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 751–800 of 3012 papers

TitleStatusHype
Predicting positive transfer for improved low-resource speech recognition using acoustic pseudo-tokens—0
Streaming Sequence Transduction through Dynamic CompressionCode0
Whispering in Norwegian: Navigating Orthographic and Dialectic Challenges—0
AccentFold: A Journey through African Accents for Zero-Shot ASR Adaptation to Target Accents—0
Digits micro-model for accurate and secure transactions—0
Byte Pair Encoding Is All You Need For Automatic Bengali Speech Recognition—0
Toward Practical Automatic Speech Recognition and Post-Processing: a Call for Explainable Error Benchmark Guideline—0
MF-AED-AEC: Speech Emotion Recognition by Leveraging Multimodal Fusion, Asr Error Detection, and Asr Error Correction—0
Locality enhanced dynamic biasing and sampling strategies for contextual ASR—0
Keep Decoding Parallel with Effective Knowledge Distillation from Language Models to End-to-end Speech Recognisers—0
Consistency Based Unsupervised Self-training For ASR Personalisation—0
Using Large Language Model for End-to-End Chinese ASR and NER—0
Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Search—0
SlideAVSR: A Dataset of Paper Explanation Videos for Audio-Visual Speech Recognition—0
Communication-Efficient Personalized Federated Learning for Speech-to-Text Tasks—0
AGADIR: Towards Array-Geometry Agnostic Directional Speech Recognition—0
Improving ASR Contextual Biasing with Guided Attention—0
Cascaded Cross-Modal Transformer for Audio-Textual ClassificationCode0
Promptformer: Prompted Conformer Transducer for ASR—0
Joint Unsupervised and Supervised Training for Automatic Speech Recognition via Bilevel Optimization—0
Transcending Controlled Environments Assessing the Transferability of ASRRobust NLU Models to Real-World Applications—0
XLS-R Deep Learning Model for Multilingual ASR on Low- Resource Languages: Indonesian, Javanese, and Sundanese—0
UCorrect: An Unsupervised Framework for Automatic Speech Recognition Error Correction—0
End to end Hindi to English speech conversion using Bark, mBART and a finetuned XLSR Wav2Vec2—0
Useful Blunders: Can Automated Speech Recognition Errors Improve Downstream Dementia Classification?—0
Continuously Learning New Words in Automatic Speech Recognition—0
LUPET: Incorporating Hierarchical Information Path into Multilingual ASR—0
Exploratory Evaluation of Speech Content Masking—0
BS-PLCNet: Band-split Packet Loss Concealment Network with Multi-task Learning Framework and Multi-discriminators—0
High-precision Voice Search Query Correction via Retrievable Speech-text Embedings—0
ICMC-ASR: The ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition Challenge—0
Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech RepresentationCode0
MLCA-AVSR: Multi-Layer Cross Attention Fusion based Audio-Visual Speech Recognition—0
TeLeS: Temporal Lexeme Similarity Score to Estimate Confidence in End-to-End ASRCode0
Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech RecognitionCode0
Hallucinations in Neural Automatic Speech Recognition: Identifying Errors and Hallucinatory Models—0
Towards Probing Contact Center Large Language Models—0
Exploring data augmentation in bias mitigation against non-native-accented speech—0
Multimodal Attention Merging for Improved Speech Recognition and Audio Event Classification—0
BLSTM-Based Confidence Estimation for End-to-End Speech Recognition—0
Lattice Rescoring Based on Large Ensemble of Complementary Neural Language Models—0
Stable Distillation: Regularizing Continued Pre-training for Low-Resource Automatic Speech RecognitionCode0
SpokesBiz -- an Open Corpus of Conversational Polish—0
Conformer-Based Speech Recognition On Extreme Edge-Computing Devices—0
Seq2seq for Automatic Paraphasia Detection in Aphasic SpeechCode0
OAVA: the open audio-visual archives aggregator—0
LiteVSR: Efficient Visual Speech Recognition by Learning from Speech Representations of Unlabeled Data—0
FastInject: Injecting Unpaired Text Data into CTC-based ASR training—0
USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models—0
ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective LearningCode0
Show:102550
← PrevPage 16 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