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 1451–1475 of 3012 papers

TitleStatusHype
Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Multi-Person Video—0
Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models—0
Run-and-back stitch search: novel block synchronous decoding for streaming encoder-decoder ASR—0
Unified Multimodal Punctuation Restoration Framework for Mixed-Modality CorpusCode1
A Noise-Robust Self-supervised Pre-training Model Based Speech Representation Learning for Automatic Speech Recognition—0
Human and Automatic Speech Recognition Performance on German Oral History Interviews—0
How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR—0
DUAL: Textless Spoken Question Answering with Speech Discrete Unit Adaptive Learning—0
RED-ACE: Robust Error Detection for ASR using Confidence Embeddings—0
Recent Progress in the CUHK Dysarthric Speech Recognition System—0
Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition—0
A Likelihood Ratio based Domain Adaptation Method for E2E Models—0
Cross-Modal ASR Post-Processing System for Error Correction and Utterance Rejection—0
Neural Architecture Search For LF-MMI Trained Time Delay Neural NetworksCode0
Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset—0
Improving Mandarin End-to-End Speech Recognition with Word N-gram Language ModelCode1
Learning Audio-Visual Speech Representation by Masked Multimodal Cluster PredictionCode2
Robust Self-Supervised Audio-Visual Speech RecognitionCode2
Speech-to-SQL: Towards Speech-driven SQL Query Generation From Natural Language Question—0
Tencent-MVSE: A Large-Scale Benchmark Dataset for Multi-Modal Video Similarity Evaluation—0
Multi-Dialect Arabic Speech Recognition—0
Multi-Variant Consistency based Self-supervised Learning for Robust Automatic Speech Recognition—0
Voice Quality and Pitch Features in Transformer-Based Speech Recognition—0
Regularizing End-to-End Speech Translation with Triangular Decomposition AgreementCode1
Integrating Knowledge in End-to-End Automatic Speech Recognition for Mandarin-English Code-Switching—0
Show:102550
← PrevPage 59 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