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 2301–2350 of 3012 papers

TitleStatusHype
Understanding Shared Speech-Text Representations—0
Understanding the Role of Self Attention for Efficient Speech Recognition—0
Understanding Zero-shot Rare Word Recognition Improvements Through LLM Integration—0
Unified Autoregressive Modeling for Joint End-to-End Multi-Talker Overlapped Speech Recognition and Speaker Attribute Estimation—0
Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems—0
Unified Modeling of Multi-Domain Multi-Device ASR Systems—0
Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator—0
Unifying Streaming and Non-streaming Zipformer-based ASR—0
Unintended Memorization in Large ASR Models, and How to Mitigate It—0
Universal-2-TF: Robust All-Neural Text Formatting for ASR—0
Universal Adversarial Perturbations for Speech Recognition Systems—0
Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling—0
UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions—0
Unmanned Aerial Vehicle Control Through Domain-based Automatic Speech Recognition—0
Unsupervised Active Learning: Optimizing Labeling Cost-Effectiveness for Automatic Speech Recognition—0
Unsupervised Adaptation with Domain Separation Networks for Robust Speech Recognition—0
Unsupervised Adaptation with Interpretable Disentangled Representations for Distant Conversational Speech Recognition—0
Unsupervised and Efficient Vocabulary Expansion for Recurrent Neural Network Language Models in ASR—0
Unsupervised ASR via Cross-Lingual Pseudo-Labeling—0
Unsupervised Automatic Speech Recognition: A Review—0
Unsupervised Cross-Domain Singing Voice Conversion—0
Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces—0
Unsupervised data selection for Speech Recognition with contrastive loss ratios—0
Unsupervised Data Selection via Discrete Speech Representation for ASR—0
Unsupervised Domain Adaptation for Robust Speech Recognition via Variational Autoencoder-Based Data Augmentation—0
Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training—0
Unsupervised domain adaptation for speech recognition with unsupervised error correction—0
Unsupervised Domain Adaptation in Speech Recognition using Phonetic Features—0
Unsupervised Domain Adaptation Schemes for Building ASR in Low-resource Languages—0
Unsupervised Domain Discovery using Latent Dirichlet Allocation for Acoustic Modelling in Speech Recognition—0
Unsupervised Fine-Tuning Data Selection for ASR Using Self-Supervised Speech Models—0
Unsupervised Method for Improving Arabic Speech Recognition Systems—0
Unsupervised Model-based speaker adaptation of end-to-end lattice-free MMI model for speech recognition—0
Unsupervised morph segmentation and statistical language models for vocabulary expansion—0
Unsupervised Pattern Discovery from Thematic Speech Archives Based on Multilingual Bottleneck Features—0
Unsupervised pre-training for sequence to sequence speech recognition—0
Unsupervised Rhythm and Voice Conversion of Dysarthric to Healthy Speech for ASR—0
Unsupervised Speaker Adaptation using Attention-based Speaker Memory for End-to-End ASR—0
Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition—0
Unsupervised Stemming based Language Model for Telugu Broadcast News Transcription—0
Unveiling Biases while Embracing Sustainability: Assessing the Dual Challenges of Automatic Speech Recognition Systems—0
Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models—0
Useful Blunders: Can Automated Speech Recognition Errors Improve Downstream Dementia Classification?—0
Use of Knowledge Graph in Rescoring the N-Best List in Automatic Speech Recognition—0
User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis—0
Using Ambiguity Detection to Streamline Linguistic Annotation—0
Using Automatic Speech Recognition in Spoken Corpus Curation—0
Using English Acoustic Models for Hindi Automatic Speech Recognition—0
Using heterogeneity in semi-supervised transcription hypotheses to improve code-switched speech recognition—0
Using Kaldi for Automatic Speech Recognition of Conversational Austrian German—0
Show:102550
← PrevPage 47 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