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 151–200 of 3012 papers

TitleStatusHype
Radically Old Way of Computing Spectra: Applications in End-to-End ASRCode1
Automatic Speech Recognition Benchmark for Air-Traffic CommunicationsCode1
A context-aware knowledge transferring strategy for CTC-based ASRCode1
Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation ModelsCode1
A convolutional neural-network model of human cochlear mechanics and filter tuning for real-time applicationsCode1
Golos: Russian Dataset for Speech ResearchCode1
Advancing Test-Time Adaptation in Wild Acoustic Test SettingsCode1
Automatic Disfluency Detection from Untranscribed SpeechCode1
A Survey on Non-Autoregressive Generation for Neural Machine Translation and BeyondCode1
Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling InsightsCode1
A Variance-Preserving Interpolation Approach for Diffusion Models with Applications to Single Channel Speech Enhancement and RecognitionCode1
AVATAR: Unconstrained Audiovisual Speech RecognitionCode1
Accented Speech Recognition With Accent-specific CodebooksCode1
AV Taris: Online Audio-Visual Speech RecognitionCode1
BASPRO: a balanced script producer for speech corpus collection based on the genetic algorithmCode1
BembaSpeech: A Speech Recognition Corpus for the Bemba LanguageCode1
BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control CommunicationsCode1
Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimationCode1
Improving Mandarin End-to-End Speech Recognition with Word N-gram Language ModelCode1
Improving Mandarin Speech Recogntion with Block-augmented TransformerCode1
Improving Whispered Speech Recognition Performance using Pseudo-whispered based Data AugmentationCode1
Incorporating External POS Tagger for Punctuation RestorationCode1
A Systematic Comparison of Phonetic Aware Techniques for Speech EnhancementCode1
Brazilian Portuguese Speech Recognition Using Wav2vec 2.0Code1
Can we use Common Voice to train a Multi-Speaker TTS system?Code1
CCC-wav2vec 2.0: Clustering aided Cross Contrastive Self-supervised learning of speech representationsCode1
A Hybrid Continuity Loss to Reduce Over-Suppression for Time-domain Target Speaker ExtractionCode1
Investigation of End-To-End Speaker-Attributed ASR for Continuous Multi-Talker RecordingsCode1
CL-MASR: A Continual Learning Benchmark for Multilingual ASRCode1
JoeyS2T: Minimalistic Speech-to-Text Modeling with JoeyNMTCode1
ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control CommunicationsCode1
A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and EnglishCode1
Attentive Sequence-to-Sequence Learning for Diacritic Restoration of Yorùbá Language TextCode1
Automatic Speech Recognition for Speech Assessment of Persian Preschool ChildrenCode1
Combining Frame-Synchronous and Label-Synchronous Systems for Speech RecognitionCode1
Common Voice: A Massively-Multilingual Speech CorpusCode1
How Does Pre-trained Wav2Vec 2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control CommunicationsCode1
A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker OneCode1
ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversionCode1
Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech RecognitionCode1
Continuous speech separation: dataset and analysisCode1
Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy SpeechCode1
CopyNE: Better Contextual ASR by Copying Named EntitiesCode1
Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation ModelsCode1
Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across ModalitiesCode1
Cross Attention Augmented Transducer Networks for Simultaneous TranslationCode1
Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech RecognitionCode1
CTC-synchronous Training for Monotonic Attention ModelCode1
ExKaldi-RT: A Real-Time Automatic Speech Recognition Extension Toolkit of KaldiCode1
ArTST: Arabic Text and Speech TransformerCode1
Show:102550
← PrevPage 4 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