{"cited_by_count":1457796,"description":"This cluster of papers focuses on the advances in speech recognition technology, covering topics such as acoustic modeling using deep neural networks, speaker verification, convolutional neural networks for speech recognition, end-to-end speech recognition systems, hidden Markov models, sequence-to-sequence models, automatic speech recognition, speaker diarization, and statistical language modeling.","display_name":"Speech Recognition and Synthesis","domain_id":"3","external_ids":{"openalex":"https://openalex.org/T10201","wikipedia":"https://en.wikipedia.org/wiki/Speech_recognition"},"field_id":"17","id":"T10201","keywords":[{"display_name":"speech recognition","id":"speech-recognition","score":0.5234,"url":"https://openalex.org/keywords/speech-recognition"},{"display_name":"speech synthesis","id":"speech-synthesis","score":0.4712,"url":"https://openalex.org/keywords/speech-synthesis"},{"display_name":"text-to-speech","id":"text-to-speech","score":0.4725,"url":"https://openalex.org/keywords/text-to-speech"},{"display_name":"speaker recognition","id":"speaker-recognition","score":0.7701,"url":"https://openalex.org/keywords/speaker-recognition"},{"display_name":"speaker verification","id":"speaker-verification","score":0.8268,"url":"https://openalex.org/keywords/speaker-verification"},{"display_name":"Mel-frequency cepstral coefficients","id":"mel-frequency-cepstral-coefficients","score":0.4076,"url":"https://openalex.org/keywords/mel-frequency-cepstral-coefficients"},{"display_name":"speaker identification","id":"speaker-identification","score":0.6497,"url":"https://openalex.org/keywords/speaker-identification"},{"display_name":"word error rate","id":"word-error-rate","score":0.7238,"url":"https://openalex.org/keywords/word-error-rate"},{"display_name":"acoustic modeling","id":"acoustic-modeling","score":0.5986,"url":"https://openalex.org/keywords/acoustic-modeling"},{"display_name":"continuous speech recognition","id":"continuous-speech-recognition","score":0.8945,"url":"https://openalex.org/keywords/continuous-speech-recognition"},{"display_name":"speech corpus","id":"speech-corpus","score":0.3809,"url":"https://openalex.org/keywords/speech-corpus"},{"display_name":"speaker adaptation","id":"speaker-adaptation","score":0.8962,"url":"https://openalex.org/keywords/speaker-adaptation"},{"display_name":"speaker-independent recognition","id":"speaker-independent-speech-recognition","score":0.8659,"url":"https://openalex.org/keywords/speaker-independent-speech-recognition"},{"display_name":"isolated word recognition","id":"isolated-word-recognition","score":0.8315,"url":"https://openalex.org/keywords/isolated-word-recognition"},{"display_name":"voice conversion","id":"voice-conversion","score":0.8185,"url":"https://openalex.org/keywords/voice-conversion"},{"display_name":"speech-to-text","id":"speech-to-text","score":0.378,"url":"https://openalex.org/keywords/speech-to-text"},{"display_name":"robust speech recognition","id":"robust-speech-recognition","score":0.7498,"url":"https://openalex.org/keywords/robust-speech-recognition"},{"display_name":"speech segmentation","id":"speech-segmentation","score":0.4328,"url":"https://openalex.org/keywords/speech-segmentation"},{"display_name":"end-to-end speech recognition","id":"end-to-end-speech-recognition","score":0.9503,"url":"https://openalex.org/keywords/end-to-end-speech-recognition"},{"display_name":"speaker diarization","id":"speaker-diarization","score":0.7542,"url":"https://openalex.org/keywords/speaker-diarization"},{"display_name":"multilingual speech recognition","id":"multilingual-speech-recognition","score":0.8683,"url":"https://openalex.org/keywords/multilingual-speech-recognition"},{"display_name":"language identification","id":"language-identification","score":0.3132,"url":"https://openalex.org/keywords/language-identification"},{"display_name":"keyword spotting","id":"keyword-spotting","score":0.5029,"url":"https://openalex.org/keywords/keyword-spotting"},{"display_name":"phoneme recognition","id":"phoneme-recognition","score":0.6022,"url":"https://openalex.org/keywords/phoneme-recognition"},{"display_name":"large vocabulary speech recognition","id":"large-vocabulary-speech-recognition","score":0.8922,"url":"https://openalex.org/keywords/large-vocabulary-speech-recognition"}],"legacy_keywords":["Deep Neural Networks","Acoustic Modeling","Speaker Verification","Convolutional Neural Networks","End-to-End Speech Recognition","Hidden Markov Models","Sequence-to-Sequence Models","Automatic Speech Recognition","Speaker Diarization","Statistical Language Modeling"],"openalex_id":"https://openalex.org/T10201","source_created_date":"2024-01-23T15:27:05","source_updated_date":"2026-10-17T03:02:00","subfield_id":"1702","url":"/topics/T10201","works_api_url":"https://api.openalex.org/works?filter=topics.id:T10201","works_count":150247,"label":"Speech Recognition and Synthesis","provider":"openalex","revision":"87f6ab568d84c76f","taxonomy_revision":"f050b5d4780b1289","title":"Speech Recognition and Synthesis","kind":"topic-directory","aeo_cohort":"topic-directory","catalogue_revision":"f050b5d4780b1289","numeric_address":"36042853512283227","address_version":"morton4x16-v1","coordinates":[3,17,1702,10201],"answer_status":"Directory metadata; local answer requires separate source review","truth_status":"Subject descriptor, not a factual answer or a demonstrated knowledge gap","reviewed_answer":null}