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 201–225 of 3012 papers

TitleStatusHype
A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and EnglishCode1
The History of Speech Recognition to the Year 2030Code1
USC: An Open-Source Uzbek Speech Corpus and Initial Speech Recognition ExperimentsCode1
Brazilian Portuguese Speech Recognition Using Wav2vec 2.0Code1
Token-Level Supervised Contrastive Learning for Punctuation RestorationCode1
STRODE: Stochastic Boundary Ordinary Differential EquationCode1
A Comparison of Methods for OOV-word Recognition on a New Public DatasetCode1
Layer-wise Analysis of a Self-supervised Speech Representation ModelCode1
TENET: A Time-reversal Enhancement Network for Noise-robust ASRCode1
Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech RecognitionCode1
Combining Frame-Synchronous and Label-Synchronous Systems for Speech RecognitionCode1
Golos: Russian Dataset for Speech ResearchCode1
Learning Audio-Visual DereverberationCode1
Incorporating External POS Tagger for Punctuation RestorationCode1
Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling InsightsCode1
Lightweight Adapter Tuning for Multilingual Speech TranslationCode1
Attention-based Contextual Language Model Adaptation for Speech RecognitionCode1
Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech TranslationCode1
End-to-End Speech Recognition from Federated Acoustic ModelsCode1
LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from SpeechCode1
A Toolbox for Construction and Analysis of Speech DatasetsCode1
RNN Transducer Models For Spoken Language UnderstandingCode1
Speak or Chat with Me: End-to-End Spoken Language Understanding System with Flexible InputsCode1
ExKaldi-RT: A Real-Time Automatic Speech Recognition Extension Toolkit of KaldiCode1
Multilingual and code-switching ASR challenges for low resource Indian languagesCode1
Show:102550
← PrevPage 9 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