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 926–950 of 3012 papers

TitleStatusHype
Language Agnostic Data-Driven Inverse Text Normalization—0
From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition—0
Syllable Subword Tokens for Open Vocabulary Speech Recognition in MalayalamCode0
BayesSpeech: A Bayesian Transformer Network for Automatic Speech Recognition—0
Multi-resolution location-based training for multi-channel continuous speech separation—0
Using Kaldi for Automatic Speech Recognition of Conversational Austrian German—0
Streaming Punctuation: A Novel Punctuation Technique Leveraging Bidirectional Context for Continuous Speech Recognition—0
Audio-Visual Efficient Conformer for Robust Speech RecognitionCode1
Towards Voice Reconstruction from EEG during Imagined SpeechCode1
Memory Augmented Lookup Dictionary based Language Modeling for Automatic Speech Recognition—0
Don't Be So Sure! Boosting ASR Decoding via Confidence Relaxation—0
Skit-S2I: An Indian Accented Speech to Intent datasetCode1
Alignment Entropy Regularization—0
End-to-End Automatic Speech Recognition model for the Sudanese Dialect—0
4D ASR: Joint modeling of CTC, Attention, Transducer, and Mask-Predict decoders—0
Mu^2SLAM: Multitask, Multilingual Speech and Language Models—0
NusaCrowd: Open Source Initiative for Indonesian NLP ResourcesCode2
Fast Entropy-Based Methods of Word-Level Confidence Estimation for End-To-End Automatic Speech Recognition—0
Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language Understanding tasksCode0
Context-aware Fine-tuning of Self-supervised Speech Models—0
Speech Aware Dialog System Technology Challenge (DSTC11)—0
BLASER: A Text-Free Speech-to-Speech Translation Evaluation MetricCode2
Improving Fast-slow Encoder based Transducer with Streaming Deliberation—0
Disentangling Prosody Representations with Unsupervised Speech Reconstruction—0
Speech and Natural Language Processing Technologies for Pseudo-Pilot Simulator—0
Show:102550
← PrevPage 38 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