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 2801–2850 of 3012 papers

TitleStatusHype
Bi-Directional Lattice Recurrent Neural Networks for Confidence EstimationCode0
When Is TTS Augmentation Through a Pivot Language Useful?Code0
Audio Segmentation for Robust Real-Time Speech Recognition Based on Neural NetworksCode0
Pretext Tasks selection for multitask self-supervised speech representation learningCode0
An Automatic Speech Recognition System for Bengali Language based on Wav2Vec2 and Transfer LearningCode0
Learning to adapt: a meta-learning approach for speaker adaptationCode0
Improving LSTM-CTC based ASR performance in domains with limited training dataCode0
Discrete Speech Unit Extraction via Independent Component AnalysisCode0
Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion TechniquesCode0
Segmentation-Free Streaming Machine TranslationCode0
Pre-training on high-resource speech recognition improves low-resource speech-to-text translationCode0
Discrete Cross-Modal Alignment Enables Zero-Shot Speech TranslationCode0
Speech-enhanced and Noise-aware Networks for Robust Speech RecognitionCode0
Discovering Phonetic Inventories with Crosslingual Automatic Speech RecognitionCode0
Selective Attention Merging for low resource tasks: A case study of Child ASRCode0
Improving CTC-based speech recognition via knowledge transferring from pre-trained language modelsCode0
A Comparative Study on Transformer vs RNN in Speech ApplicationsCode0
ASDF: A Differential Testing Framework for Automatic Speech Recognition SystemsCode0
Swiss Parliaments Corpus, an Automatically Aligned Swiss German Speech to Standard German Text CorpusCode0
Adapting the adapters for code-switching in multilingual ASRCode0
Improving Automatic Speech Recognition for Non-Native English with Transfer Learning and Language Model DecodingCode0
Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech RecognitionCode0
Let SSMs be ConvNets: State-space Modeling with Optimal Tensor ContractionsCode0
Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin ChineseCode0
Leveraging Broadcast Media Subtitle Transcripts for Automatic Speech Recognition and SubtitlingCode0
DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distributionCode0
Syllable Subword Tokens for Open Vocabulary Speech Recognition in MalayalamCode0
A Change of Heart: Improving Speech Emotion Recognition through Speech-to-Text Modality ConversionCode0
Enhancing Quantised End-to-End ASR Models via PersonalisationCode0
Synchronous Speech Recognition and Speech-to-Text Translation with Interactive DecodingCode0
Whose Emotion Matters? Speaking Activity Localisation without Prior KnowledgeCode0
Unsupervised Data Selection for TTS: Using Arabic Broadcast News as a Case StudyCode0
Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation NetworkCode0
Hybrid phonetic-neural model for correction in speech recognition systemsCode0
Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LMCode0
Self-supervised Speech Representations Still Struggle with African American Vernacular EnglishCode0
NeMo Inverse Text Normalization: From Development To ProductionCode0
End-to-End Speech Recognition With Joint Dereverberation Of Sub-Band Autoregressive EnvelopesCode0
Conditional independence for pretext task selection in Self-supervised speech representation learningCode0
Neural Architecture Search For LF-MMI Trained Time Delay Neural NetworksCode0
HYBRIDFORMER: improving SqueezeFormer with hybrid attention and NSR mechanismCode0
ADIMA: Abuse Detection In Multilingual AudioCode0
Semantically Corrected Amharic Automatic Speech RecognitionCode0
Semantically Meaningful Metrics for Norwegian ASR SystemsCode0
Towards Temporally Explainable Dysarthric Speech Clarity AssessmentCode0
Hybrid ASR for Resource-Constrained Robots: HMM - Deep Learning FusionCode0
Light Gated Recurrent Units for Speech RecognitionCode0
Human Transcription Quality ImprovementCode0
A comparative analysis between Conformer-Transducer, Whisper, and wav2vec2 for improving the child speech recognitionCode0
HuBERT-EE: Early Exiting HuBERT for Efficient Speech RecognitionCode0
Show:102550
← PrevPage 57 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