speech recognition


Speech recognition is the task of identifying words spoken aloud, analyzing the voice and language, and accurately transcribing the words.

SuPseudo: A Pseudo-supervised Learning Method for Neural Speech Enhancement in Far-field Speech Recognition

Add code
May 30, 2025
Viaarxiv icon

Running Conventional Automatic Speech Recognition on Memristor Hardware: A Simulated Approach

Add code
May 30, 2025
Viaarxiv icon

MOPSA: Mixture of Prompt-Experts Based Speaker Adaptation for Elderly Speech Recognition

Add code
May 30, 2025
Viaarxiv icon

Rhythm Features for Speaker Identification

Add code
Jun 07, 2025
Viaarxiv icon

In-context Language Learning for Endangered Languages in Speech Recognition

Add code
May 28, 2025
Viaarxiv icon

Exploring Generative Error Correction for Dysarthric Speech Recognition

Add code
May 26, 2025
Viaarxiv icon

On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition

Add code
May 28, 2025
Viaarxiv icon

Prompting Whisper for Improved Verbatim Transcription and End-to-end Miscue Detection

Add code
May 29, 2025
Viaarxiv icon

Robust Unsupervised Adaptation of a Speech Recogniser Using Entropy Minimisation and Speaker Codes

Add code
Jun 12, 2025
Viaarxiv icon

Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech Recognition

Add code
May 28, 2025
Viaarxiv icon