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 901–925 of 3012 papers

TitleStatusHype
Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentation—0
MADI: Inter-domain Matching and Intra-domain Discrimination for Cross-domain Speech Recognition—0
UML: A Universal Monolingual Output Layer for Multilingual ASR—0
Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech RecognitionCode1
Connecting Humanities and Social Sciences: Applying Language and Speech Technology to Online Panel Surveys—0
An ASR-free Fluency Scoring Approach with Self-Supervised Learning—0
Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition—0
A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker OneCode1
Speaker and Language Change Detection using Wav2vec2 and Whisper—0
Massively Multilingual Shallow Fusion with Large Language Models—0
Stabilising and accelerating light gated recurrent units for automatic speech recognition—0
Adaptive Axonal Delays in feedforward spiking neural networks for accurate spoken word recognition—0
Speaker Change Detection for Transformer Transducer ASR—0
Adaptable End-to-End ASR Models using Replaceable Internal LMs and Residual Softmax—0
Confidence Score Based Speaker Adaptation of Conformer Speech Recognition SystemsCode0
ASR Bundestag: A Large-Scale political debate dataset in German—0
ASDF: A Differential Testing Framework for Automatic Speech Recognition SystemsCode0
PATCorrect: Non-autoregressive Phoneme-augmented Transformer for ASR Error Correction—0
Leveraging supplementary text data to kick-start automatic speech recognition system development with limited transcriptions—0
MAC: A unified framework boosting low resource automatic speech recognition—0
Complex Dynamic Neurons Improved Spiking Transformer Network for Efficient Automatic Speech RecognitionCode1
Improving Rare Words Recognition through Homophone Extension and Unified Writing for Low-resource Cantonese Speech Recognition—0
Fillers in Spoken Language Understanding: Computational and Psycholinguistic Perspectives—0
Unsupervised Data Selection for TTS: Using Arabic Broadcast News as a Case StudyCode0
A Multi-Purpose Audio-Visual Corpus for Multi-Modal Persian Speech Recognition: the Arman-AV Dataset—0
Show:102550
← PrevPage 37 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