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 681–690 of 3012 papers

Title	Date	Tasks	Status
Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model	Apr 6, 2021	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified
Comparing Discrete and Continuous Space LLMs for Speech Recognition	Sep 1, 2024	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified
A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spotting	Sep 18, 2023	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified
Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures	Apr 12, 2021	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified
Comparing Two Basic Methods for Discriminating Between Similar Languages and Varieties	Dec 1, 2016	Automatic Speech Recognition (ASR)General Classification	—Unverified
ASR Error Detection via Audio-Transcript entailment	Jul 22, 2022	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified
Comparison of Grapheme-to-Phoneme Conversion Methods on a Myanmar Pronunciation Dictionary	Dec 1, 2016	Active LearningAutomatic Speech Recognition	—Unverified
Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR	Jul 1, 2019	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified
Comparison of Self-Supervised Speech Pre-Training Methods on Flemish Dutch	Sep 29, 2021	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified
Artificial Neural Networks to Recognize Speakers Division from Continuous Bengali Speech	Apr 18, 2024	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	—Unverified

Show:10 25 50

← PrevPage 69 of 302Next →

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