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 2401–2450 of 3012 papers

TitleStatusHype
Improved Training Techniques for Online Neural Machine Translation—0
Generating Robust Audio Adversarial Examples using Iterative Proportional Clipping—0
Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training—0
Understanding Semantics from Speech Through Pre-training—0
Improving OOV Detection and Resolution with External Language Models in Acoustic-to-Word ASR—0
Espresso: A Fast End-to-end Neural Speech Recognition ToolkitCode1
Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentences—0
Simultaneous Speech Recognition and Speaker Diarization for Monaural Dialogue Recordings with Target-Speaker Acoustic Models—0
NeMo: a toolkit for building AI applications using Neural Modules—0
An Investigation Into On-device Personalization of End-to-end Automatic Speech Recognition Models—0
Harnessing Indirect Training Data for End-to-End Automatic Speech Translation: Tricks of the Trade—0
Integrating Source-channel and Attention-based Sequence-to-sequence Models for Speech Recognition—0
A Comparative Study on Transformer vs RNN in Speech ApplicationsCode0
Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model—0
Neural Network-Based Modeling of Phonetic Durations—0
Motivations, challenges, and perspectives for the development of an Automatic Speech Recognition System for the under-resourced Ngiemboon Language—0
Semantic Language Model for Tunisian Dialect—0
Human-Informed Speakers and Interpreters Analysis in the WAW Corpus and an Automatic Method for Calculating Interpreters' D\'ecalage—0
Towards Accurate Text Verbalization for ASR Based on Audio Alignment—0
Dialect-Specific Models for Automatic Speech Recognition of African American Vernacular English—0
Deploying Technology to Save Endangered Languages—0
Gender Representation in French Broadcast Corpora and Its Impact on ASR Performance—0
Towards Better Understanding of Spontaneous Conversations: Overcoming Automatic Speech Recognition Errors With Intent Recognition—0
Two-Staged Acoustic Modeling Adaption for Robust Speech Recognition by the Example of German Oral History Interviews—0
End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning—0
Unsupervised Stemming based Language Model for Telugu Broadcast News Transcription—0
Exploiting Cross-Lingual Speaker and Phonetic Diversity for Unsupervised Subword Modeling—0
Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition—0
Mitigating Noisy Inputs for Question Answering—0
Fast and Accurate Capitalization and Punctuation for Automatic Speech Recognition Using Transformer and Chunk Merging—0
An End-to-End Text-independent Speaker Verification Framework with a Keyword Adversarial Network—0
Practical Speech Recognition with HTK—0
Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systems—0
V2S attack: building DNN-based voice conversion from automatic speaker verification—0
A Speech Test Set of Practice Business Presentations with Additional Relevant Texts—0
Personalizing ASR for Dysarthric and Accented Speech with Limited DataCode0
DuTongChuan: Context-aware Translation Model for Simultaneous Interpreting—0
MaSS: A Large and Clean Multilingual Corpus of Sentence-aligned Spoken Utterances Extracted from the BibleCode0
Correlation Distance Skip Connection Denoising Autoencoder (CDSK-DAE) for Speech Feature Enhancement—0
Hierarchical Sequence to Sequence Voice Conversion with Limited Data—0
Investigating Target Set Reduction for End-to-End Speech Recognition of Hindi-English Code-Switching Data—0
Large-Scale Mixed-Bandwidth Deep Neural Network Acoustic Modeling for Automatic Speech Recognition—0
Acoustic Model Optimization Based On Evolutionary Stochastic Gradient Descent with Anchors for Automatic Speech Recognition—0
A Highly Efficient Distributed Deep Learning System For Automatic Speech Recognition—0
Joint Speech Recognition and Speaker Diarization via Sequence Transduction—0
Teach an all-rounder with experts in different domains—0
Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech RecognitionCode0
ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning—0
Improved low-resource Somali speech recognition by semi-supervised acoustic and language model training—0
End-to-End Speech Recognition with High-Frame-Rate Features Extraction—0
Show:102550
← PrevPage 49 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