speech recognition


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

ASR-FAIRBENCH: Measuring and Benchmarking Equity Across Speech Recognition Systems

Add code
May 16, 2025
Viaarxiv icon

PersonaTAB: Predicting Personality Traits using Textual, Acoustic, and Behavioral Cues in Fully-Duplex Speech Dialogs

Add code
May 20, 2025
Viaarxiv icon

Private kNN-VC: Interpretable Anonymization of Converted Speech

Add code
May 23, 2025
Viaarxiv icon

FiLLM -- A Filipino-optimized Large Language Model based on Southeast Asia Large Language Model (SEALLM)

Add code
May 25, 2025
Viaarxiv icon

Survey of End-to-End Multi-Speaker Automatic Speech Recognition for Monaural Audio

Add code
May 16, 2025
Viaarxiv icon

Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference

Add code
May 20, 2025
Viaarxiv icon

Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker and Speech Traits

Add code
May 20, 2025
Viaarxiv icon

Automatic Speech Recognition for African Low-Resource Languages: Challenges and Future Directions

Add code
May 16, 2025
Viaarxiv icon

Calm-Whisper: Reduce Whisper Hallucination On Non-Speech By Calming Crazy Heads Down

Add code
May 19, 2025
Viaarxiv icon

KIT's Offline Speech Translation and Instruction Following Submission for IWSLT 2025

Add code
May 19, 2025
Viaarxiv icon