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 101–125 of 3012 papers

TitleStatusHype
Boosting the Transferability of Audio Adversarial Examples with Acoustic Representation Optimization—0
Whispering in Amharic: Fine-tuning Whisper for Low-resource Language—0
Your voice is your voice: Supporting Self-expression through Speech Generation and LLMs in Augmented and Alternative Communication—0
Evaluating ASR Confidence Scores for Automated Error Detection in User-Assisted Correction Interfaces—0
ValSub: Subsampling Validation Data to Mitigate Forgetting during ASR Personalization—0
Everything Can Be Described in Words: A Simple Unified Multi-Modal Framework with Semantic and Temporal Alignment—0
An Exhaustive Evaluation of TTS- and VC-based Data Augmentation for ASR—0
Automatic Speech Recognition for Non-Native English: Accuracy and Disfluency Handling—0
Building English ASR model with regional language support—0
From Voice to Safety: Language AI Powered Pilot-ATC Communication Understanding for Airport Surface Movement Collision Risk Assessment—0
Qieemo: Speech Is All You Need in the Emotion Recognition in Conversations—0
Direct Speech to Speech Translation: A Review—0
Fine-Tuning Whisper for Inclusive Prosodic Stress Analysis—0
Unveiling Biases while Embracing Sustainability: Assessing the Dual Challenges of Automatic Speech Recognition Systems—0
LiteASR: Efficient Automatic Speech Recognition with Low-Rank ApproximationCode2
Adapting Automatic Speech Recognition for Accented Air Traffic Control Communications—0
CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASRCode2
Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision—0
CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech Recognition—0
Exploring Gender Disparities in Automatic Speech Recognition Technology—0
Improving the Inclusivity of Dutch Speech Recognition by Fine-tuning Whisper on the JASMIN-CGN CorpusCode0
Understanding Zero-shot Rare Word Recognition Improvements Through LLM Integration—0
The Esethu Framework: Reimagining Sustainable Dataset Governance and Curation for Low-Resource Languages—0
Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders—0
Adopting Whisper for Confidence Estimation—0
Show:102550
← PrevPage 5 of 121Next →
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