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 1451–1475 of 3012 papers

TitleStatusHype
Disappeared Command: Spoofing Attack On Automatic Speech Recognition Systems with Sound Masking—0
Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation—0
An Investigation of Monotonic Transducers for Large-Scale Automatic Speech Recognition—0
Automated speech tools for helping communities process restricted-access corpora for language revival efforts—0
Lombard Effect for Bilingual Speakers in Cantonese and English: importance of spectro-temporal features—0
Study of Indian English Pronunciation Variabilities relative to Received Pronunciation—0
A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes—0
Self-critical Sequence Training for Automatic Speech Recognition—0
HuBERT-EE: Early Exiting HuBERT for Efficient Speech RecognitionCode0
ASR in German: A Detailed Error Analysis—0
Building an ASR Error Robust Spoken Virtual Patient System in a Highly Class-Imbalanced Scenario Without Speech Data—0
Defense against Adversarial Attacks on Hybrid Speech Recognition using Joint Adversarial Fine-tuning with Denoiser—0
Auditory-Based Data Augmentation for End-to-End Automatic Speech Recognition—0
Unsupervised Uncertainty Measures of Automatic Speech Recognition for Non-intrusive Speech Intelligibility PredictionCode0
Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Model—0
A Wav2vec2-Based Experimental Study on Self-Supervised Learning Methods to Improve Child Speech Recognition—0
Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation—0
Audio-visual multi-channel speech separation, dereverberation and recognition—0
Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation—0
Hear No Evil: Towards Adversarial Robustness of Automatic Speech Recognition via Multi-Task Learning—0
Towards End-to-end Unsupervised Speech Recognition—0
A Complementary Joint Training Approach Using Unpaired Speech and Text for Low-Resource Automatic Speech Recognition—0
Unsupervised Data Selection via Discrete Speech Representation for ASR—0
An Analysis of Semantically-Aligned Speech-Text Embeddings—0
Deliberation Model for On-Device Spoken Language Understanding—0
Show:102550
← PrevPage 59 of 121Next →
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