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 251–300 of 3012 papers

TitleStatusHype
End-to-End Speech Recognition and Disfluency RemovalCode1
KoSpeech: Open-Source Toolkit for End-to-End Korean Speech RecognitionCode1
Sum-Product Networks for Robust Automatic Speaker IdentificationCode1
Investigation of End-To-End Speaker-Attributed ASR for Continuous Multi-Talker RecordingsCode1
Distilling the Knowledge of BERT for Sequence-to-Sequence ASRCode1
Word Error Rate Estimation Without ASR Output: e-WER2Code1
Pretraining Techniques for Sequence-to-Sequence Voice ConversionCode1
Automatic Speech Recognition Benchmark for Air-Traffic CommunicationsCode1
AVLnet: Learning Audio-Visual Language Representations from Instructional VideosCode1
Learning to Count Words in Fluent Speech enables Online Speech RecognitionCode1
On the Comparison of Popular End-to-End Models for Large Scale Speech RecognitionCode1
Adapting End-to-End Speech Recognition for Readable SubtitlesCode1
End-to-end Named Entity Recognition from English SpeechCode1
PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASRCode1
Distilling Knowledge from Ensembles of Acoustic Models for Joint CTC-Attention End-to-End Speech RecognitionCode1
Improved Noisy Student Training for Automatic Speech RecognitionCode1
Enhancing Monotonic Multihead Attention for Streaming ASRCode1
CTC-synchronous Training for Monotonic Attention ModelCode1
ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global ContextCode1
A convolutional neural-network model of human cochlear mechanics and filter tuning for real-time applicationsCode1
ClovaCall: Korean Goal-Oriented Dialog Speech Corpus for Automatic Speech Recognition of Contact CentersCode1
Transformer based Grapheme-to-Phoneme ConversionCode1
Multi-modal Dense Video CaptioningCode1
Morfessor EM+Prune: Improved Subword Segmentation with Expectation Maximization and PruningCode1
Natural Language Processing Advancements By Deep Learning: A SurveyCode1
Unsupervised pretraining transfers well across languagesCode1
Continuous speech separation: dataset and analysisCode1
Common Voice: A Massively-Multilingual Speech CorpusCode1
Deep Contextualized Acoustic Representations For Semi-Supervised Speech RecognitionCode1
Espresso: A Fast End-to-end Neural Speech Recognition ToolkitCode1
RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data AugmentationCode1
SpecAugment: A Simple Data Augmentation Method for Automatic Speech RecognitionCode1
Mitigating the Impact of Speech Recognition Errors on Spoken Question Answering by Adversarial Domain AdaptationCode1
How2: A Large-scale Dataset for Multimodal Language UnderstandingCode1
Deep Audio-Visual Speech RecognitionCode1
Attention-based Audio-Visual Fusion for Robust Automatic Speech RecognitionCode1
Open Source Automatic Speech Recognition for GermanCode1
Zero-shot keyword spotting for visual speech recognition in-the-wildCode1
Word Error Rate Estimation for Speech Recognition: e-WERCode1
Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacesCode1
Speech Commands: A Dataset for Limited-Vocabulary Speech RecognitionCode1
Attentive Sequence-to-Sequence Learning for Diacritic Restoration of Yorùbá Language TextCode1
State-of-the-art Speech Recognition With Sequence-to-Sequence ModelsCode1
Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence ModelsCode1
A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural NetworksCode1
Single-Channel Multi-Speaker Separation using Deep ClusteringCode1
NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech—0
WhisperKit: On-device Real-time ASR with Billion-Scale Transformers—0
Lightweight Target-Speaker-Based Overlap Transcription for Practical Streaming ASR—0
AI-Generated Song Detection via Lyrics TranscriptsCode0
Show:102550
← PrevPage 6 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