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 101–150 of 3012 papers

TitleStatusHype
Earnings-22: A Practical Benchmark for Accents in the WildCode1
Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech RecognitionCode1
EnCodecMAE: Leveraging neural codecs for universal audio representation learningCode1
End-to-end Audio-visual Speech Recognition with ConformersCode1
End-to-end Named Entity Recognition from English SpeechCode1
Adaptation of Whisper models to child speech recognitionCode1
Enhancing Monotonic Multihead Attention for Streaming ASRCode1
Enhancing Multimodal Sentiment Analysis for Missing Modality through Self-Distillation and Unified Modality Cross-AttentionCode1
Adapting End-to-End Speech Recognition for Readable SubtitlesCode1
Espresso: A Fast End-to-end Neural Speech Recognition ToolkitCode1
Decentralizing Feature Extraction with Quantum Convolutional Neural Network for Automatic Speech RecognitionCode1
Continuous speech separation: dataset and analysisCode1
FAST-RIR: Fast neural diffuse room impulse response generatorCode1
Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy SpeechCode1
Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation ModelsCode1
From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech RecognitionCode1
Golos: Russian Dataset for Speech ResearchCode1
Google Crowdsourced Speech Corpora and Related Open-Source Resources for Low-Resource Languages and Dialects: An OverviewCode1
HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language ModelsCode1
HypR: A comprehensive study for ASR hypothesis revising with a reference corpusCode1
Improved Noisy Student Training for Automatic Speech RecognitionCode1
Improving Mandarin End-to-End Speech Recognition with Word N-gram Language ModelCode1
A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural NetworksCode1
Improving Self-supervised Pre-training using Accent-Specific CodebooksCode1
Incorporating External POS Tagger for Punctuation RestorationCode1
indic-punct: An automatic punctuation restoration and inverse text normalization framework for Indic languagesCode1
Consistent Training and Decoding For End-to-end Speech Recognition Using Lattice-free MMICode1
ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global ContextCode1
CopyNE: Better Contextual ASR by Copying Named EntitiesCode1
Common Voice: A Massively-Multilingual Speech CorpusCode1
Accented Speech Recognition With Accent-specific CodebooksCode1
Complex Dynamic Neurons Improved Spiking Transformer Network for Efficient Automatic Speech RecognitionCode1
Combining Frame-Synchronous and Label-Synchronous Systems for Speech RecognitionCode1
Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech RecognitionCode1
CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian PortugueseCode1
CCC-wav2vec 2.0: Clustering aided Cross Contrastive Self-supervised learning of speech representationsCode1
A convolutional neural-network model of human cochlear mechanics and filter tuning for real-time applicationsCode1
A context-aware knowledge transferring strategy for CTC-based ASRCode1
Can Contextual Biasing Remain Effective with Whisper and GPT-2?Code1
Can we use Common Voice to train a Multi-Speaker TTS system?Code1
CL-MASR: A Continual Learning Benchmark for Multilingual ASRCode1
BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control CommunicationsCode1
BembaSpeech: A Speech Recognition Corpus for the Bemba LanguageCode1
BASPRO: a balanced script producer for speech corpus collection based on the genetic algorithmCode1
BENDR: using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG dataCode1
Brazilian Portuguese Speech Recognition Using Wav2vec 2.0Code1
Advancing Test-Time Adaptation in Wild Acoustic Test SettingsCode1
AVLnet: Learning Audio-Visual Language Representations from Instructional VideosCode1
AV Taris: Online Audio-Visual Speech RecognitionCode1
A Variance-Preserving Interpolation Approach for Diffusion Models with Applications to Single Channel Speech Enhancement and RecognitionCode1
Show:102550
← PrevPage 3 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