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 2176–2200 of 3012 papers

TitleStatusHype
Adapting End-to-End Speech Recognition for Readable SubtitlesCode1
An End-to-End Mispronunciation Detection System for L2 English Speech Leveraging Novel Anti-Phone Modeling—0
An Audio-enriched BERT-based Framework for Spoken Multiple-choice Question Answering—0
Detecting Adversarial Examples for Speech Recognition via Uncertainty QuantificationCode0
End-to-end Named Entity Recognition from English SpeechCode1
Large scale evaluation of importance maps in automatic speech recognition—0
PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASRCode1
Investigation of Large-Margin Softmax in Neural Language Modeling—0
Early Stage LM Integration Using Local and Global Log-Linear Combination—0
A Comparison of Label-Synchronous and Frame-Synchronous End-to-End Models for Speech Recognition—0
Improving Proper Noun Recognition in End-to-End ASR By Customization of the MWER Loss Criterion—0
Iterative Pseudo-Labeling for Speech RecognitionCode0
Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech RecognitionCode0
Improved Noisy Student Training for Automatic Speech RecognitionCode1
Enhancing Monotonic Multihead Attention for Streaming ASRCode1
A systematic comparison of grapheme-based vs. phoneme-based label units for encoder-decoder-attention models—0
Distilling Knowledge from Ensembles of Acoustic Models for Joint CTC-Attention End-to-End Speech RecognitionCode1
An Effective End-to-End Modeling Approach for Mispronunciation Detection—0
Audio-visual Multi-channel Recognition of Overlapped Speech—0
Weak-Attention Suppression For Transformer Based Speech Recognition—0
Quaternion Neural Networks for Multi-channel Distant Speech Recognition—0
Dynamic Sparsity Neural Networks for Automatic Speech Recognition—0
AccentDB: A Database of Non-Native English Accents to Assist Neural Speech Recognition—0
Reducing Spelling Inconsistencies in Code-Switching ASR using Contextualized CTC Loss—0
Conformer: Convolution-augmented Transformer for Speech RecognitionCode3
Show:102550
← PrevPage 88 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