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 2751–2800 of 3012 papers

TitleStatusHype
Language Identification Using Deep Convolutional Recurrent Neural NetworksCode0
Audiovisual Speaker Tracking using Nonlinear Dynamical Systems with Dynamic Stream WeightsCode0
Language Modeling for Code-Switching: Evaluation, Integration of Monolingual Data, and Discriminative TrainingCode0
A Dataset for Speech Emotion Recognition in Greek Theatrical PlaysCode0
Investigating the Effects of Word Substitution Errors on Sentence EmbeddingsCode0
AequeVox: Automated Fairness Testing of Speech Recognition SystemsCode0
Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech RecognitionCode0
ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective LearningCode0
Language-Universal Adapter Learning with Knowledge Distillation for End-to-End Multilingual Speech RecognitionCode0
Boosting Cross-Domain Speech Recognition with Self-SupervisionCode0
A Small and Fast BERT for Chinese Medical Punctuation RestorationCode0
Towards Inclusive ASR: Investigating Voice Conversion for Dysarthric Speech Recognition in Low-Resource LanguagesCode0
Intrinsic evaluation of language models for code-switchingCode0
Interpersonal Relationship Labels for the CALLHOME CorpusCode0
Integrating Emotion Recognition with Speech Recognition and Speaker Diarisation for ConversationsCode0
Vietnamese Capitalization and Punctuation Recovery ModelsCode0
Large-Scale End-to-End Multilingual Speech Recognition and Language Identification with Multi-Task LearningCode0
ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech ToolkitCode0
Does Joint Training Really Help Cascaded Speech Translation?Code0
Confusion2vec 2.0: Enriching Ambiguous Spoken Language Representations with SubwordsCode0
Multimodal Grounding for Sequence-to-Sequence Speech RecognitionCode0
Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech RecognitionCode0
Arabic Dysarthric Speech Recognition Using Adversarial and Signal-Based AugmentationCode0
DoCIA: An Online Document-Level Context Incorporation Agent for Speech TranslationCode0
Confidence Score Based Speaker Adaptation of Conformer Speech Recognition SystemsCode0
Multimodal Speech Recognition for Language-Guided Embodied AgentsCode0
LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related TasksCode0
A Theory of Unsupervised Speech RecognitionCode0
Political corpus creation through automatic speech recognition on EU debatesCode0
Blank Collapse: Compressing CTC emission for the faster decodingCode0
Big model only for hard audios: Sample dependent Whisper model selection for efficient inferencesCode0
Latent Tree Language ModelCode0
Adversarial Training For Low-Resource Disfluency CorrectionCode0
A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature ExtractorsCode0
A Comparison of Adaptation Techniques and Recurrent Neural Network ArchitecturesCode0
Submodular Rank Aggregation on Score-based Permutations for Distributed Automatic Speech RecognitionCode0
The Sequence-to-Sequence Baseline for the Voice Conversion Challenge 2020: Cascading ASR and TTSCode0
Transformer Based Punctuation Restoration for TurkishCode0
Improving Voice Separation by Incorporating End-to-end Speech RecognitionCode0
Multi-Sentence Resampling: A Simple Approach to Alleviate Dataset Length Bias and Beam-Search DegradationCode0
Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal ModelsCode0
A Speech Representation Anonymization Framework via Selective Noise PerturbationCode0
Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker ChainCode0
Confidence Estimation for Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural NetworksCode0
Speech-Based Visual Question AnsweringCode0
Improving the Inclusivity of Dutch Speech Recognition by Fine-tuning Whisper on the JASMIN-CGN CorpusCode0
Improving RNN Transducer Modeling for End-to-End Speech RecognitionCode0
Bigger is not Always Better: The Effect of Context Size on Speech Pre-TrainingCode0
Bidirectional Quaternion Long-Short Term Memory Recurrent Neural Networks for Speech RecognitionCode0
Learning from Past Mistakes: Improving Automatic Speech Recognition Output via Noisy-Clean Phrase Context ModelingCode0
Show:102550
← PrevPage 56 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