MoBoAligner: a Neural Alignment Model for Non-autoregressive TTS with Monotonic Boundary Search

By Naihan Li, Shujie Liu, Yanqing Liu, Sheng Zhao, Ming Liu, Ming Zhou. 2020

7 citations recorded by the source corpus.

To speed up the inference of neural speech synthesis, non-autoregressive models receive increasing attention recently. In non-autoregressive models, additional durations of text tokens are required to make a hard alignment between the encoder and the decoder. The duration-based alignment plays a crucial role since it controls the correspondence between text tokens and spectrum frames and determines the rhythm and speed of synthesized audio. To get better duration-based alignment and improve the quality of non-autoregressive speech synthesis, in this paper, we propose a novel neural alignment model named MoboAligner. Given the pairs of the text and mel spectrum, MoboAligner tries to identify the boundaries of text tokens in the given mel spectrum frames based on the token-frame similarity in the neural semantic space with an end-to-end framework. With these boundaries, durations can be extracted and used in the training of non-autoregressive TTS models. Compared with the duration extracted by TransformerTTS, MoboAligner brings improvement for the non-autoregressive TTS model on MOS (3.74 comparing to FastSpeech's 3.44). Besides, MoboAligner is task-specified and lightweight, which reduces the parameter number by 45% and the training time consuming by 30%.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Sheng Zhao
5. Lei He
6. Frank K. Soong
7. Yanqing Liu
8. Bohan Li

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, methodology): “Replacing Attention with Duration Prediction Label from encoder-decoder attention [284, 355, 193, 177] Label from CTC alignment [19] Label from HMM alignment [286, 411, 190, 246, 72, 298] Dynamic programming [422, 189, 229] Monotonic alignment search [156] Monotonic interpolation with soft DTW [67, ”
• DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021 (2021, background): “Phoneme representation is widely used as the input of end-toend TTS systems like recent neural TTS models [13, 15, 6, 27], which can avoid ambiguity depending on the text context.”
• EfficientTTS: An Efficient and High-Quality Text-to-Speech Architecture (2020, background): “Lots of prior studies have been proposed to ensure correct alignments (Li et al., 2020; Chiu & Raffel, 2018; Raffel et al., 2017), but most of them require sequential steps and often fail to meet all the criteria mentioned above.”