Accented text-to-speech (TTS) synthesis seeks to generate speech with an
accent (L2) as a variant of the standard version (L1). How to control the
intensity of accent in the process of TTS is a very interesting research
direction, and has attracted more and more attention. Recent work design a
speaker-adversarial loss to disentangle the speaker and accent information, and
then adjust the loss weight to control the accent intensity. However, such a
control method lacks interpretability, and there is no direct correlation
between the controlling factor and natural accent intensity. To this end, this
paper propose a new intuitive and explicit accent intensity control scheme for
accented TTS. Specifically, we first extract the posterior probability, called
as ``goodness of pronunciation (GoP)'' from the L1 speech recognition model to
quantify the phoneme accent intensity for accented speech, then design a
FastSpeech2 based TTS model, named Ai-TTS, to take the accent intensity
expression into account during speech generation. Experiments show that the our
method outperforms the baseline model in terms of accent rendering and
intensity control.

本文提出了一种直观明确的口音强度控制方案，首先从 L1 语音识别模型中提取后验概率，称为 “发音好坏度”，量化有重音的语音的音素重音程度，然后设计了一种基于 FastSpeech2 的 TTS 模型 Ai-TTS，在语音生成过程中考虑口音强度表达。实验证明，我们的方法在口音渲染和强度控制方面优于基线模型。

重音文本转语音的明确强度掌控

Explicit Intensity Control for Accented Text-to-speech

In the following report we propose pipelines for Goodness of Pronunciation
(GoP) computation solving OOV problem at testing time using Vocab/Lexicon
expansion techniques. The pipeline uses different components of ASR system to
quantify accent and automatically evaluate them as scores. We use the
posteriors of an ASR model trained on native English speech, along with the
phone level boundaries to obtain phone level pronunciation scores. We used this
as a baseline pipeline and implemented methods to remove UNK and SPN phonemes
in the GoP output by building three pipelines. The Online, Offline and Hybrid
pipeline which returns the scores but also can prevent unknown words in the
final output. The Online method is based per utterance, Offline method
pre-incorporates a set of OOV words for a given data set and the Hybrid method
combines the above two ideas to expand the lexicon as well work per utterance.
We further provide utilities such as the Phoneme to posterior mappings, GoP
scores of each utterance as a vector, and Word boundaries used in the GoP
pipeline for use in future research.

通过使用 ASR 系统的不同组件评估口音并自动评估它们，我们提出了一种解决测试时开放式语音识别系统中的 OOV 问题的 GoP 计算的流水线，并且通过构建三个管道来实现去除 GoP 输出中的 UNK 和 SPN 音素，Online、Offline 和 Hybrid 管道，以扩展词库以及对每个 utterance 进行处理，最终提供 Phoneme to posterior mappings、每个 utterance 的 GoP 得分向量以及 GoP 流程中使用的 Word boundaries 等实用工具供未来研究使用。