Research any topic before you write.

Find related topics. | Discover entities. | See connections. | Build a topical map.

Speech recognition

Speech recognition (automatic speech recognition (ASR), computer speech recognition, or speech-to-text (STT)) is a sub-field of computational linguistics concerned with methods and technologies that translate spoken language into text or other interpretable forms.

History, Applications, Technology & Products

Use the mouse wheel or two fingers (on touchscreens) to zoom in and out of the map.

Research this topic

Explore the main themes, entities and connections around Speech recognition. Start with the topic map, then use the sections below for research and deeper semantic analysis.

Explore this topic

Start with a few of the strongest sections from the source topic. These are research directions, not a list of keywords you must use.

Topics to explore

Browse the full topic structure. Each item opens a new analysis centered on that subject.

Overview

History

Models, methods, and algorithms

Applications

Performance

Further information

Advanced semantic analysis

Deeper signals for content research, entity SEO and topical coverage. The plain-language headings explain what each technical view is useful for.

Map overview Semantic statistics

Speech recognition

Nodes240
Edges239
Triples275
Avg. degree1.99
Density0.008333
Components1

How this topic connects Entity context

See the strongest relationship patterns around the current topic before diving into the raw triples.

Speech recognition

Top relations

related to Further reading · 77
Speech recognition → Advanced, Andrew, Annie, Applications, Australia, Automatic Speech Recognition, Beat, Building Computers That Understand, Business Media, Cambridge Studies, Cambridge University Press, Clare-Marie, Cole, Conversational Interface Technologies, David, December, Distant Speech Recognition, Efficient Controller-free Text Entry, Emerging Applications, Ergonomics
related to Books · 31
Speech recognition → Applications, Building Computers That Understand, Computer Speech, Deep Learning Approach, Deng, DNN-based, Doug O'Shaughnessey, Dynamic, Frederick JelinekSpoken Language Processing, Fundamentals, IntroductionAutomatic Speech Recognition, Jurafsky, Language Processing, Lawrence Rabiner, Learning, Li Deng, Machine, Manfred, Martin, Methods
related to 1970–1990 · 26
Speech recognition → Baker, BBN, Carnegie Mellon, CMU, DARPA, Defense Analysis, During, HMM, HMMs, IBM, ICASSP, Institute, James Baker, Janet, Leonard Baum, Markov, Massachusetts, Newton, Philadelphia, Raj Reddy's
related to Pre-1970 · 26
Speech recognition → Audrey, Bell Labs, Biddulph, Davis, Flanagan, Fumitada Itakura, Funding, Gunnar Fant, IBM's, James, John, Linear, Nagoya University, Nippon Telegraph, Pierce, Previous, Raj Reddy, Reddy's, Shoebox, Shuzo Saito
related to Education · 13
Speech recognition → Also, Amira Learning, Assessing, Automatic, CALL, CAPT, CEFR, Common European Framework, In, Languages, Microsoft Teams, Pronunciation, Reference
related to Hidden Markov models · 12
Speech recognition → An HMM, Each, Fourier, Gaussians, HMM, HMMs, In, Markov, Speech, The, The HMM, These
related to Software · 11
Speech recognition → Android, APIs, Commercial, Common Voice, Coqui STT, Gboard, HTK, Microsoft Windows, Speech, Sphinx, TensorFlow
related to Performance · 10
Speech recognition → Accuracy, Command Success Rate, CSR, Other, Single Word Error Rate, Speech, SWER, The, Vocalizations, WER
related to Security · 9
Speech recognition → Alexa, Attackers, For, One, Speech, The, They, Two, Voice-controlled
see also · 7
Speech recognition → AI, Language Tags, Language TranslatorAutomotive, LinuxSpeech, NaturallySpeakingFluency Voice TechnologyGoogle Voice, SearchIBM ViaVoiceKeyword, VoiceXMLVoxForgeWindows Speech Recognition List

Important terminology Word statistics

Use these terms to understand the vocabulary surrounding the topic, not as a checklist for keyword stuffing.

Important terminology

speech recognition language used voice systems use model applications speaker learning system neural models words many word using deep hmm

Entity relationships Subject–Predicate–Object triples

SubjectPredicateObjectConfidenceSrc
Speech recognitionis amulti-level pattern recognition task.Acoustic signals are structured into a hierarchy of units0.90text
10instance ofwhere n is an integer0.80text
individual phonemesinstance ofin spite of their effectiveness in classifying short-time units0.80text
isolated wordsinstance ofin spite of their effectiveness in classifying short-time units0.80text
early neural networks were rarely successful for continuous recognition because of their limited ability to model temporal dependencies.One approach was to use neural networks for feature transformationinstance ofin spite of their effectiveness in classifying short-time units0.80text
or dimensionality reductioninstance ofin spite of their effectiveness in classifying short-time units0.80text
intonationinstance ofsometimes with inconsequential prosody0.80text
pitchinstance ofsometimes with inconsequential prosody0.80text
tempoinstance ofsometimes with inconsequential prosody0.80text
rhythminstance ofsometimes with inconsequential prosody0.80text
and stressinstance ofsometimes with inconsequential prosody0.80text
Microsoft Teamsinstance offor example in products0.80text

Related concept clusters Concept neighborhoods

These clusters group vocabulary that occurs around closely connected concepts in the source material.

    Connections between topic areas Semantic bridges

    Bridges can reveal useful research angles that are easy to miss in a flat list of related terms.

    Min side: 3
    For writers, content strategists, SEOs, marketers and creators — from quick topic research to advanced semantic analysis.