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 51–100 of 3012 papers

TitleStatusHype
4-bit Conformer with Native Quantization Aware Training for Speech RecognitionCode2
CMGAN: Conformer-based Metric GAN for Speech EnhancementCode2
Learning Audio-Visual Speech Representation by Masked Multimodal Cluster PredictionCode2
Robust Self-Supervised Audio-Visual Speech RecognitionCode2
Fast Transformers with Clustered AttentionCode2
Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across ModalitiesCode1
From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech RecognitionCode1
DuplexMamba: Enhancing Real-time Speech Conversations with Duplex and Streaming CapabilitiesCode1
VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR IdentificationCode1
Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation ModelsCode1
Sagalee: an Open Source Automatic Speech Recognition Dataset for Oromo LanguageCode1
FlanEC: Exploring Flan-T5 for Post-ASR Error CorrectionCode1
MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-FormulaCode1
Enhancing Multimodal Sentiment Analysis for Missing Modality through Self-Distillation and Unified Modality Cross-AttentionCode1
VHASR: A Multimodal Speech Recognition System With Vision HotwordsCode1
Mamba for Streaming ASR Combined with Unimodal AggregationCode1
LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech RecognitionCode1
ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic FeaturesCode1
Evolutionary Prompt Design for LLM-Based Post-ASR Error CorrectionCode1
Framework for Curating Speech Datasets and Evaluating ASR Systems: A Case Study for PolishCode1
Vibravox: A Dataset of French Speech Captured with Body-conduction Audio SensorsCode1
Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation ModelsCode1
Improving Self-supervised Pre-training using Accent-Specific CodebooksCode1
Pinyin Regularization in Error Correction for Chinese Speech Recognition with Large Language ModelsCode1
ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMsCode1
Automatic speech recognition for the Nepali language using CNN, bidirectional LSTM and ResNetCode1
Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy SpeechCode1
LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech RecognitionCode1
A Variance-Preserving Interpolation Approach for Diffusion Models with Applications to Single Channel Speech Enhancement and RecognitionCode1
SoccerNet-Echoes: A Soccer Game Audio Commentary DatasetCode1
Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation ModelsCode1
Unveiling the Potential of LLM-Based ASR on Chinese Open-Source DatasetsCode1
Less Peaky and More Accurate CTC Forced Alignment by Label PriorsCode1
Speech Robust Bench: A Robustness Benchmark For Speech RecognitionCode1
A Cross-Modal Approach to Silent Speech with LLM-Enhanced RecognitionCode1
It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech RecognitionCode1
REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASRCode1
Word-Level ASR Quality Estimation for Efficient Corpus Sampling and Post-Editing through Analyzing Attentions of a Reference-Free MetricCode1
Extending Whisper with prompt tuning to target-speaker ASRCode1
D4AM: A General Denoising Framework for Downstream Acoustic ModelsCode1
Improving Whispered Speech Recognition Performance using Pseudo-whispered based Data AugmentationCode1
Improved Child Text-to-Speech Synthesis through Fastpitch-based Transfer LearningCode1
Multilingual DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific ExpertsCode1
Automatic Disfluency Detection from Untranscribed SpeechCode1
Developing a Multilingual Dataset and Evaluation Metrics for Code-Switching: A Focus on Hong Kong's Polylingual DynamicsCode1
CL-MASR: A Continual Learning Benchmark for Multilingual ASRCode1
ArTST: Arabic Text and Speech TransformerCode1
Accented Speech Recognition With Accent-specific CodebooksCode1
Advancing Test-Time Adaptation in Wild Acoustic Test SettingsCode1
Speech collage: code-switched audio generation by collaging monolingual corporaCode1
Show:102550
← PrevPage 2 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