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 1676–1700 of 3012 papers

TitleStatusHype
Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet—0
Identifying Introductions in Podcast Episodes from Automatically Generated Transcripts—0
Sub-word Level Lip Reading With Visual Attention—0
Prompt-tuning in ASR systems for efficient domain-adaptation—0
All-neural beamformer for continuous speech separation—0
Continual learning using lattice-free MMI for speech recognition—0
Word Order Does Not Matter For Speech Recognition—0
Improving Character Error Rate Is Not Equal to Having Clean Speech: Speech Enhancement for ASR Systems with Black-box Acoustic Models—0
Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric—0
A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation—0
SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition—0
Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition—0
Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy—0
DITTO: Data-efficient and Fair Targeted Subset Selection for ASR Accent Adaptation—0
Towards High-fidelity Singing Voice Conversion with Acoustic Reference and Contrastive Predictive Coding—0
Data Augmentation with Locally-time Reversed Speech for Automatic Speech Recognition—0
An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition—0
Wav2vec-S: Semi-Supervised Pre-Training for Low-Resource ASR—0
Personalized Automatic Speech Recognition Trained on Small Disordered Speech Datasets—0
A Genetic Programming Approach To Zero-Shot Neural Architecture Ranking—0
Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognition—0
Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units—0
SCaLa: Supervised Contrastive Learning for End-to-End Speech Recognition—0
Exploring Heterogeneous Characteristics of Layers in ASR Models for More Efficient Training—0
Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-trained Models—0
Show:102550
← PrevPage 68 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