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 1601–1650 of 3012 papers

TitleStatusHype
CTC Variations Through New WFST Topologies—0
Spell my name: keyword boosted speech recognition—0
Is Attention always needed? A Case Study on Language Identification from Speech—0
BERT Attends the Conversation: Improving Low-Resource Conversational ASRCode0
Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition—0
ASR Rescoring and Confidence Estimation with ELECTRA—0
Towards efficient end-to-end speech recognition with biologically-inspired neural networks—0
Exploiting Pre-Trained ASR Models for Alzheimer's Disease Recognition Through Spontaneous Speech—0
Building a Noisy Audio Dataset to Evaluate Machine Learning Approaches for Automatic Speech Recognition Systems—0
Chinese Medical Speech Recognition with Punctuated Hypothesis—0
Exploring the Integration of E2E ASR and Pronunciation Modeling for English Mispronunciation Detection—0
Employing low-pass filtered temporal speech features for the training of ideal ratio mask in speech enhancement—0
Improving Punctuation Restoration for Speech Transcripts via External Data—0
Speech Technology for Everyone: Automatic Speech Recognition for Non-Native English with Transfer Learning—0
SpliceOut: A Simple and Efficient Audio Augmentation Method—0
Synthesising Audio Adversarial Examples for Automatic Speech Recognition—0
Conditioning Sequence-to-sequence Networks with Learned Activations—0
PhaseFool: Phase-oriented Audio Adversarial Examples via Energy Dissipation—0
Demystifying Limited Adversarial Transferability in Automatic Speech Recognition Systems—0
MLP-based architecture with variable length input for automatic speech recognition—0
Understanding the Role of Self Attention for Efficient Speech Recognition—0
W-CTC: a Connectionist Temporal Classification Loss with Wild Cards—0
Comparison of Self-Supervised Speech Pre-Training Methods on Flemish Dutch—0
FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition—0
Word-level confidence estimation for RNN transducers—0
Private Language Model Adaptation for Speech Recognition—0
Factorized Neural Transducer for Efficient Language Model AdaptationCode1
BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition—0
Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden IntermediatesCode3
Challenges and Opportunities of Speech Recognition for Bengali Language—0
Topic Model Robustness to Automatic Speech Recognition Errors in Podcast Transcripts—0
Learning Domain Specific Language Models for Automatic Speech Recognition through Machine Translation—0
iRNN: Integer-only Recurrent Neural Network—0
Audio-Visual Speech Recognition is Worth 32328 Voxels—0
MeetDot: Videoconferencing with Live Translation Captions—0
Model-Based Approach for Measuring the Fairness in ASR—0
Multimodal Audio-textual Architecture for Robust Spoken Language Understanding—0
PDAugment: Data Augmentation by Pitch and Duration Adjustments for Automatic Lyrics Transcription—0
Utterance-level neural confidence measure for end-to-end children speech recognition—0
Improving Accent Identification and Accented Speech Recognition Under a Framework of Self-supervised Learning—0
Improving Streaming Transformer Based ASR Under a Framework of Self-supervised Learning—0
Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech—0
Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech RecognitionCode1
Non-autoregressive Transformer with Unified Bidirectional Decoder for Automatic Speech Recognition—0
Multi-Sentence Resampling: A Simple Approach to Alleviate Dataset Length Bias and Beam-Search DegradationCode0
Unsupervised Domain Adaptation Schemes for Building ASR in Low-resource Languages—0
Remember the context! ASR slot error correction through memorization—0
Self-Attention Channel Combinator Frontend for End-to-End Multichannel Far-field Speech Recognition—0
Coarse-To-Fine And Cross-Lingual ASR Transfer—0
Vietnamese end-to-end speech recognition using wav2vec 2.0Code1
Show:102550
← PrevPage 33 of 61Next →
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