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 726–750 of 3012 papers

TitleStatusHype
4-bit Quantization of LSTM-based Speech Recognition Models—0
Handling Numeric Expressions in Automatic Speech Recognition—0
Audio-Visual Speech Recognition is Worth 32328 Voxels—0
Audio-Visual Speech Enhancement and Separation by Utilizing Multi-Modal Self-Supervised Embeddings—0
A Mixture of Expert Based Deep Neural Network for Improved ASR—0
Amharic-English Speech Translation in Tourism Domain—0
Adam^+: A Stochastic Method with Adaptive Variance Reduction—0
Audio-visual Recognition of Overlapped speech for the LRS2 dataset—0
Audio-visual multi-channel speech separation, dereverberation and recognition—0
Audio-visual Multi-channel Recognition of Overlapped Speech—0
Audio-visual Multi-channel Integration and Recognition of Overlapped Speech—0
A meta learning scheme for fast accent domain expansion in Mandarin speech recognition—0
ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio—0
A Code-Switching Corpus of Turkish-German Conversations—0
A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network—0
Audio Enhancement for Computer Audition -- An Iterative Training Paradigm Using Sample Importance—0
Audio De-identification - a New Entity Recognition Task—0
Alzheimer Disease Classification through ASR-based Transcriptions: Exploring the Impact of Punctuation and Pauses—0
Audio De-identification: A New Entity Recognition Task—0
Audio-conditioned phonemic and prosodic annotation for building text-to-speech models from unlabeled speech data—0
Almost Unsupervised Text to Speech and Automatic Speech Recognition—0
Audio-attention discriminative language model for ASR rescoring—0
All-neural online source separation, counting, and diarization for meeting analysis—0
A Cycle-GAN Approach to Model Natural Perturbations in Speech for ASR Applications—0
AC-Mix: Self-Supervised Adaptation for Low-Resource Automatic Speech Recognition using Agnostic Contrastive Mixup—0
Show:102550
← PrevPage 30 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