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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 451–475 of 3012 papers

Title	Date	Tasks	Status	Score
Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems	Sep 13, 2017	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
AfriHuBERT: A self-supervised speech representation model for African languages	Sep 30, 2024	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
End to End ASR System with Automatic Punctuation Insertion	Dec 3, 2020	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
Advancing African-Accented Speech Recognition: Epistemic Uncertainty-Driven Data Selection for Generalizable ASR Models	Jun 3, 2023	Accented Speech RecognitionActive Learning	CodeCode Available	5
AequeVox: Automated Fairness Testing of Speech Recognition Systems	Oct 19, 2021	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
ASDF: A Differential Testing Framework for Automatic Speech Recognition Systems	Feb 11, 2023	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
Effects of Layer Freezing on Transferring a Speech Recognition System to Under-resourced Languages	Feb 8, 2021	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
Efficient Ensemble for Multimodal Punctuation Restoration using Time-Delay Neural Network	Feb 26, 2023	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generator	May 30, 2023	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
RED-ACE: Robust Error Detection for ASR using Confidence Embeddings	Mar 14, 2022	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
Analyzing the impact of speaker localization errors on speech separation for automatic speech recognition	Oct 24, 2019	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
Kurdish (Sorani) Speech to Text: Presenting an Experimental Dataset	Nov 29, 2019	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
Does Joint Training Really Help Cascaded Speech Translation?	Oct 24, 2022	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
Adversarial Training For Low-Resource Disfluency Correction	Jun 10, 2023	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation	Apr 7, 2025	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
Domain Specific Wav2vec 2.0 Fine-tuning For The SE&R 2022 Challenge	Jul 29, 2022	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
Discrete Speech Unit Extraction via Independent Component Analysis	Jan 11, 2025	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective Learning	Dec 11, 2023	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study	Aug 18, 2020	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation	Oct 18, 2022	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
Self-supervised Speech Representations Still Struggle with African American Vernacular English	Aug 26, 2024	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
BERT Attends the Conversation: Improving Low-Resource Conversational ASR	Oct 5, 2021	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
Arabic Speech Recognition by End-to-End, Modular Systems and Human	Jan 21, 2021	Arabic Speech RecognitionAutomatic Speech Recognition	CodeCode Available	5
Semantic Mask for Transformer based End-to-End Speech Recognition	Dec 6, 2019	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5
DISCO: A Large Scale Human Annotated Corpus for Disfluency Correction in Indo-European Languages	Oct 25, 2023	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	5

Show:10 25 50

← PrevPage 19 of 121Next →

All datasets LRS2 RealMAN Sagalee HUI speech corpus LRS3-TED M-AILabs speech dataset The Spoken Wikipedia Corpora Voxforge German VoxPopuli

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	TM-CTC	Test WER	10.1	—	Unverified
2	TM-seq2seq	Test WER	9.7	—	Unverified
3	CTC/attention	Test WER	8.2	—	Unverified
4	LF-MMI TDNN	Test WER	6.7	—	Unverified
5	Whisper-LLaMA	Test WER	6.6	—	Unverified
6	End2end Conformer	Test WER	3.9	—	Unverified
7	End2end Conformer	Test WER	3.7	—	Unverified
8	MoCo + wav2vec (w/o extLM)	Test WER	2.7	—	Unverified
9	CTC/Attention	Test WER	1.5	—	Unverified
10	Whisper	Test WER	1.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SpatialNet	CER	14.5	—	Unverified
2	CleanMel-L-mask	CER	14.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Conformer	Test WER	15.32	—	Unverified
2	Whisper-largev3-finetuned	Test WER	10.82	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Conformer Transducer	WER (%)	1.89	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DistillAV	WER	1.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Conformer Transducer	WER (%)	4.28	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Conformer Transducer	WER (%)	8.04	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Conformer Transducer	WER (%)	3.36	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Conformer Transducer (German)	WER (%)	8.98	—	Unverified