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 2801–2825 of 3012 papers

TitleStatusHype
Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LMCode0
Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments—0
ASR error management for improving spoken language understanding—0
Anti-spoofing Methods for Automatic SpeakerVerification System—0
Local Monotonic Attention Mechanism for End-to-End Speech and Language Processing—0
Use of Knowledge Graph in Rescoring the N-Best List in Automatic Speech Recognition—0
A Generative Model of a Pronunciation Lexicon for Hindi—0
M\'alr\'omur: A Manually Verified Corpus of Recorded Icelandic Speech—0
Acoustic Model Compression with MAP adaptation—0
Speech-Based Visual Question AnsweringCode0
Towards Estimating the Upper Bound of Visual-Speech Recognition: The Visual Lip-Reading Feasibility Database—0
Automatic Viseme Vocabulary Construction to Enhance Continuous Lip-reading—0
An enhanced automatic speech recognition system for Arabic—0
An Unsupervised Speaker Clustering Technique based on SOM and I-vectors for Speech Recognition Systems—0
A Code-Switching Corpus of Turkish-German Conversations—0
``Oh, I've Heard That Before'': Modelling Own-Dialect Bias After Perceptual Learning by Weighting Training Data—0
Identifying dialects with textual and acoustic cues—0
Gender and Dialect Bias in YouTube's Automatic Captions—0
The SUMMA Platform Prototype—0
CASSANDRA: A multipurpose configurable voice-enabled human-computer-interface—0
Real-Time Keyword Extraction from Conversations—0
A Hierarchical Neural Model for Learning Sequences of Dialogue Acts—0
Learning Similarity Functions for Pronunciation Variations—0
Direct Acoustics-to-Word Models for English Conversational Speech Recognition—0
Recognizing Multi-talker Speech with Permutation Invariant Training—0
Show:102550
← PrevPage 113 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