to as conditional models, are a class of logistical models used for classification or regression. They distinguish decision boundaries through observed data, such as pass/fail, win/lose, alive/dead or healthy/sick. Typical discriminative models include logistic regression (LR), conditional random fields (CRFs) (specified over an undirected graph), decision trees, and many others. Typical generative model approaches include naive Bayes classifiers, Gaussian mixture models, variational autoencoders, generative adversarial networks and others.
Statistical inferenceStatistical inference is the process of using data analysis to infer properties of an underlying distribution of probability. Inferential statistical analysis infers properties of a population, for example by testing hypotheses and deriving estimates. It is assumed that the observed data set is sampled from a larger population. Inferential statistics can be contrasted with descriptive statistics. Descriptive statistics is solely concerned with properties of the observed data, and it does not rest on the assumption that the data come from a larger population.
Time seriesIn mathematics, a time series is a series of data points indexed (or listed or graphed) in time order. Most commonly, a time series is a sequence taken at successive equally spaced points in time. Thus it is a sequence of discrete-time data. Examples of time series are heights of ocean tides, counts of sunspots, and the daily closing value of the Dow Jones Industrial Average. A time series is very frequently plotted via a run chart (which is a temporal line chart).
International Phonetic AlphabetThe International Phonetic Alphabet (IPA) is an alphabetic system of phonetic notation based primarily on the Latin script. It was devised by the International Phonetic Association in the late 19th century as a standardized representation of speech sounds in written form. The IPA is used by lexicographers, foreign language students and teachers, linguists, speech–language pathologists, singers, actors, constructed language creators, and translators.
Acoustic modelAn acoustic model is used in automatic speech recognition to represent the relationship between an audio signal and the phonemes or other linguistic units that make up speech. The model is learned from a set of audio recordings and their corresponding transcripts. It is created by taking audio recordings of speech, and their text transcriptions, and using software to create statistical representations of the sounds that make up each word. Modern speech recognition systems use both an acoustic model and a language model to represent the statistical properties of speech.
InferenceInferences are steps in reasoning, moving from premises to logical consequences; etymologically, the word infer means to "carry forward". Inference is theoretically traditionally divided into deduction and induction, a distinction that in Europe dates at least to Aristotle (300s BCE). Deduction is inference deriving logical conclusions from premises known or assumed to be true, with the laws of valid inference being studied in logic. Induction is inference from particular evidence to a universal conclusion.
Standard EnglishIn an English-speaking country, Standard English (SE) is the variety of English that has undergone substantial regularisation and is associated with formal schooling, language assessment, and official print publications, such as public service announcements and newspapers of record, etc. All linguistic features are subject to the effects of standardisation, including morphology, phonology, syntax, lexicon, register, discourse markers, pragmatics, as well as written features such as spelling conventions, punctuation, capitalisation and abbreviation practices.
Viterbi algorithmThe Viterbi algorithm is a dynamic programming algorithm for obtaining the maximum a posteriori probability estimate of the most likely sequence of hidden states—called the Viterbi path—that results in a sequence of observed events, especially in the context of Markov information sources and hidden Markov models (HMM). The algorithm has found universal application in decoding the convolutional codes used in both CDMA and GSM digital cellular, dial-up modems, satellite, deep-space communications, and 802.
Markov modelIn probability theory, a Markov model is a stochastic model used to model pseudo-randomly changing systems. It is assumed that future states depend only on the current state, not on the events that occurred before it (that is, it assumes the Markov property). Generally, this assumption enables reasoning and computation with the model that would otherwise be intractable. For this reason, in the fields of predictive modelling and probabilistic forecasting, it is desirable for a given model to exhibit the Markov property.
Greek alphabetThe Greek alphabet has been used to write the Greek language since the late 9th or early 8th century BC. It is derived from the earlier Phoenician alphabet, and was the earliest known alphabetic script to have distinct letters for vowels as well as consonants. In Archaic and early Classical times, the Greek alphabet existed in many local variants, but, by the end of the 4th century BC, the Euclidean alphabet, with 24 letters, ordered from alpha to omega, had become standard and it is this version that is still used for Greek writing today.
Mixture modelIn statistics, a mixture model is a probabilistic model for representing the presence of subpopulations within an overall population, without requiring that an observed data set should identify the sub-population to which an individual observation belongs. Formally a mixture model corresponds to the mixture distribution that represents the probability distribution of observations in the overall population.
Artificial neural networkArtificial neural networks (ANNs, also shortened to neural networks (NNs) or neural nets) are a branch of machine learning models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.
Vocal tractThe vocal tract is the cavity in human bodies and in animals where the sound produced at the sound source (larynx in mammals; syrinx in birds) is filtered. In birds it consists of the trachea, the syrinx, the oral cavity, the upper part of the esophagus, and the beak. In mammals it consists of the laryngeal cavity, the pharynx, the oral cavity, and the nasal cavity. The estimated average length of the vocal tract in men is 16.9 cm and 14.1 cm in women.
Pitch (music)Pitch is a perceptual property of sounds that allows their ordering on a frequency-related scale, or more commonly, pitch is the quality that makes it possible to judge sounds as "higher" and "lower" in the sense associated with musical melodies. Pitch is a major auditory attribute of musical tones, along with duration, loudness, and timbre. Pitch may be quantified as a frequency, but pitch is not a purely objective physical property; it is a subjective psychoacoustical attribute of sound.
Pitch classIn music, a pitch class (p.c. or pc) is a set of all pitches that are a whole number of octaves apart; for example, the pitch class C consists of the Cs in all octaves. "The pitch class C stands for all possible Cs, in whatever octave position." Important to musical set theory, a pitch class is "all pitches related to each other by octave, enharmonic equivalence, or both." Thus, using scientific pitch notation, the pitch class "C" is the set {Cn : n is an integer} = {..., C−2, C−1, C0, C1, C2, C3 ...}.
Auditory phoneticsAuditory phonetics is the branch of phonetics concerned with the hearing of speech sounds and with speech perception. It thus entails the study of the relationships between speech stimuli and a listener's responses to such stimuli as mediated by mechanisms of the peripheral and central auditory systems, including certain areas of the brain. It is said to compose one of the three main branches of phonetics along with acoustic and articulatory phonetics, though with overlapping methods and questions.
