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 151–200 of 3012 papers

TitleStatusHype
FlanEC: Exploring Flan-T5 for Post-ASR Error CorrectionCode1
Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio—0
GEC-RAG: Improving Generative Error Correction via Retrieval-Augmented Generation for Automatic Speech Recognition Systems—0
A Benchmark of French ASR Systems Based on Error Severity—0
Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR—0
Adapting Whisper for Regional Dialects: Enhancing Public Services for Vulnerable Populations in the United Kingdom—0
persoDA: Personalized Data Augmentation for Personalized ASR—0
Selective Attention Merging for low resource tasks: A case study of Child ASRCode0
AdaCS: Adaptive Normalization for Enhanced Code-Switching ASRCode0
Speech Recognition for Automatically Assessing Afrikaans and isiXhosa Preschool Oral Narratives—0
Discrete Speech Unit Extraction via Independent Component AnalysisCode0
Universal-2-TF: Robust All-Neural Text Formatting for ASR—0
Comparing Self-Supervised Learning Models Pre-Trained on Human Speech and Animal Vocalizations for Bioacoustics ProcessingCode0
Contextual ASR Error Handling with LLMs Augmentation for Goal-Oriented Conversational AI—0
Benchmarking Rotary Position Embeddings for Automatic Speech Recognition—0
Samba-ASR: State-Of-The-Art Speech Recognition Leveraging Structured State-Space Models—0
Listening and Seeing Again: Generative Error Correction for Audio-Visual Speech RecognitionCode0
Improving Transducer-Based Spoken Language Understanding with Self-Conditioned CTC and Knowledge Transfer—0
Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal ModelsCode0
LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale—0
DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech RecognitionCode2
Zero-resource Speech Translation and Recognition with LLMs—0
UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition—0
Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition—0
Enhancing Multilingual ASR for Unseen Languages via Language Embedding Modeling—0
Adapting Whisper for Code-Switching through Encoding Refining and Language-Aware Decoding—0
Speech Retrieval-Augmented Generation without Automatic Speech Recognition—0
TouchASP: Elastic Automatic Speech Perception that Everyone Can Touch—0
MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-FormulaCode1
Transcribing and Translating, Fast and Slow: Joint Speech Translation and Recognition—0
LAMA-UT: Language Agnostic Multilingual ASR through Orthography Unification and Language-Specific Transliteration—0
Streaming Keyword Spotting Boosted by Cross-layer Discrimination ConsistencyCode2
Speak & Improve Corpus 2025: an L2 English Speech Corpus for Language Assessment and Feedback—0
Speak & Improve Challenge 2025: Tasks and Baseline Systems—0
Greek2MathTex: A Greek Speech-to-Text Framework for LaTeX Equations GenerationCode0
Harnessing Transfer Learning from Swahili: Advancing Solutions for Comorian Dialects—0
Leveraging Prompt Learning and Pause Encoding for Alzheimer's Disease Detection—0
Effective Text Adaptation for LLM-based ASR through Soft Prompt Fine-Tuning—0
Not All Errors Are Equal: Investigation of Speech Recognition Errors in Alzheimer's Disease Detection—0
Comprehensive Audio Query Handling System with Integrated Expert Models and Contextual Understanding—0
ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correction—0
GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken ChatbotCode7
Late fusion ensembles for speech recognition on diverse input audio representations—0
A Comparative Study of LLM-based ASR and Whisper in Low Resource and Code Switching Scenario—0
Empowering the Deaf and Hard of Hearing Community: Enhancing Video Captions Using Large Language Models—0
How to Learn a New Language? An Efficient Solution for Self-Supervised Learning Models Unseen Languages Adaption in Low-Resource Scenario—0
AMPS: ASR with Multimodal Paraphrase Supervision—0
Continual Learning in Machine Speech Chain Using Gradient Episodic Memory—0
Aligning Pre-trained Models for Spoken Language Translation—0
Enhancing Code-Switching ASR Leveraging Non-Peaky CTC Loss and Deep Language Posterior Injection—0
Show:102550
← PrevPage 4 of 61Next →
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