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 1151–1175 of 3012 papers

TitleStatusHype
Bridging Speech and Textual Pre-trained Models with Unsupervised ASR—0
Evaluation of Off-the-shelf Speech Recognizers Across Diverse Dialogue Domains—0
Evaluation of Off-the-shelf Speech Recognizers on Different Accents in a Dialogue Domain—0
Evaluation of real-time transcriptions using end-to-end ASR models—0
Everyone deserves their voice to be heard: Analyzing Predictive Gender Bias in ASR Models Applied to Dutch Speech Data—0
Everything Can Be Described in Words: A Simple Unified Multi-Modal Framework with Semantic and Temporal Alignment—0
Evolutionary optimization of contexts for phonetic correction in speech recognition systems—0
Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept—0
E-PUR: An Energy-Efficient Processing Unit for Recurrent Neural Networks—0
BLSTM-Based Confidence Estimation for End-to-End Speech Recognition—0
Bridging the Modality Gap: Softly Discretizing Audio Representation for LLM-based Automatic Speech Recognition—0
Exploiting Beam Search Confidence for Energy-Efficient Speech Recognition—0
Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition—0
Exploiting Cross-domain And Cross-Lingual Ultrasound Tongue Imaging Features For Elderly And Dysarthric Speech Recognition—0
An Investigative Study of Multi-Modal Cross-Lingual Retrieval—0
Exploiting Cross-Lingual Speaker and Phonetic Diversity for Unsupervised Subword Modeling—0
Exploiting Nontrivial Connectivity for Automatic Speech Recognition—0
Exploiting Pre-Trained ASR Models for Alzheimer's Disease Recognition Through Spontaneous Speech—0
Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition—0
Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding—0
Environment-aware Reconfigurable Noise Suppression—0
Exploiting the large-scale German Broadcast Corpus to boost the Fraunhofer IAIS Speech Recognition System—0
Exploration of Adapter for Noise Robust Automatic Speech Recognition—0
Exploration of End-to-End ASR for OpenSTT -- Russian Open Speech-to-Text Dataset—0
Entity resolution for noisy ASR transcripts—0
Show:102550
← PrevPage 47 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