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
An efficient text augmentation approach for contextualized Mandarin speech recognition—0
Optimizing Byte-level Representation for End-to-end ASR—0
Inclusive ASR for Disfluent Speech: Cascaded Large-Scale Self-Supervised Learning with Targeted Fine-Tuning and Data Augmentation—0
ROAR: Reinforcing Original to Augmented Data Ratio Dynamics for Wav2Vec2.0 Based ASR—0
Language Complexity and Speech Recognition Accuracy: Orthographic Complexity Hurts, Phonological Complexity Doesn'tCode0
Multi-Channel Multi-Speaker ASR Using Target Speaker's Solo Segment—0
The Second DISPLACE Challenge : DIarization of SPeaker and LAnguage in Conversational Environments—0
LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related TasksCode0
Transcription-Free Fine-Tuning of Speech Separation Models for Noisy and Reverberant Multi-Speaker Automatic Speech Recognition—0
Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion TechniquesCode0
DualVC 3: Leveraging Language Model Generated Pseudo Context for End-to-end Low Latency Streaming Voice Conversion—0
Transformer-based Model for ASR N-Best Rescoring and Rewriting—0
Audio-conditioned phonemic and prosodic annotation for building text-to-speech models from unlabeled speech data—0
Towards Unsupervised Speech Recognition Without Pronunciation ModelsCode0
ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets—0
Guiding Frame-Level CTC Alignments Using Self-knowledge DistillationCode0
PRoDeliberation: Parallel Robust Deliberation for End-to-End Spoken Language Understanding—0
Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter—0
AS-70: A Mandarin stuttered speech dataset for automatic speech recognition and stuttering event detection—0
Reading Miscue Detection in Primary School through Automatic Speech Recognition—0
mHuBERT-147: A Compact Multilingual HuBERT ModelCode0
ASTRA: Aligning Speech and Text Representations for Asr without Sampling—0
MS-HuBERT: Mitigating Pre-training and Inference Mismatch in Masked Language Modelling methods for learning Speech Representations—0
Pitch-Aware RNN-T for Mandarin Chinese Mispronunciation Detection and Diagnosis—0
LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR—0
Flexible Multichannel Speech Enhancement for Noise-Robust Frontend—0
Improving Zero-Shot Chinese-English Code-Switching ASR with kNN-CTC and Gated Monolingual Datastores—0
Hypernetworks for Personalizing ASR to Atypical Speech—0
To Distill or Not to Distill? On the Robustness of Robust Knowledge DistillationCode0
Enhancing CTC-based speech recognition with diverse modeling units—0
Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition—0
Text Injection for Neural Contextual Biasing—0
Keyword-Guided Adaptation of Automatic Speech Recognition—0
Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping—0
Enabling ASR for Low-Resource Languages: A Comprehensive Dataset Creation Approach—0
Wav2Prompt: End-to-End Speech Prompt Generation and Tuning For LLM in Zero and Few-shot Learning—0
Zipper: A Multi-Tower Decoder Architecture for Fusing Modalities—0
Intelligent Clinical Documentation: Harnessing Generative AI for Patient-Centric Clinical Note Generation—0
Denoising LM: Pushing the Limits of Error Correction Models for Speech Recognition—0
Contrastive and Consistency Learning for Neural Noisy-Channel Model in Spoken Language UnderstandingCode0
Joint Optimization of Streaming and Non-Streaming Automatic Speech Recognition with Multi-Decoder and Knowledge Distillation—0
You don't understand me!: Comparing ASR results for L1 and L2 speakers of Swedish—0
FairLENS: Assessing Fairness in Law Enforcement Speech Recognition—0
Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models—0
Continued Pretraining for Domain Adaptation of Wav2vec2.0 in Automatic Speech Recognition for Elementary Math Classroom Settings—0
Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer—0
Lost in Transcription: Identifying and Quantifying the Accuracy Biases of Automatic Speech Recognition Systems Against Disfluent Speech—0
Open Implementation and Study of BEST-RQ for Speech Processing—0
MMGER: Multi-modal and Multi-granularity Generative Error Correction with LLM for Joint Accent and Speech Recognition—0
Combining X-Vectors and Bayesian Batch Active Learning: Two-Stage Active Learning Pipeline for Speech Recognition—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