Deep Learning

PromptTTS++: Controlling Speaker Identity in Prompt-based Text-to-Speech using Natural Language Descriptions
Accepted to ICASSP 2024
Enhancing Multilingual TTS with Voice Conversion based Data Augmentation and Posterior Embedding
Accepted to ICASSP 2024
Electrolaryngeal Speech Intelligibility Enhancement Through Robust Linguistic Encoders
Accepted to ICASSP 2024
Period VITS: Variational Inference With Explicit Pitch Modeling For End-to-End Emotional Speech Synthesis
Accepted to ICASSP 2023
TTS-by-TTS 2: Data-selective Augmentation for Neural Speech Synthesis Using Ranking Support Vector Machine with Variational Autoencoder
Accepted to Interspeech 2022