Picture for Haobin Tang

Haobin Tang

ED-TTS: Multi-Scale Emotion Modeling using Cross-Domain Emotion Diarization for Emotional Speech Synthesis

Add code
Jan 16, 2024
Viaarxiv icon

EmoMix: Emotion Mixing via Diffusion Models for Emotional Speech Synthesis

Add code
Jun 01, 2023
Viaarxiv icon

SAR: Self-Supervised Anti-Distortion Representation for End-To-End Speech Model

Add code
Apr 23, 2023
Viaarxiv icon

Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropy

Add code
Mar 14, 2023
Viaarxiv icon

QI-TTS: Questioning Intonation Control for Emotional Speech Synthesis

Add code
Mar 14, 2023
Viaarxiv icon

Speech Augmentation Based Unsupervised Learning for Keyword Spotting

Add code
May 28, 2022
Figure 1 for Speech Augmentation Based Unsupervised Learning for Keyword Spotting
Figure 2 for Speech Augmentation Based Unsupervised Learning for Keyword Spotting
Figure 3 for Speech Augmentation Based Unsupervised Learning for Keyword Spotting
Figure 4 for Speech Augmentation Based Unsupervised Learning for Keyword Spotting
Viaarxiv icon