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 876–900 of 3012 papers

TitleStatusHype
Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative StudyCode0
Transcription free filler word detection with Neural semi-CRFsCode0
MIXPGD: Hybrid Adversarial Training for Speech Recognition Systems—0
Clinical BERTScore: An Improved Measure of Automatic Speech Recognition Performance in Clinical Settings—0
wav2vec and its current potential to Automatic Speech Recognition in German for the usage in Digital History: A comparative assessment of available ASR-technologies for the use in cultural heritage contexts—0
End-to-End Speech Recognition: A Survey—0
Leveraging Large Text Corpora for End-to-End Speech Summarization—0
Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages—0
Leveraging Redundancy in Multiple Audio Signals for Far-Field Speech Recognition—0
N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space—0
Language-Universal Adapter Learning with Knowledge Distillation for End-to-End Multilingual Speech RecognitionCode0
Deep Visual Forced Alignment: Learning to Align Transcription with Talking Face Video—0
Diacritic Recognition Performance in Arabic ASR—0
MoLE : Mixture of Language Experts for Multi-Lingual Automatic Speech Recognition—0
Improving Medical Speech-to-Text Accuracy with Vision-Language Pre-training Model—0
A Comparison of Speech Data Augmentation Methods Using S3PRL Toolkit—0
Multimodal Speech Recognition for Language-Guided Embodied AgentsCode0
A low latency attention module for streaming self-supervised speech representation learningCode0
Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator—0
Speech Corpora Divergence Based Unsupervised Data Selection for ASR—0
Efficient Ensemble for Multimodal Punctuation Restoration using Time-Delay Neural NetworkCode0
Factual Consistency Oriented Speech Recognition—0
Ensemble knowledge distillation of self-supervised speech models—0
Improving Massively Multilingual ASR With Auxiliary CTC Objectives—0
Evaluating Automatic Speech Recognition in an Incremental Setting—0
Show:102550
← PrevPage 36 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