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 826–850 of 3012 papers

TitleStatusHype
Adversarial Speaker Disentanglement Using Unannotated External Data for Self-supervised Representation Based Voice Conversion—0
Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech RecognitionCode1
Critical Appraisal of Artificial Intelligence-Mediated Communication—0
OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking—0
Back Translation for Speech-to-text Translation Without TranscriptsCode1
Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations—0
Investigating the Sensitivity of Automatic Speech Recognition Systems to Phonetic Variation in L2 Englishes—0
Masked Audio Text Encoders are Effective Multi-Modal Rescorers—0
Quran Recitation Recognition using End-to-End Deep Learning—0
Who Needs Decoders? Efficient Estimation of Sequence-level Attributes—0
Exploration of Language Dependency for Japanese Self-Supervised Speech Representation Models—0
Multi-Temporal Lip-Audio Memory for Visual Speech Recognition—0
Lookahead When It Matters: Adaptive Non-causal Transformers for Streaming Neural Transducers—0
Employing Hybrid Deep Neural Networks on Dari Speech—0
Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks—0
End-to-end spoken language understanding using joint CTC loss and self-supervised, pretrained acoustic encoders—0
A Study on the Integration of Pipeline and E2E SLU systems for Spoken Semantic Parsing toward STOP Quality Challenge—0
Building a Non-native Speech Corpus Featuring Chinese-English Bilingual Children: Compilation and Rationale—0
Towards Better Domain Adaptation for Self-supervised Models: A Case Study of Child ASRCode0
Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization—0
Understanding Shared Speech-Text Representations—0
Self-regularised Minimum Latency Training for Streaming Transformer-based Speech Recognition—0
Non-autoregressive End-to-end Approaches for Joint Automatic Speech Recognition and Spoken Language Understanding—0
OLISIA: a Cascade System for Spoken Dialogue State TrackingCode0
Towards the Universal Defense for Query-Based Audio Adversarial Attacks—0
Show:102550
← PrevPage 34 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