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 401–450 of 3012 papers

TitleStatusHype
Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech RecognitionCode0
Improving Automatic Speech Recognition for Non-Native English with Transfer Learning and Language Model DecodingCode0
HYBRIDFORMER: improving SqueezeFormer with hybrid attention and NSR mechanismCode0
Hybrid ASR for Resource-Constrained Robots: HMM - Deep Learning FusionCode0
Audio Segmentation for Robust Real-Time Speech Recognition Based on Neural NetworksCode0
Hybrid phonetic-neural model for correction in speech recognition systemsCode0
HuBERT-EE: Early Exiting HuBERT for Efficient Speech RecognitionCode0
Human Transcription Quality ImprovementCode0
Improving CTC-based speech recognition via knowledge transferring from pre-trained language modelsCode0
AI-Generated Song Detection via Lyrics TranscriptsCode0
Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASRCode0
Audiovisual Speaker Tracking using Nonlinear Dynamical Systems with Dynamic Stream WeightsCode0
Guiding Frame-Level CTC Alignments Using Self-knowledge DistillationCode0
A low latency attention module for streaming self-supervised speech representation learningCode0
How Phonotactics Affect Multilingual and Zero-shot ASR PerformanceCode0
Assessing the Use of Prosody in Constituency Parsing of Imperfect TranscriptsCode0
Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer GeneratorCode0
Measuring the Accuracy of Automatic Speech Recognition SolutionsCode0
Greek2MathTex: A Greek Speech-to-Text Framework for LaTeX Equations GenerationCode0
Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of SpeechCode0
Augmenting Librispeech with French Translations: A Multimodal Corpus for Direct Speech Translation EvaluationCode0
How You Say It Matters: Measuring the Impact of Verbal Disfluency Tags on Automated Dementia DetectionCode0
Improving LSTM-CTC based ASR performance in domains with limited training dataCode0
FLEURS: Few-shot Learning Evaluation of Universal Representations of SpeechCode0
Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative StudyCode0
Fine-Grained Grounding for Multimodal Speech RecognitionCode0
Finnish Parliament ASR corpus - Analysis, benchmarks and statisticsCode0
FASA: a Flexible and Automatic Speech Aligner for Extracting High-quality Aligned Children Speech DataCode0
FastEmit: Low-latency Streaming ASR with Sequence-level Emission RegularizationCode0
Multilingual Bottleneck Features for Improving ASR Performance of Code-Switched Speech in Under-Resourced LanguagesCode0
A Simplified Fully Quantized Transformer for End-to-end Speech RecognitionCode0
Exploiting Attention-based Sequence-to-Sequence Architectures for Sound Event LocalizationCode0
Exploring Generative Error Correction for Dysarthric Speech RecognitionCode0
Explainability of Speech Recognition Transformers via Gradient-based Attention VisualizationCode0
ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech ToolkitCode0
ASR Benchmarking: Need for a More Representative Conversational DatasetCode0
Multi-Stage Speaker Diarization for Noisy ClassroomsCode0
Enhancing Quantised End-to-End ASR Models via PersonalisationCode0
Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification TasksCode0
Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech RecognitionCode0
On Out-of-Distribution Detection for Audio with Deep Nearest NeighborsCode0
End-to-End Speech Recognition With Joint Dereverberation Of Sub-Band Autoregressive EnvelopesCode0
End-to-End Learning of Speech 2D Feature-Trajectory for Prosthetic HandsCode0
End-to-End Open Vocabulary Keyword Search With Multilingual Neural RepresentationsCode0
Perceptual and Task-Oriented Assessment of a Semantic Metric for ASR EvaluationCode0
Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation NetworkCode0
End to End ASR System with Automatic Punctuation InsertionCode0
A Small and Fast BERT for Chinese Medical Punctuation RestorationCode0
AfriHuBERT: A self-supervised speech representation model for African languagesCode0
Effects of Layer Freezing on Transferring a Speech Recognition System to Under-resourced LanguagesCode0
Show:102550
← PrevPage 9 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