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 451–500 of 3012 papers

TitleStatusHype
Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative StudyCode0
Guiding Frame-Level CTC Alignments Using Self-knowledge DistillationCode0
Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification TasksCode0
Enhancing Quantised End-to-End ASR Models via PersonalisationCode0
ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech ToolkitCode0
Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation NetworkCode0
Analyzing Robustness of End-to-End Neural Models for Automatic Speech RecognitionCode0
End-to-End Speech Recognition With Joint Dereverberation Of Sub-Band Autoregressive EnvelopesCode0
A Small and Fast BERT for Chinese Medical Punctuation RestorationCode0
Explainability of Speech Recognition Transformers via Gradient-based Attention VisualizationCode0
Analyzing the impact of speaker localization errors on speech separation for automatic speech recognitionCode0
Revealing and Protecting Labels in Distributed TrainingCode0
AfriHuBERT: A self-supervised speech representation model for African languagesCode0
End-to-End Learning of Speech 2D Feature-Trajectory for Prosthetic HandsCode0
End-to-End Open Vocabulary Keyword Search With Multilingual Neural RepresentationsCode0
AequeVox: Automated Fairness Testing of Speech Recognition SystemsCode0
Segmentation-Free Streaming Machine TranslationCode0
Selective Attention Merging for low resource tasks: A case study of Child ASRCode0
End to End ASR System with Automatic Punctuation InsertionCode0
ASDF: A Differential Testing Framework for Automatic Speech Recognition SystemsCode0
Exploiting Attention-based Sequence-to-Sequence Architectures for Sound Event LocalizationCode0
Language Modeling for Code-Switching: Evaluation, Integration of Monolingual Data, and Discriminative TrainingCode0
Sequential Randomized Smoothing for Adversarially Robust Speech RecognitionCode0
EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based DecodingCode0
Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language Understanding tasksCode0
ed-cec: improving rare word recognition using asr postprocessing based on error detection and context-aware error correctionCode0
Effects of Layer Freezing on Transferring a Speech Recognition System to Under-resourced LanguagesCode0
Adversarial Training For Low-Resource Disfluency CorrectionCode0
DoCIA: An Online Document-Level Context Incorporation Agent for Speech TranslationCode0
Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical StudyCode0
Does Joint Training Really Help Cascaded Speech Translation?Code0
Arabic Speech Recognition by End-to-End, Modular Systems and HumanCode0
Discrete Cross-Modal Alignment Enables Zero-Shot Speech TranslationCode0
Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion TechniquesCode0
Arabic Dysarthric Speech Recognition Using Adversarial and Signal-Based AugmentationCode0
Discrete Speech Unit Extraction via Independent Component AnalysisCode0
Domain Specific Wav2vec 2.0 Fine-tuning For The SE&R 2022 ChallengeCode0
Did you hear that? Adversarial Examples Against Automatic Speech RecognitionCode0
A Comparative Study on Transformer vs RNN in Speech ApplicationsCode0
A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature ExtractorsCode0
A Dataset for Speech Emotion Recognition in Greek Theatrical PlaysCode0
SSR7000: A Synchronized Corpus of Ultrasound Tongue Imaging for End-to-End Silent Speech RecognitionCode0
Direct Segmentation Models for Streaming Speech TranslationCode0
BERT Attends the Conversation: Improving Low-Resource Conversational ASRCode0
Detecting Adversarial Examples for Speech Recognition via Uncertainty QuantificationCode0
Deep Learning for Audio Signal ProcessingCode0
Deep Spiking Neural Networks for Large Vocabulary Automatic Speech RecognitionCode0
DiaCorrect: End-to-end error correction for speaker diarizationCode0
DISCO: A Large Scale Human Annotated Corpus for Disfluency Correction in Indo-European LanguagesCode0
Data Fusion for Audiovisual Speaker Localization: Extending Dynamic Stream Weights to the Spatial DomainCode0
Show:102550
← PrevPage 10 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