David Kao

Robust and Unbounded Length Generalization in Autoregressive Transformer-Based Text-to-Speech

2024 · arXiv (Cornell University)

Autoregressive (AR) Transformer-based sequence models are known to have difficulty generalizing to sequences longer than those seen during training. When applied to text-to-speech (TTS), these models tend to drop or repeat words or produce erratic …

Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis

2019 · arXiv (Cornell University)

Recent work has explored sequence-to-sequence latent variable models for expressive speech synthesis (supporting control and transfer of prosody and style), but has not presented a coherent framework for understanding the trade-offs between the competing methods. …