speech recognition


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

A Mixture-of-Experts Model for Multimodal Emotion Recognition in Conversations

Add code
Feb 26, 2026
Viaarxiv icon

Voice-Driven Semantic Perception for UAV-Assisted Emergency Networks

Add code
Feb 19, 2026
Viaarxiv icon

ViSpeechFormer: A Phonemic Approach for Vietnamese Automatic Speech Recognition

Add code
Feb 10, 2026
Viaarxiv icon

Joint Enhancement and Classification using Coupled Diffusion Models of Signals and Logits

Add code
Feb 17, 2026
Viaarxiv icon

Enroll-on-Wakeup: A First Comparative Study of Target Speech Extraction for Seamless Interaction in Real Noisy Human-Machine Dialogue Scenarios

Add code
Feb 17, 2026
Viaarxiv icon

Cross-Modal Bottleneck Fusion For Noise Robust Audio-Visual Speech Recognition

Add code
Feb 09, 2026
Viaarxiv icon

Speech to Speech Synthesis for Voice Impersonation

Add code
Feb 13, 2026
Viaarxiv icon

Where Are We At with Automatic Speech Recognition for the Bambara Language?

Add code
Feb 10, 2026
Viaarxiv icon

"Sorry, I Didn't Catch That": How Speech Models Miss What Matters Most

Add code
Feb 16, 2026
Viaarxiv icon

CLAP-Based Automatic Word Naming Recognition in Post-Stroke Aphasia

Add code
Feb 16, 2026
Viaarxiv icon