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 651–700 of 3012 papers

TitleStatusHype
Affect Recognition in Conversations Using Large Language Models—0
Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR—0
Big model only for hard audios: Sample dependent Whisper model selection for efficient inferencesCode0
Memory-augmented conformer for improved end-to-end long-form ASRCode1
Sparsely Shared LoRA on Whisper for Child Speech Recognition—0
Leveraging Data Collection and Unsupervised Learning for Code-switched Tunisian Arabic Automatic Speech Recognition—0
Incorporating Ultrasound Tongue Images for Audio-Visual Speech Enhancement—0
Exploring Speech Enhancement for Low-resource Speech Synthesis—0
Semi-Autoregressive Streaming ASR With Label Context—0
Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognition—0
HTEC: Human Transcription Error Correction—0
Corpus Synthesis for Zero-shot ASR domain Adaptation using Large Language Models—0
Training dynamic models using early exits for automatic speech recognition on resource-constrained devicesCode0
Instruction-Following Speech Recognition—0
HypR: A comprehensive study for ASR hypothesis revising with a reference corpusCode1
Investigating End-to-End ASR Architectures for Long Form Audio Transcription—0
A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spotting—0
Enhancing Quantised End-to-End ASR Models via PersonalisationCode0
Improving Speech Recognition for African American English With Audio Classification—0
Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation—0
Boosting End-to-End Multilingual Phoneme Recognition through Exploiting Universal Speech Attributes Constraints—0
Transformer Based Punctuation Restoration for TurkishCode0
t-SOT FNT: Streaming Multi-talker ASR with Text-only Domain Adaptation Capability—0
Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription—0
Towards Word-Level End-to-End Neural Speaker Diarization with Auxiliary Network—0
Echotune: A Modular Extractor Leveraging the Variable-Length Nature of Speech in ASR Tasks—0
EnCodecMAE: Leveraging neural codecs for universal audio representation learningCode1
Enhancing Child Vocalization Classification with Phonetically-Tuned Embeddings for Assisting Autism Diagnosis—0
Open-vocabulary Keyword-spotting with Adaptive Instance Normalization—0
Can Whisper perform speech-based in-context learning?—0
Improving Robustness of Neural Inverse Text Normalization via Data-Augmentation, Semi-Supervised Learning, and Post-Aligning Method—0
Kid-Whisper: Towards Bridging the Performance Gap in Automatic Speech Recognition for Children VS. Adults—0
Hybrid ASR for Resource-Constrained Robots: HMM - Deep Learning FusionCode0
Leveraging Large Language Models for Exploiting ASR Uncertainty—0
Perceptual and Task-Oriented Assessment of a Semantic Metric for ASR EvaluationCode0
Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems—0
TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models—0
Bring the Noise: Introducing Noise Robustness to Pretrained Automatic Speech Recognition—0
AVATAR: Robust Voice Search Engine Leveraging Autoregressive Document Retrieval and Contrastive Learning—0
Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation—0
Contextual Biasing of Named-Entities with Large Language Models—0
Learning Speech Representation From Contrastive Token-Acoustic Pretraining—0
Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer—0
ASTER: Automatic Speech Recognition System Accessibility Testing for Stutterers—0
Unsupervised Active Learning: Optimizing Labeling Cost-Effectiveness for Automatic Speech Recognition—0
Decoupled Structure for Improved Adaptability of End-to-End Models—0
A Small and Fast BERT for Chinese Medical Punctuation RestorationCode0
Convoifilter: A case study of doing cocktail party speech recognition—0
TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition—0
Indonesian Automatic Speech Recognition with XLSR-53—0
Show:102550
← PrevPage 14 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