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 326–350 of 3012 papers

TitleStatusHype
Recording for Eyes, Not Echoing to Ears: Contextualized Spoken-to-Written Conversion of ASR Transcripts—0
Enhancing Large Language Model-based Speech Recognition by Contextualization for Rare and Ambiguous Words—0
Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation—0
Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learning—0
Audio Enhancement for Computer Audition -- An Iterative Training Paradigm Using Sample Importance—0
LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech RecognitionCode1
VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing—0
MooER: LLM-based Speech Recognition and Translation Models from Moore ThreadsCode3
wav2graph: A Framework for Supervised Learning Knowledge Graph from SpeechCode2
MathBridge: A Large Corpus Dataset for Translating Spoken Mathematical Expressions into LaTeX Formulas for Improved Readability—0
ASR-enhanced Multimodal Representation Learning for Cross-Domain Product Retrieval—0
Self-Supervised Learning for Multi-Channel Neural Transducer—0
StreamVoice+: Evolving into End-to-end Streaming Zero-shot Voice Conversion—0
ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic FeaturesCode1
Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation—0
Towards interfacing large language models with ASR systems using confidence measures and prompting—0
On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition—0
On the Effect of Purely Synthetic Training Data for Different Automatic Speech Recognition Architectures—0
Sentiment Reasoning for HealthcareCode3
Evolutionary Prompt Design for LLM-Based Post-ASR Error CorrectionCode1
Reexamining Racial Disparities in Automatic Speech Recognition Performance: The Role of Confounding by Provenance—0
Framework for Curating Speech Datasets and Evaluating ASR Systems: A Case Study for PolishCode1
Handling Numeric Expressions in Automatic Speech Recognition—0
A light-weight and efficient punctuation and word casing prediction model for on-device streaming ASR—0
Robust ASR Error Correction with Conservative Data Filtering—0
Show:102550
← PrevPage 14 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