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 351–400 of 3012 papers

TitleStatusHype
LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related TasksCode0
Audio Adversarial Examples: Targeted Attacks on Speech-to-TextCode0
Latent Tree Language ModelCode0
Let SSMs be ConvNets: State-space Modeling with Optimal Tensor ContractionsCode0
Language-Universal Adapter Learning with Knowledge Distillation for End-to-End Multilingual Speech RecognitionCode0
Language Modeling for Code-Switching: Evaluation, Integration of Monolingual Data, and Discriminative TrainingCode0
Language Complexity and Speech Recognition Accuracy: Orthographic Complexity Hurts, Phonological Complexity Doesn'tCode0
Kurdish (Sorani) Speech to Text: Presenting an Experimental DatasetCode0
Language Identification Using Deep Convolutional Recurrent Neural NetworksCode0
Large-Scale End-to-End Multilingual Speech Recognition and Language Identification with Multi-Task LearningCode0
Iterative Pseudo-Labeling for Speech RecognitionCode0
Killkan: The Automatic Speech Recognition Dataset for Kichwa with Morphosyntactic InformationCode0
Investigating the Effects of Word Substitution Errors on Sentence EmbeddingsCode0
Attentional Speech Recognition Models Misbehave on Out-of-domain UtterancesCode0
Leveraging Broadcast Media Subtitle Transcripts for Automatic Speech Recognition and SubtitlingCode0
mHuBERT-147: A Compact Multilingual HuBERT ModelCode0
Pretext Tasks selection for multitask self-supervised speech representation learningCode0
A Theory of Unsupervised Speech RecognitionCode0
Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech RecognitionCode0
Improving Voice Separation by Incorporating End-to-end Speech RecognitionCode0
A Change of Heart: Improving Speech Emotion Recognition through Speech-to-Text Modality ConversionCode0
Improving RNN Transducer Modeling for End-to-End Speech RecognitionCode0
Improving CTC-based speech recognition via knowledge transferring from pre-trained language modelsCode0
Improving LSTM-CTC based ASR performance in domains with limited training dataCode0
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
Hybrid phonetic-neural model for correction in speech recognition systemsCode0
Improving the Inclusivity of Dutch Speech Recognition by Fine-tuning Whisper on the JASMIN-CGN CorpusCode0
HYBRIDFORMER: improving SqueezeFormer with hybrid attention and NSR mechanismCode0
Integrating Emotion Recognition with Speech Recognition and Speaker Diarisation for ConversationsCode0
How Phonotactics Affect Multilingual and Zero-shot ASR PerformanceCode0
How You Say It Matters: Measuring the Impact of Verbal Disfluency Tags on Automated Dementia DetectionCode0
HuBERT-EE: Early Exiting HuBERT for Efficient Speech RecognitionCode0
Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of SpeechCode0
Greek2MathTex: A Greek Speech-to-Text Framework for LaTeX Equations GenerationCode0
Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASRCode0
Iterative pseudo-forced alignment by acoustic CTC loss for self-supervised ASR domain adaptationCode0
Attention-based Multi-hypothesis Fusion for Speech SummarizationCode0
Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer GeneratorCode0
Guiding Frame-Level CTC Alignments Using Self-knowledge DistillationCode0
Human Transcription Quality ImprovementCode0
Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech RecognitionCode0
AI-Generated Song Detection via Lyrics TranscriptsCode0
Attentively Embracing Noise for Robust Latent Representation in BERTCode0
A Simplified Fully Quantized Transformer for End-to-end Speech RecognitionCode0
Assessing the Use of Prosody in Constituency Parsing of Imperfect TranscriptsCode0
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
FLEURS: Few-shot Learning Evaluation of Universal Representations of SpeechCode0
Show:102550
← PrevPage 8 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