Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTS
arXiv:1906.00672
Abstract
Neural TTS has demonstrated strong capabilities to generate human-like speech with high quality and naturalness, while its generalization to out-of-domain texts is still a challenging task, with regard to the design of attention-based sequence-to-sequence acoustic modeling. Various errors occur in those inputs with unseen context, including attention collapse, skipping, repeating, etc., which limits the broader applications. In this paper, we propose a novel stepwise monotonic attention method in sequence-to-sequence acoustic modeling to improve the robustness on out-of-domain inputs. The method utilizes the strict monotonic property in TTS with constraints on monotonic hard attention that the alignments between inputs and outputs sequence must be not only monotonic but allowing no skipping on inputs. Soft attention could be used to evade mismatch between training and inference. The experimental results show that the proposed method could achieve significant improvements in robustness on out-of-domain scenarios for phoneme-based models, without any regression on the in-domain naturalness test.
arXiv commentAccepted by Interspeech 2019, Graz, Austria; v3: typo fixed
References in corpus (9)
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- WaveNet: A Generative Model for Raw Audio
- From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification
- Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention
- Online and Linear-Time Attention by Enforcing Monotonic Alignments
- Reinforcement Learning Neural Turing Machines - Revised
- Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesis
- A Regularized Framework for Sparse and Structured Neural Attention
- Local Monotonic Attention Mechanism for End-to-End Speech and Language Processing