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 351–375 of 3012 papers

TitleStatusHype
Audio De-identification: A New Entity Recognition Task—0
Audio-visual Multi-channel Integration and Recognition of Overlapped Speech—0
Audio-visual Multi-channel Recognition of Overlapped Speech—0
Audio Visual Speech Recognition using Deep Recurrent Neural Networks—0
Analysis of Phonetic Transcription for Danish Automatic Speech Recognition—0
Analysis of Multilingual Sequence-to-Sequence speech recognition systems—0
Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition—0
Analysis of Manipuri Tones in ManiTo: A Tonal Contrast Database—0
An Analysis of Semantically-Aligned Speech-Text Embeddings—0
A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audio—0
Analysis of GlobalPhone and Ethiopian Languages Speech Corpora for Multilingual ASR—0
Adapting Automatic Speech Recognition for Accented Air Traffic Control Communications—0
A Comparative Study of LLM-based ASR and Whisper in Low Resource and Code Switching Scenario—0
Analyse de l'effet de la r\'everb\'eration sur la reconnaissance automatique de la parole (Analyzing how reverberation affects Automatic Speech Recognition)—0
An Adaptive Psychoacoustic Model for Automatic Speech Recognition—0
Adapting a FrameNet Semantic Parser for Spoken Language Understanding Using Adversarial Learning—0
4D ASR: Joint modeling of CTC, Attention, Transducer, and Mask-Predict decoders—0
Audio Adversarial Examples for Robust Hybrid CTC/Attention Speech Recognition—0
A Multi-Task Learning Framework for Overcoming the Catastrophic Forgetting in Automatic Speech Recognition—0
A Multi-Purpose Audio-Visual Corpus for Multi-Modal Persian Speech Recognition: the Arman-AV Dataset—0
A Multimodal Dense Retrieval Approach for Speech-Based Open-Domain Question Answering—0
A Multimodal Approach to Device-Directed Speech Detection with Large Language Models—0
Adaptation and Optimization of Automatic Speech Recognition (ASR) for the Maritime Domain in the Field of VHF Communication—0
A Comparative Analysis of Crowdsourced Natural Language Corpora for Spoken Dialog Systems—0
A Multi-Dialectal Dataset for German Dialect ASR and Dialect-to-Standard Speech Translation—0
Show:102550
← PrevPage 15 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