Deep learningDeep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.
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.
PhonemeIn phonology and linguistics, a phoneme (ˈfoʊniːm) is a unit of phone that can distinguish one word from another in a particular language. For example, in most dialects of English, with the notable exception of the West Midlands and the north-west of England, the sound patterns sɪn (sin) and sɪŋ (sing) are two separate words that are distinguished by the substitution of one phoneme, /n/, for another phoneme, /ŋ/. Two words like this that differ in meaning through the contrast of a single phoneme form a minimal pair.
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.
Phonological awarenessPhonological awareness is an individual's awareness of the phonological structure, or sound structure, of words. Phonological awareness is an important and reliable predictor of later reading ability and has, therefore, been the focus of much research. Phonological awareness involves the detection and manipulation of sounds at three levels of sound structure: (1) syllables, (2) onsets and rimes, and (3) phonemes. Awareness of these sounds is demonstrated through a variety of tasks (see below).
Conditional random fieldConditional random fields (CRFs) are a class of statistical modeling methods often applied in pattern recognition and machine learning and used for structured prediction. Whereas a classifier predicts a label for a single sample without considering "neighbouring" samples, a CRF can take context into account. To do so, the predictions are modelled as a graphical model, which represents the presence of dependencies between the predictions. What kind of graph is used depends on the application.
Phonemic orthographyA phonemic orthography is an orthography (system for writing a language) in which the graphemes (written symbols) correspond to the phonemes (significant spoken sounds) of the language. Natural languages rarely have perfectly phonemic orthographies; a high degree of grapheme–phoneme correspondence can be expected in orthographies based on alphabetic writing systems, but they differ in how complete this correspondence is.
PhonicsPhonics is a method for teaching people how to read and write an alphabetic language (such as English or Russian). It is done by demonstrating the relationship between the sounds of the spoken language (phonemes), and the letters or groups of letters (graphemes) or syllables of the written language. In English, this is also known as the alphabetic principle or the alphabetic code. While the principles of phonics generally apply regardless of the language or region, the examples in this article are from General American English pronunciation.
Speech synthesisSpeech synthesis is the artificial production of human speech. A computer system used for this purpose is called a speech synthesizer, and can be implemented in software or hardware products. A text-to-speech (TTS) system converts normal language text into speech; other systems render symbolic linguistic representations like phonetic transcriptions into speech. The reverse process is speech recognition. Synthesized speech can be created by concatenating pieces of recorded speech that are stored in a database.
Voice (phonetics)Voice or voicing is a term used in phonetics and phonology to characterize speech sounds (usually consonants). Speech sounds can be described as either voiceless (otherwise known as unvoiced) or voiced. The term, however, is used to refer to two separate concepts: Voicing can refer to the articulatory process in which the vocal folds vibrate, its primary use in phonetics to describe phones, which are particular speech sounds. It can also refer to a classification of speech sounds that tend to be associated with vocal cord vibration but may not actually be voiced at the articulatory level.
Image segmentationIn and computer vision, image segmentation is the process of partitioning a into multiple image segments, also known as image regions or image objects (sets of pixels). 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.
Long short-term memoryLong short-term memory (LSTM) network is a recurrent neural network (RNN), aimed to deal with the vanishing gradient problem present in traditional RNNs. Its relative insensitivity to gap length is its advantage over other RNNs, hidden Markov models and other sequence learning methods. It aims to provide a short-term memory for RNN that can last thousands of timesteps, thus "long short-term memory".
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 random fieldIn the domain of physics and probability, a Markov random field (MRF), Markov network or undirected graphical model is a set of random variables having a Markov property described by an undirected graph. In other words, a random field is said to be a Markov random field if it satisfies Markov properties. The concept originates from the Sherrington–Kirkpatrick model. A Markov network or MRF is similar to a Bayesian network in its representation of dependencies; the differences being that Bayesian networks are directed and acyclic, whereas Markov networks are undirected and may be cyclic.
ReadingReading is the process of taking in the sense or meaning of letters, symbols, etc., especially by sight or touch. For educators and researchers, reading is a multifaceted process involving such areas as word recognition, orthography (spelling), alphabetics, phonics, phonemic awareness, vocabulary, comprehension, fluency, and motivation. Other types of reading and writing, such as pictograms (e.g., a hazard symbol and an emoji), are not based on speech-based writing systems.
English phonologyEnglish phonology is the system of speech sounds used in spoken English. Like many other languages, English has wide variation in pronunciation, both historically and from dialect to dialect. In general, however, the regional dialects of English share a largely similar (but not identical) phonological system. Among other things, most dialects have vowel reduction in unstressed syllables and a complex set of phonological features that distinguish fortis and lenis consonants (stops, affricates, and fricatives).
Segment (linguistics)In linguistics, a segment is "any discrete unit that can be identified, either physically or auditorily, in the stream of speech". The term is most used in phonetics and phonology to refer to the smallest elements in a language, and this usage can be synonymous with the term phone. In spoken languages, segments will typically be grouped into consonants and vowels, but the term can be applied to any minimal unit of a linear sequence meaningful to the given field of analysis, such as a mora or a syllable in prosodic phonology, a morpheme in morphology, or a chereme in sign language analysis.
PhonotacticsPhonotactics (from Ancient Greek phōnḗ "voice, sound" and taktikós "having to do with arranging") is a branch of phonology that deals with restrictions in a language on the permissible combinations of phonemes. Phonotactics defines permissible syllable structure, consonant clusters and vowel sequences by means of phonotactic constraints. Phonotactic constraints are highly language-specific. For example, in Japanese, consonant clusters like /st/ do not occur.
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/.
Expectation–maximization algorithmIn statistics, an expectation–maximization (EM) algorithm is an iterative method to find (local) maximum likelihood or maximum a posteriori (MAP) estimates of parameters in statistical models, where the model depends on unobserved latent variables. The EM iteration alternates between performing an expectation (E) step, which creates a function for the expectation of the log-likelihood evaluated using the current estimate for the parameters, and a maximization (M) step, which computes parameters maximizing the expected log-likelihood found on the E step.
