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.
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.
GraphemeIn linguistics, a grapheme is the smallest functional unit of a writing system. The word grapheme is derived and the suffix -eme by analogy with phoneme and other names of emic units. The study of graphemes is called graphemics. The concept of graphemes is abstract and similar to the notion in computing of a character. By comparison, a specific shape that represents any particular grapheme in a given typeface is called a glyph. There are two main opposing grapheme concepts.
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.
Artificial intelligenceArtificial intelligence (AI) is the intelligence of machines or software, as opposed to the intelligence of human beings or animals. AI applications include advanced web search engines (e.g., Google Search), recommendation systems (used by YouTube, Amazon, and Netflix), understanding human speech (such as Siri and Alexa), self-driving cars (e.g., Waymo), generative or creative tools (ChatGPT and AI art), and competing at the highest level in strategic games (such as chess and Go).
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.
Emic unitIn linguistics and related fields, an emic unit is a type of abstract object. Kinds of emic units are generally denoted by terms with the suffix -eme, such as phoneme, grapheme, and morpheme. The term "emic unit" is defined by Nöth (1995) to mean "an invariant form obtained from the reduction of a class of variant forms to a limited number of abstract units". The variant forms are called etic units (from phonetic). This means that a given emic unit is considered to be a single underlying object that may have a number of different observable "surface" representations.
IdeasthesiaIdeasthesia (alternative spelling ideaesthesia) is a neuropsychological phenomenon in which activations of concepts (inducers) evoke perception-like sensory experiences (concurrents). The name comes from the Ancient Greek ἰδέα (idéa) and αἴσθησις (aísthēsis), meaning 'sensing concepts' or 'sensing ideas'. The notion was introduced by neuroscientist Danko Nikolić as an alternative explanation for a set of phenomena traditionally covered by synesthesia.
SynesthesiaSynesthesia (American English) or synaesthesia (British English) is a perceptual phenomenon in which stimulation of one sensory or cognitive pathway leads to involuntary experiences in a second sensory or cognitive pathway. People who report a lifelong history of such experiences are known as synesthetes. Awareness of synesthetic perceptions varies from person to person. In one common form of synesthesia, known as grapheme–color synesthesia or color–graphemic synesthesia, letters or numbers are perceived as inherently colored.
Feature learningIn machine learning, feature learning or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process.
Writing systemA writing system is a method of visually representing verbal communication, based on a script and a set of rules regulating its use. While both writing and speech are useful in conveying messages, writing differs in also being a reliable form of information storage and transfer. Writing systems require shared understanding between writers and readers of the meaning behind the sets of characters that make up a script.
Language processing in the brainIn psycholinguistics, language processing refers to the way humans use words to communicate ideas and feelings, and how such communications are processed and understood. Language processing is considered to be a uniquely human ability that is not produced with the same grammatical understanding or systematicity in even human's closest primate relatives. Throughout the 20th century the dominant model for language processing in the brain was the Geschwind-Lichteim-Wernicke model, which is based primarily on the analysis of brain-damaged patients.
OrthographyAn orthography is a set of conventions for writing a language, including norms of spelling, hyphenation, capitalization, word boundaries, emphasis, and punctuation. Most transnational languages in the modern period have a writing system, and most of these systems have undergone substantial standardization, thus exhibiting less dialect variation than the spoken language. These processes can fossilize pronunciation patterns that are no longer routinely observed in speech (e.g.
PhoneticsPhonetics is a branch of linguistics that studies how humans produce and perceive sounds, or in the case of sign languages, the equivalent aspects of sign. Linguists who specialize in studying the physical properties of speech are phoneticians. The field of phonetics is traditionally divided into three sub-disciplines based on the research questions involved such as how humans plan and execute movements to produce speech (articulatory phonetics), how various movements affect the properties of the resulting sound (acoustic phonetics), or how humans convert sound waves to linguistic information (auditory phonetics).
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.
Orthographic depthThe orthographic depth of an alphabetic orthography indicates the degree to which a written language deviates from simple one-to-one letter–phoneme correspondence. It depends on how easy it is to predict the pronunciation of a word based on its spelling: shallow orthographies are easy to pronounce based on the written word, and deep orthographies are difficult to pronounce based on how they are written. In shallow orthographies, the spelling-sound correspondence is direct: from the rules of pronunciation, one is able to pronounce the word correctly.
Named-entity recognitionNamed-entity recognition (NER) (also known as (named) entity identification, entity chunking, and entity extraction) is a subtask of information extraction that seeks to locate and classify named entities mentioned in unstructured text into pre-defined categories such as person names, organizations, locations, medical codes, time expressions, quantities, monetary values, percentages, etc. Most research on NER/NEE systems has been structured as taking an unannotated block of text, such as this one: Jim bought 300 shares of Acme Corp.
GlyphA glyph (ɡlɪf) is any kind of purposeful mark. In typography, a glyph is "the specific shape, design, or representation of a character". It is a particular graphical representation, in a particular typeface, of an element of written language. A grapheme, or part of a grapheme (such as a diacritic), or sometimes several graphemes in combination (a composed glyph) can be represented by a glyph. In most languages written in any variety of the Latin alphabet except English, the use of diacritics to signify a sound mutation is common.
Facial recognition systemA facial recognition system is a technology potentially capable of matching a human face from a or a video frame against a database of faces. Such a system is typically employed to authenticate users through ID verification services, and works by pinpointing and measuring facial features from a given image. Development began on similar systems in the 1960s, beginning as a form of computer application. Since their inception, facial recognition systems have seen wider uses in recent times on smartphones and in other forms of technology, such as robotics.
Word embeddingIn natural language processing (NLP), a word embedding is a representation of a word. The embedding is used in text analysis. Typically, the representation is a real-valued vector that encodes the meaning of the word in such a way that words that are closer in the vector space are expected to be similar in meaning. Word embeddings can be obtained using language modeling and feature learning techniques, where words or phrases from the vocabulary are mapped to vectors of real numbers.
