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 1951–1975 of 3012 papers

TitleStatusHype
Latent Dirichlet Allocation Based Acoustic Data Selection for Automatic Speech Recognition—0
Lattention: Lattice-attention in ASR rescoring—0
Lattice-based Improvements for Voice Triggering Using Graph Neural Networks—0
Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers—0
Lattice Rescoring Based on Large Ensemble of Complementary Neural Language Models—0
Lattice Transformer for Speech Translation—0
Layer Pruning on Demand with Intermediate CTC—0
Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition—0
Learned Transferable Architectures Can Surpass Hand-Designed Architectures for Large Scale Speech Recognition—0
LearnerVoice: A Dataset of Non-Native English Learners' Spontaneous Speech—0
Learning a Dual-Mode Speech Recognition Model via Self-Pruning—0
Learning a Neural Diff for Speech Models—0
Learning ASR pathways: A sparse multilingual ASR model—0
Learning Domain Specific Language Models for Automatic Speech Recognition through Machine Translation—0
Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition—0
Learning linearly separable features for speech recognition using convolutional neural networks—0
Learning not to Discriminate: Task Agnostic Learning for Improving Monolingual and Code-switched Speech Recognition—0
Learning Robust Dialog Policies in Noisy Environments—0
Learnings from curating a trustworthy, well-annotated, and useful dataset of disordered English speech—0
Learning Similarity Functions for Pronunciation Variations—0
Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition—0
Learning to Jointly Transcribe and Subtitle for End-to-End Spontaneous Speech Recognition—0
Learning to Recognize Code-switched Speech Without Forgetting Monolingual Speech Recognition—0
Learning When to Trust Which Teacher for Weakly Supervised ASR—0
Learning without Forgetting: Task Aware Multitask Learning for Multi-Modality Tasks—0
Show:102550
← PrevPage 79 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