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

Showing 27412750 of 3012 papers

TitleStatusHype
A Method to Reveal Speaker Identity in Distributed ASR Training, and How to Counter ItCode0
Iterative pseudo-forced alignment by acoustic CTC loss for self-supervised ASR domain adaptationCode0
Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification TasksCode0
Multilingual Bottleneck Features for Improving ASR Performance of Code-Switched Speech in Under-Resourced LanguagesCode0
PersonaTAB: Predicting Personality Traits using Textual, Acoustic, and Behavioral Cues in Fully-Duplex Speech DialogsCode0
Augmenting Librispeech with French Translations: A Multimodal Corpus for Direct Speech Translation EvaluationCode0
AfriHuBERT: A self-supervised speech representation model for African languagesCode0
Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance GapsCode0
Language Complexity and Speech Recognition Accuracy: Orthographic Complexity Hurts, Phonological Complexity Doesn'tCode0
Robust Unstructured Knowledge Access in Conversational Dialogue with ASR ErrorsCode0
Show:102550
← PrevPage 275 of 302Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TM-CTCTest WER10.1Unverified
2TM-seq2seqTest WER9.7Unverified
3CTC/attentionTest WER8.2Unverified
4LF-MMI TDNNTest WER6.7Unverified
5Whisper-LLaMATest WER6.6Unverified
6End2end ConformerTest WER3.9Unverified
7End2end ConformerTest WER3.7Unverified
8MoCo + wav2vec (w/o extLM)Test WER2.7Unverified
9CTC/AttentionTest WER1.5Unverified
10WhisperTest WER1.3Unverified
#ModelMetricClaimedVerifiedStatus
1SpatialNetCER14.5Unverified
2CleanMel-L-maskCER14.4Unverified
#ModelMetricClaimedVerifiedStatus
1ConformerTest WER15.32Unverified
2Whisper-largev3-finetunedTest WER10.82Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)1.89Unverified
#ModelMetricClaimedVerifiedStatus
1DistillAVWER1.4Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)4.28Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)8.04Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)3.36Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer Transducer (German)WER (%)8.98Unverified