Hierarchical Context-Aware Transformers for Non-Autoregressive Text to Speech

Abstract

In this paper, we propose methods for improving the modeling performance of a Transformer-based non-autoregressive text-to-speech (TNA-TTS) model. Although the text encoder and audio decoder handle different types and lengths of data (i.e., text and audio), the TNA-TTS models are not designed considering these variations. Therefore, to improve the modeling performance of the TNA-TTS model we propose a hierarchical Transformer structure-based text encoder and audio decoder that are designed to accommodate the characteristics of each module. For the text encoder, we constrain each self-attention layer so the encoder focuses on a text sequence from the local to the global scope. Conversely, the audio decoder constrains its self-attention layers to focus in the reverse direction, i.e., from global to local scope. Additionally, we further improve the pitch modeling accuracy of the audio decoder by providing sentence and word-level pitch as conditions. Various objective and subjective evaluations verified that the proposed method outperformed the baseline TNA-TTS.

arXiv commentAccepted to INTERSPEECH 2021

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• Longformer: The Long-Document Transformer
• FastSpeech: Fast, Robust and Controllable Text to Speech
• Generating Long Sequences with Sparse Transformers
• CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network