SOTAVerified

Automatic Speech Recognition (ASR)

Automatic Speech Recognition (ASR) involves converting spoken language into written text. It is designed to transcribe spoken words into text in real-time, allowing people to communicate with computers, mobile devices, and other technology using their voice. The goal of Automatic Speech Recognition is to accurately transcribe speech, taking into account variations in accent, pronunciation, and speaking style, as well as background noise and other factors that can affect speech quality.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 901–925 of 3012 papers

TitleStatusHype
Differentially Private Speaker Anonymization—0
Digits micro-model for accurate and secure transactions—0
Convolutional Speech Recognition with Pitch and Voice Quality Features—0
Direct Acoustics-to-Word Models for English Conversational Speech Recognition—0
Directed Speech Separation for Automatic Speech Recognition of Long Form Conversational Speech—0
Directional ASR: A New Paradigm for E2E Multi-Speaker Speech Recognition with Source Localization—0
Convoifilter: A case study of doing cocktail party speech recognition—0
Conversational Speech Recognition Needs Data? Experiments with Austrian German—0
Effective Cross-Utterance Language Modeling for Conversational Speech Recognition—0
Aligning Pre-trained Models for Spoken Language Translation—0
Conversational Speech Recognition by Learning Audio-textual Cross-modal Contextual Representation—0
Conversational Speech Recognition By Learning Conversation-level Characteristics—0
Discourse on ASR Measurement: Introducing the ARPOCA Assessment Tool—0
Discovering Canonical Indian English Accents: A Crowdsourcing-based Approach—0
A Text-to-Speech Pipeline, Evaluation Methodology, and Initial Fine-Tuning Results for Child Speech Synthesis—0
Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection—0
A Text Normalisation System for Non-Standard English Words—0
A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems—0
Contribution \`a l'\'etude de la variabilit\'e de la voix des personnes \^ag\'ees en reconnaissance automatique de la parole (Contribution to the study of elderly people's voice variability in automatic speech recognition) [in French]—0
Discriminative Speech Recognition Rescoring with Pre-trained Language Models—0
Discriminative training of RNNLMs with the average word error criterion—0
Disentangled-Transformer: An Explainable End-to-End Automatic Speech Recognition Model with Speech Content-Context Separation—0
Contrastive Semi-supervised Learning for ASR—0
Disentangling Prosody Representations with Unsupervised Speech Reconstruction—0
ATCSpeechNet: A multilingual end-to-end speech recognition framework for air traffic control systems—0
Show:102550
← PrevPage 37 of 121Next →
All datasetsLRS2RealMANSagaleeHUI speech corpusLRS3-TEDM-AILabs speech datasetThe Spoken Wikipedia CorporaVoxforge GermanVoxPopuli

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TM-CTCTest WER10.1—Unverified
2TM-seq2seqTest WER9.7—Unverified
3CTC/attentionTest WER8.2—Unverified
4LF-MMI TDNNTest WER6.7—Unverified
5Whisper-LLaMATest WER6.6—Unverified
6End2end ConformerTest WER3.9—Unverified
7End2end ConformerTest WER3.7—Unverified
8MoCo + wav2vec (w/o extLM)Test WER2.7—Unverified
9CTC/AttentionTest WER1.5—Unverified
10WhisperTest WER1.3—Unverified
#ModelMetricClaimedVerifiedStatus
1SpatialNetCER14.5—Unverified
2CleanMel-L-maskCER14.4—Unverified
#ModelMetricClaimedVerifiedStatus
1ConformerTest WER15.32—Unverified
2Whisper-largev3-finetunedTest WER10.82—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)1.89—Unverified
#ModelMetricClaimedVerifiedStatus
1DistillAVWER1.4—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)4.28—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)8.04—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)3.36—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer Transducer (German)WER (%)8.98—Unverified