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 1351–1375 of 3012 papers

TitleStatusHype
Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptation—0
Homophone-based Label Smoothing in End-to-End Automatic Speech Recognition—0
Houston we have a Divergence: A Subgroup Performance Analysis of ASR Models—0
Factual Consistency Oriented Speech Recognition—0
CAFE A Novel Code switching Dataset for Algerian Dialect French and English—0
How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR—0
How does end-to-end speech recognition training impact speech enhancement artifacts?—0
Arabic Code-Switching Speech Recognition using Monolingual Data—0
How Might We Create Better Benchmarks for Speech Recognition?—0
Facetron: A Multi-speaker Face-to-Speech Model based on Cross-modal Latent Representations—0
How to Learn a New Language? An Efficient Solution for Self-Supervised Learning Models Unseen Languages Adaption in Low-Resource Scenario—0
How to Scale Up Kernel Methods to Be As Good As Deep Neural Nets—0
How to Train Dependency Parsers with Inexact Search for Joint Sentence Boundary Detection and Parsing of Entire Documents—0
How transferable are features in convolutional neural network acoustic models across languages?—0
Byte Pair Encoding Is All You Need For Automatic Bengali Speech Recognition—0
HTEC: Human Transcription Error Correction—0
Face-Dubbing++: Lip-Synchronous, Voice Preserving Translation of Videos—0
Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models—0
Bypass Temporal Classification: Weakly Supervised Automatic Speech Recognition with Imperfect Transcripts—0
Human-Informed Speakers and Interpreters Analysis in the WAW Corpus and an Automatic Method for Calculating Interpreters' D\'ecalage—0
Human Listening and Live Captioning: Multi-Task Training for Speech Enhancement—0
Adversarial Joint Training with Self-Attention Mechanism for Robust End-to-End Speech Recognition—0
Extracting Domain Invariant Features by Unsupervised Learning for Robust Automatic Speech Recognition—0
Huqariq: A Multilingual Speech Corpus of Native Languages of Peru forSpeech Recognition—0
Extracting Biomedical Entities from Noisy Audio Transcripts—0
Show:102550
← PrevPage 55 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