Adaptation of Whisper models to child speech recognition
Paper
•
2307.13008
•
Published
Rishabh Jain
rishabhjain16
AI & ML interests
LLMs,
Speech AI (ASR, TTS, SR)
Audio-Vision
Vision Transformers
Recent Activity
updated
a dataset
14 days ago
rishabhjain16/lrs3
updated
a dataset
14 days ago
rishabhjain16/lrs2
published
a dataset
14 days ago
rishabhjain16/lrs2
Organizations
authored
6
papers
27 days ago
Synthetic Speaking Children -- Why We Need Them and How to Make Them
Paper
•
2311.06307
•
Published
A comparative analysis between Conformer-Transducer, Whisper, and wav2vec2 for improving the child speech recognition
Paper
•
2311.04936
•
Published
Improved Child Text-to-Speech Synthesis through Fastpitch-based Transfer Learning
Paper
•
2311.04313
•
Published
A Wav2vec2-Based Experimental Study on Self-Supervised Learning Methods to Improve Child Speech Recognition
Paper
•
2204.05419
•
Published
A Text-to-Speech Pipeline, Evaluation Methodology, and Initial Fine-Tuning Results for Child Speech Synthesis
Paper
•
2203.11562
•
Published