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 2226–2250 of 3012 papers

TitleStatusHype
Quaternion Neural Networks for Multi-channel Distant Speech Recognition—0
An Effective End-to-End Modeling Approach for Mispronunciation Detection—0
AccentDB: A Database of Non-Native English Accents to Assist Neural Speech Recognition—0
Reducing Spelling Inconsistencies in Code-Switching ASR using Contextualized CTC Loss—0
That Sounds Familiar: an Analysis of Phonetic Representations Transfer Across Languages—0
Dynamic Sparsity Neural Networks for Automatic Speech Recognition—0
Contextualizing ASR Lattice Rescoring with Hybrid Pointer Network Language Model—0
Context-Dependent Acoustic Modeling without Explicit Phone Clustering—0
Coupled Training of Sequence-to-Sequence Models for Accented Speech RecognitionCode0
You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation—0
Automatic Estimation of Intelligibility Measure for Consonants in Speech—0
DiscreTalk: Text-to-Speech as a Machine Translation Problem—0
Incremental Learning for End-to-End Automatic Speech Recognition—0
RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions—0
The Perceptimatic English Benchmark for Speech Perception Models—0
Fast and Robust Unsupervised Contextual Biasing for Speech Recognition—0
Does Visual Self-Supervision Improve Learning of Speech Representations for Emotion Recognition?—0
MultiQT: Multimodal Learning for Real-Time Question Tracking in Speech—0
Improving the Language Model for Low-Resource ASR with Online Text Corpora—0
Multi-Staged Cross-Lingual Acoustic Model Adaption for Robust Speech Recognition in Real-World Applications - A Case Study on German Oral History Interviews—0
Challenges of Applying Automatic Speech Recognition for Transcribing EU Parliament Committee Meetings: A Pilot Study—0
Preparation of Bangla Speech Corpus from Publicly Available Audio \& Text—0
Automatic Transcription Challenges for Inuktitut, a Low-Resource Polysynthetic Language—0
Crossing the SSH Bridge with Interview Data—0
An Investigative Study of Multi-Modal Cross-Lingual Retrieval—0
Show:102550
← PrevPage 90 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