Speech recognition

Speech recognition is an <a href="/facts/Interdisciplinary/HP0uaNUs">interdisciplinary</a> subfield of <a href="/facts/Computer_science/lN3pEyPz">computer science</a> and <a href="/facts/Computational_linguistics/XmegJ6LC">computational linguistics</a> that develops <a href="/facts/Methodology/dk5X9Hxx">methodologies</a> and technologies that enable the recognition and <a href="/facts/Translation/2foI82so">translation</a> 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 <a href="/facts/Computer_science/lN3pEyPz">computer science</a>, <a href="/facts/Linguistics/oQuamvf2">linguistics</a> and <a href="/facts/Computer_engineering/5x1TRKGo">computer engineering</a> fields. The reverse process is <a href="/facts/Speech_synthesis/ceTczTv9">speech synthesis</a>.
Some speech recognition systems require "training" (also called "enrollment") where an individual speaker reads text or isolated <a href="/facts/Vocabulary/gUfoY6TJ">vocabulary</a> into the system. The system analyzes the person's specific voice and uses it to fine-tune the recognition of that person's speech, resulting in increased accuracy. Systems that do not use training are called "speaker-independent" systems. Systems that use training are called "speaker dependent".
Speech recognition applications include <a href="/facts/Voice_user_interface/jkdI6nGy">voice user interfaces</a> such as voice dialing (e.g. "call home"), call routing (e.g. "I would like to make a collect call"), <a href="/facts/Domotic/kfz6C07m">domotic</a> appliance control, search key words (e.g. find a podcast where particular words were spoken), simple data entry (e.g., entering a credit card number), preparation of structured documents (e.g. a radiology report), determining speaker characteristics, speech-to-text processing (e.g., <a href="/facts/Word_processor/qAR7lagF">word processors</a> or <a href="/facts/Email/6pD9GLtI">emails</a>), and <a href="/facts/Aircraft/EhC4mBep">aircraft</a> (usually termed <a href="/facts/Direct_voice_input/PYl1y7es">direct voice input</a>). Automatic <a href="/facts/Pronunciation_assessment/EbahMuLF">pronunciation assessment</a> is used in education such as for spoken language learning.
The term voice recognition or <a href="/facts/Speaker_recognition/9Td6nPY7">speaker identification</a> refers to identifying the speaker, rather than what they are saying. <a href="/facts/Speaker_recognition/9Td6nPY7">Recognizing the speaker</a> can simplify the task of <a href="/facts/Speech_translation/AsaTBR5b">translating speech</a> in systems that have been trained on a specific person's voice or it can be used to <a href="/facts/Authentication/64y4S69b">authenticate</a> or verify the identity of a speaker as part of a security process.
From the technology perspective, speech recognition has a long history with several waves of major innovations. Most recently, the field has benefited from advances in <a href="/facts/Deep_learning/JLuwD3ea">deep learning</a> and <a href="/facts/Big_data/XGtrVg4z">big data</a>. The advances are evidenced not only by the surge of academic papers published in the field, but more importantly by the worldwide industry adoption of a variety of deep learning methods in designing and deploying speech recognition systems.

Speech recognition open-in-new

Speech recognition