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 1401–1450 of 3012 papers

TitleStatusHype
Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR—0
Measuring the Impact of Individual Domain Factors in Self-Supervised Pre-Training—0
Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR ErrorsCode1
Integrating Text Inputs For Training and Adapting RNN Transducer ASR Models—0
Language technology practitioners as language managers: arbitrating data bias and predictive bias in ASR—0
A Survey of Multilingual Models for Automatic Speech Recognition—0
Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech RecognitionCode1
Ask2Mask: Guided Data Selection for Masked Speech Modeling—0
Towards Better Meta-Initialization with Task Augmentation for Kindergarten-aged Speech Recognition—0
Differentially Private Speaker Anonymization—0
Improving CTC-based speech recognition via knowledge transferring from pre-trained language modelsCode0
Korean Tokenization for Beam Search Rescoring in Speech Recognition—0
VADOI:Voice-Activity-Detection Overlapping Inference For End-to-end Long-form Speech Recognition—0
r-G2P: Evaluating and Enhancing Robustness of Grapheme to Phoneme Conversion by Controlled noise introducing and Contextual information incorporation—0
Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition—0
SemEval 2022 Task 12: Symlink- Linking Mathematical Symbols to their Descriptions—0
Domain Adaptation of low-resource Target-Domain models using well-trained ASR Conformer Models—0
'Beach' to 'Bitch': Inadvertent Unsafe Transcription of Kids' Content on YouTube—0
MLP-ASR: Sequence-length agnostic all-MLP architectures for speech recognition—0
AISHELL-NER: Named Entity Recognition from Chinese SpeechCode1
Mitigating Closed-model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition—0
Conversational Speech Recognition By Learning Conversation-level Characteristics—0
Knowledge Transfer from Large-scale Pretrained Language Models to End-to-end Speech Recognizers—0
ADIMA: Abuse Detection In Multilingual AudioCode0
Multi-style Training for South African Call Centre Audio—0
Saving RNN Computations with a Neuron-Level Fuzzy Memoization Scheme—0
Multimodal Depression Classification Using Articulatory Coordination Features And Hierarchical Attention Based Text Embeddings—0
Improving Automatic Speech Recognition for Non-Native English with Transfer Learning and Language Model DecodingCode0
Enhancing ASR for Stuttered Speech with Limited Data Using Detect and Pass—0
A two-step approach to leverage contextual data: speech recognition in air-traffic communications—0
Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech RecognitionCode1
Polyphonic pitch detection with convolutional recurrent neural networks—0
The CUHK-TENCENT speaker diarization system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge—0
Joint Speech Recognition and Audio Captioning—0
The RoyalFlush System of Speech Recognition for M2MeT Challenge—0
ASR-Aware End-to-end Neural Diarization—0
Streaming Multi-Talker ASR with Token-Level Serialized Output TrainingCode1
RescoreBERT: Discriminative Speech Recognition Rescoring with BERT—0
Error Correction in ASR using Sequence-to-Sequence Models—0
Language Dependencies in Adversarial Attacks on Speech Recognition Systems—0
Visualizing Automatic Speech Recognition -- Means for a Better Understanding?—0
BEA-Base: A Benchmark for ASR of Spontaneous Hungarian—0
Star Temporal Classification: Sequence Classification with Partially Labeled DataCode0
Reducing language context confusion for end-to-end code-switching automatic speech recognition—0
Synthesizing Dysarthric Speech Using Multi-talker TTS for Dysarthric Speech Recognition—0
Sentiment-Aware Automatic Speech Recognition pre-training for enhanced Speech Emotion Recognition—0
Discovering Phonetic Inventories with Crosslingual Automatic Speech RecognitionCode0
On the Effectiveness of Pinyin-Character Dual-Decoding for End-to-End Mandarin Chinese ASR—0
The Norwegian Parliamentary Speech Corpus—0
Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models—0
Show:102550
← PrevPage 29 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