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 1851–1900 of 3012 papers

TitleStatusHype
Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios—0
Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding—0
End-to-End Speaker-Attributed ASR with Transformer—0
Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition—0
Speaker conditioned acoustic modeling for multi-speaker conversational ASR—0
Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval—0
Towards Lifelong Learning of End-to-end ASR—0
Adversarial Joint Training with Self-Attention Mechanism for Robust End-to-End Speech Recognition—0
ExKaldi-RT: A Real-Time Automatic Speech Recognition Extension Toolkit of KaldiCode1
On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASRCode0
Context-sensitive evaluation of automatic speech recognition: considering user experience & language variation—0
Dialect Identification through Adversarial Learning and Knowledge Distillation on Romanian BERT—0
Tutorial Proposal: End-to-End Speech Translation—0
Leveraging End-to-End ASR for Endangered Language Documentation: An Empirical Study on Yol\'oxochitl Mixtec—0
Multilingual and code-switching ASR challenges for low resource Indian languagesCode1
Configurable Privacy-Preserving Automatic Speech Recognition—0
Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognition—0
Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone—0
Integer-only Zero-shot Quantization for Efficient Speech RecognitionCode1
Adversarial Attacks and Defenses for Speech Recognition Systems—0
Multiple-hypothesis CTC-based semi-supervised adaptation of end-to-end speech recognition—0
Quantifying Bias in Automatic Speech RecognitionCode0
BART based semantic correction for Mandarin automatic speech recognition system—0
Construction of a Large-scale Japanese ASR Corpus on TV Recordings—0
Leveraging pre-trained representations to improve access to untranscribed speech from endangered languagesCode1
Mutually-Constrained Monotonic Multihead Attention for Online ASR—0
Residual Energy-Based Models for End-to-End Speech Recognition—0
Radically Old Way of Computing Spectra: Applications in End-to-End ASRCode1
An Approach to Improve Robustness of NLP Systems against ASR Errors—0
Voice Privacy with Smart Digital Assistants in Educational Settings—0
Hallucination of speech recognition errors with sequence to sequence learning—0
SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition SystemsCode0
Contextual Biasing of Language Models for Speech Recognition in Goal-Oriented Conversational Agents—0
Transformer-based ASR Incorporating Time-reduction Layer and Fine-tuning with Self-Knowledge Distillation—0
Fast Development of ASR in African Languages using Self Supervised Speech Representation LearningCode1
EdgeCRNN: an edgecomputing oriented model of acoustic feature enhancement for keyword spotting—0
Dynamic Acoustic Unit Augmentation With BPE-Dropout for Low-Resource End-to-End Speech Recognition—0
A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training—0
Learning Word-Level Confidence For Subword End-to-End ASR—0
Best of Both Worlds: Robust Accented Speech Recognition with Adversarial Transfer Learning—0
Contrastive Semi-supervised Learning for ASR—0
A Parallelizable Lattice Rescoring Strategy with Neural Language ModelsCode3
An Ultra-low Power RNN Classifier for Always-On Voice Wake-Up Detection Robust to Real-World Scenarios—0
Neural model robustness for skill routing in large-scale conversational AI systems: A design choice exploration—0
WaveGuard: Understanding and Mitigating Audio Adversarial ExamplesCode1
Incorporating VAD into ASR System by Multi-task Learning—0
Alignment Knowledge Distillation for Online Streaming Attention-based Speech Recognition—0
Brain Signals to Rescue Aphasia, Apraxia and Dysarthria Speech Recognition—0
Exploiting Attention-based Sequence-to-Sequence Architectures for Sound Event LocalizationCode0
Meta-Learning for improving rare word recognition in end-to-end ASR—0
Show:102550
← PrevPage 38 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