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 101–125 of 3012 papers

TitleStatusHype
CTC-synchronous Training for Monotonic Attention ModelCode1
D4AM: A General Denoising Framework for Downstream Acoustic ModelsCode1
Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimationCode1
Complex Dynamic Neurons Improved Spiking Transformer Network for Efficient Automatic Speech RecognitionCode1
BASPRO: a balanced script producer for speech corpus collection based on the genetic algorithmCode1
Adaptation of Whisper models to child speech recognitionCode1
Back Translation for Speech-to-text Translation Without TranscriptsCode1
BembaSpeech: A Speech Recognition Corpus for the Bemba LanguageCode1
Adapting End-to-End Speech Recognition for Readable SubtitlesCode1
Distilling Knowledge from Ensembles of Acoustic Models for Joint CTC-Attention End-to-End Speech RecognitionCode1
AVLnet: Learning Audio-Visual Language Representations from Instructional VideosCode1
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech TranslationCode1
DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question AnsweringCode1
DuplexMamba: Enhancing Real-time Speech Conversations with Duplex and Streaming CapabilitiesCode1
AVATAR: Unconstrained Audiovisual Speech RecognitionCode1
Efficient Neural Architecture Search for End-to-end Speech Recognition via Straight-Through GradientsCode1
EnCodecMAE: Leveraging neural codecs for universal audio representation learningCode1
End-to-end Audio-visual Speech Recognition with ConformersCode1
End-to-End Speech Recognition from Federated Acoustic ModelsCode1
Enhancing Monotonic Multihead Attention for Streaming ASRCode1
ESB: A Benchmark For Multi-Domain End-to-End Speech RecognitionCode1
Espresso: A Fast End-to-end Neural Speech Recognition ToolkitCode1
AV Taris: Online Audio-Visual Speech RecognitionCode1
Extending Whisper with prompt tuning to target-speaker ASRCode1
BENDR: using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG dataCode1
Show:102550
← PrevPage 5 of 121Next →
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