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.
Generative pre-trained transformerGenerative pre-trained transformers (GPT) are a type of large language model (LLM) and a prominent framework for generative artificial intelligence. The first GPT was introduced in 2018 by OpenAI. GPT models are artificial neural networks that are based on the transformer architecture, pre-trained on large data sets of unlabelled text, and able to generate novel human-like content. As of 2023, most LLMs have these characteristics and are sometimes referred to broadly as GPTs.
Large language modelA large language model (LLM) is a language model characterized by its large size. Their size is enabled by AI accelerators, which are able to process vast amounts of text data, mostly scraped from the Internet. The artificial neural networks which are built can contain from tens of millions and up to billions of weights and are (pre-)trained using self-supervised learning and semi-supervised learning. Transformer architecture contributed to faster training.
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.
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.
Foundation modelsA foundation model (also called base model) is a large machine learning (ML) model trained on a vast quantity of data at scale (often by self-supervised learning or semi-supervised learning) such that it can be adapted to a wide range of downstream tasks. Foundation models have helped bring about a major transformation in how artificial intelligence (AI) systems are built, such as by powering prominent chatbots and other user-facing AI.
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.
Dialect levellingDialect levelling or leveling (in American English) is the process of an overall reduction in the variation or diversity of features between two or more dialects. Typically, this comes about through assimilation, mixture, and merging of certain dialects, often by language standardization. It has been observed in most languages with large numbers of speakers after industrialisation and modernisation of the areas in which they are spoken.
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.
Varieties of ArabicThe varieties (or dialects or vernacular languages) of Arabic, a Semitic language within the Afroasiatic family originating in the Arabian Peninsula, are the linguistic systems that Arabic speakers speak natively. There are considerable variations from region to region, with degrees of mutual intelligibility that are often related to geographical distance and some that are mutually unintelligible. Many aspects of the variability attested to in these modern variants can be found in the ancient Arabic dialects in the peninsula.
Augmentative and alternative communicationAugmentative and alternative communication (AAC) encompasses the communication methods used to supplement or replace speech or writing for those with impairments in the production or comprehension of spoken or written language. AAC is used by those with a wide range of speech and language impairments, including congenital impairments such as cerebral palsy, intellectual impairment and autism, and acquired conditions such as amyotrophic lateral sclerosis and Parkinson's disease.
Danish languageDanish (ˈdeɪnᵻʃ, ; dansk ˈtænˀsk, dansk sprog ˈtænˀsk ˈspʁɔwˀ) is a North Germanic language spoken by about six million people, principally in and around Denmark. Communities of Danish speakers are also found in Greenland, the Faroe Islands, and the northern German region of Southern Schleswig, where it has minority language status. Minor Danish-speaking communities are also found in Norway, Sweden, the United States, Canada, Brazil, and Argentina.
Speaker recognitionSpeaker recognition is the identification of a person from characteristics of voices. It is used to answer the question "Who is speaking?" The term voice recognition can refer to speaker recognition or speech recognition. Speaker verification (also called speaker authentication) contrasts with identification, and speaker recognition differs from speaker diarisation (recognizing when the same speaker is speaking).
AcronymAn acronym is a word or name consisting of parts of the full name's words. Initialisms or alphabetisms are acronyms formed from the string of initials which are usually pronounced as individual letters, as in the FBI (Federal Bureau of Investigation). But acronyms sometimes use syllables instead, as in Benelux (short for Belgium, the Netherlands, and Luxembourg), NAPOCOR (National Power Corporation), and TRANSCO (National Transmission Corporation). They can also be a mixture, as in radar (Radio Detection And Ranging) and MIDAS (Missile Defense Alarm System).
Pattern recognitionPattern recognition is the automated recognition of patterns and regularities in data. While similar, pattern recognition (PR) is not to be confused with pattern machines (PM) which may possess (PR) capabilities but their primary function is to distinguish and create emergent pattern. PR has applications in statistical data analysis, signal processing, , information retrieval, bioinformatics, data compression, computer graphics and machine learning.
Natural-language user interfaceNatural-language user interface (LUI or NLUI) is a type of computer human interface where linguistic phenomena such as verbs, phrases and clauses act as UI controls for creating, selecting and modifying data in software applications. In interface design, natural-language interfaces are sought after for their speed and ease of use, but most suffer the challenges to understanding wide varieties of ambiguous input. Natural-language interfaces are an active area of study in the field of natural-language processing and computational linguistics.
Indonesian languageIndonesian (bahasa Indonesia baˈhasa indoˈnesija) is the official and national language of Indonesia. It is a standardized variety of Malay, an Austronesian language that has been used as a lingua franca in the multilingual Indonesian archipelago for centuries. Indonesia is the fourth most populous nation in the world, with over 270 million inhabitants of which the majority speak Indonesian, which makes it one of the most widely spoken languages in the world.
Data wranglingData wrangling, sometimes referred to as data munging, is the process of transforming and mapping data from one "raw" data form into another format with the intent of making it more appropriate and valuable for a variety of downstream purposes such as analytics. The goal of data wrangling is to assure quality and useful data. Data analysts typically spend the majority of their time in the process of data wrangling compared to the actual analysis of the data.
Data PreprocessingData preprocessing can refer to manipulation or dropping of data before it is used in order to ensure or enhance performance, and is an important step in the data mining process. The phrase "garbage in, garbage out" is particularly applicable to data mining and machine learning projects. Data collection methods are often loosely controlled, resulting in out-of-range values, impossible data combinations, and missing values, amongst other issues. Analyzing data that has not been carefully screened for such problems can produce misleading results.
