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 701–750 of 3012 papers

TitleStatusHype
Bayes Risk Transducer: Transducer with Controllable Alignment Prediction—0
Accurate synthesis of Dysarthric Speech for ASR data augmentation—0
Radio2Text: Streaming Speech Recognition Using mmWave Radio Signals—0
End-to-End Open Vocabulary Keyword Search With Multilingual Neural RepresentationsCode0
Improving CTC-AED model with integrated-CTC and auxiliary loss regularization—0
Text Injection for Capitalization and Turn-Taking Prediction in Speech Models—0
Using Text Injection to Improve Recognition of Personal Identifiers in Speech—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
OmniDataComposer: A Unified Data Structure for Multimodal Data Fusion and Infinite Data GenerationCode1
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
ÌròyìnSpeech: A multi-purpose Yorùbá Speech CorpusCode1
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
Adaptation of Whisper models to child speech recognitionCode1
A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision QuantizationCode0
Boosting Punctuation Restoration with Data Generation and Reinforcement Learning—0
Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training—0
Exploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation—0
A meta learning scheme for fast accent domain expansion in Mandarin speech recognition—0
Prompting Large Language Models with Speech Recognition Abilities—0
A Change of Heart: Improving Speech Emotion Recognition through Speech-to-Text Modality ConversionCode0
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
Transcribing Educational Videos Using Whisper: A preliminary study on using AI for transcribing educational videos—0
Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework—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
NoRefER: a Referenceless Quality Metric for Automatic Speech Recognition via Semi-Supervised Language Model Fine-Tuning with Contrastive LearningCode1
Exploring the Role of Audio in Video Captioning—0
Federated Self-Learning with Weak Supervision for Speech Recognition—0
A Reference-less Quality Metric for Automatic Speech Recognition via Contrastive-Learning of a Multi-Language Model with Self-SupervisionCode1
Learning When to Trust Which Teacher for Weakly Supervised ASR—0
Mixture Encoder for Joint Speech Separation and Recognition—0
Rehearsal-Free Online Continual Learning for Automatic Speech RecognitionCode0
MobileASR: A resource-aware on-device learning framework for user voice personalization applications on mobile phones—0
Show:102550
← PrevPage 15 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