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 901–950 of 3012 papers

TitleStatusHype
Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation—0
Learning Speech Representation From Contrastive Token-Acoustic Pretraining—0
Contextual Biasing of Named-Entities with Large Language Models—0
Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer—0
ASTER: Automatic Speech Recognition System Accessibility Testing for Stutterers—0
Unsupervised Active Learning: Optimizing Labeling Cost-Effectiveness for Automatic Speech Recognition—0
Decoupled Structure for Improved Adaptability of End-to-End Models—0
A Small and Fast BERT for Chinese Medical Punctuation RestorationCode0
Convoifilter: A case study of doing cocktail party speech recognition—0
TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition—0
Indonesian Automatic Speech Recognition with XLSR-53—0
Bayes Risk Transducer: Transducer with Controllable Alignment Prediction—0
Radio2Text: Streaming Speech Recognition Using mmWave Radio Signals—0
Accurate synthesis of Dysarthric Speech for ASR data augmentation—0
End-to-End Open Vocabulary Keyword Search With Multilingual Neural RepresentationsCode0
Improving CTC-AED model with integrated-CTC and auxiliary loss regularization—0
Using Text Injection to Improve Recognition of Personal Identifiers in Speech—0
Text Injection for Capitalization and Turn-Taking Prediction in Speech Models—0
Integrating Emotion Recognition with Speech Recognition and Speaker Diarisation for ConversationsCode0
Bilingual Streaming ASR with Grapheme units and Auxiliary Monolingual Loss—0
A Novel Self-training Approach for Low-resource Speech Recognition—0
Comparative Analysis of the wav2vec 2.0 Feature Extractor—0
Boosting Chinese ASR Error Correction with Dynamic Error Scaling Mechanism—0
ApproBiVT: Lead ASR Models to Generalize Better Using Approximated Bias-Variance Tradeoff Guided Early Stopping and Checkpoint Averaging—0
Cascaded Cross-Modal Transformer for Request and Complaint Detection—0
On-Device Speaker Anonymization of Acoustic Embeddings for ASR based onFlexible Location Gradient Reversal Layer—0
Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training—0
A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision QuantizationCode0
Boosting Punctuation Restoration with Data Generation and Reinforcement Learning—0
A meta learning scheme for fast accent domain expansion in Mandarin speech recognition—0
Exploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation—0
A Change of Heart: Improving Speech Emotion Recognition through Speech-to-Text Modality ConversionCode0
Prompting Large Language Models with Speech Recognition Abilities—0
A Deep Dive into the Disparity of Word Error Rates Across Thousands of NPTEL MOOC VideosCode0
Model Adaptation for ASR in low-resource Indian Languages—0
Representation Learning With Hidden Unit Clustering For Low Resource Speech Applications—0
Replay to Remember: Continual Layer-Specific Fine-tuning for German Speech Recognition—0
Exploring the Integration of Large Language Models into Automatic Speech Recognition Systems: An Empirical Study—0
Speech Diarization and ASR with GMM—0
Token-Level Serialized Output Training for Joint Streaming ASR and ST Leveraging Textual Alignments—0
Online Hybrid CTC/Attention End-to-End Automatic Speech Recognition Architecture—0
Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework—0
Transcribing Educational Videos Using Whisper: A preliminary study on using AI for transcribing educational videos—0
Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Data—0
Boosting Norwegian Automatic Speech Recognition—0
Multilingual Contextual Adapters To Improve Custom Word Recognition In Low-resource Languages—0
Don't Stop Self-Supervision: Accent Adaptation of Speech Representations via Residual Adapters—0
Accelerating Transducers through Adjacent Token Merging—0
Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learning—0
The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios—0
Show:102550
← PrevPage 19 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