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 1701–1750 of 3012 papers

TitleStatusHype
Towards High-fidelity Singing Voice Conversion with Acoustic Reference and Contrastive Predictive Coding—0
Towards Lifelong Learning of End-to-end ASR—0
Towards Maximum Likelihood Training for Transducer-based Streaming Speech Recognition—0
Towards Measuring Fairness in Speech Recognition: Casual Conversations Dataset Transcriptions—0
Continuous Silent Speech Recognition using EEG—0
Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR—0
Towards Online End-to-end Transformer Automatic Speech Recognition—0
Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation—0
Towards Probing Contact Center Large Language Models—0
Towards Processing of the Oral History Interviews and Related Printed Documents—0
Towards Quantum Language Models—0
Representative Subset Selection for Efficient Fine-Tuning in Self-Supervised Speech Recognition—0
Towards Selection of Text-to-speech Data to Augment ASR Training—0
Towards speech-to-text translation without speech recognition—0
Towards Stream Translation: Adaptive Computation Time for Simultaneous Machine Translation—0
Towards Structured Deep Neural Network for Automatic Speech Recognition—0
Towards Structured Deep Neural Network for Automatic Speech Recognition—0
Towards the Universal Defense for Query-Based Audio Adversarial Attacks—0
Unified model for code-switching speech recognition and language identification based on a concatenated tokenizer—0
Toward Streaming ASR with Non-Autoregressive Insertion-based Model—0
Towards Understanding ASR Error Correction for Medical Conversations—0
Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only—0
Towards Word-Level End-to-End Neural Speaker Diarization with Auxiliary Network—0
Towards Zero-Shot Code-Switched Speech Recognition—0
Toward Zero Oracle Word Error Rate on the Switchboard Benchmark—0
Tradition or Innovation: A Comparison of Modern ASR Methods for Forced Alignment—0
Training for Speech Recognition on Coprocessors—0
Training Neural Speech Recognition Systems with Synthetic Speech Augmentation—0
Training Neural Speech Recognition Systems with Synthetic Speech Augmentation—0
Training Speech Enhancement Systems with Noisy Speech Datasets—0
Training variance and performance evaluation of neural networks in speech—0
Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers—0
Transcending Controlled Environments Assessing the Transferability of ASRRobust NLU Models to Real-World Applications—0
TranscRater: a Tool for Automatic Speech Recognition Quality Estimation—0
Transcribe, Align and Segment: Creating speech datasets for low-resource languages—0
Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASR—0
Transcribing and Translating, Fast and Slow: Joint Speech Translation and Recognition—0
Transcribing Educational Videos Using Whisper: A preliminary study on using AI for transcribing educational videos—0
Transcription-Free Fine-Tuning of Speech Separation Models for Noisy and Reverberant Multi-Speaker Automatic Speech Recognition—0
Transcript-Prompted Whisper with Dictionary-Enhanced Decoding for Japanese Speech Annotation—0
Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition—0
Transferable Adversarial Attacks against ASR—0
Transferable and Configurable Audio Adversarial Attack from Low-Level Features—0
Transfer Learning Approaches for Streaming End-to-End Speech Recognition System—0
Transfer Learning-Based Deep Residual Learning for Speech Recognition in Clean and Noisy Environments—0
Transfer Learning for British Sign Language Modelling—0
Transfer Learning for Less-Resourced Semitic Languages Speech Recognition: the Case of Amharic—0
Transfer Learning for Robust Low-Resource Children's Speech ASR with Transformers and Source-Filter Warping—0
Transfer Learning from Adult to Children for Speech Recognition: Evaluation, Analysis and Recommendations—0
Transferring Knowledge from a RNN to a DNN—0
Show:102550
← PrevPage 35 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