The field of prosody transfer in speech synthesis systems is rapidly
advancing. This research is focused on evaluating learning methods for adapting
pre-trained monolingual text-to-speech (TTS) models to multilingual conditions,
i.e., Supervised Fine-Tuning (SFT) and Transfer Learning (TL). This comparison
utilizes three distinct metrics: Mean Opinion Score (MOS), Recognition Accuracy
(RA), and Mel Cepstral Distortion (MCD). Results demonstrate that, in
comparison to SFT, TL leads to significantly enhanced performance, with an
average MOS higher by 1.53 points, a 37.5% increase in RA, and approximately a
7.8-point improvement in MCD. These findings are instrumental in helping build
TTS models for low-resource languages.

对语音合成系统中的韵律传输领域进行研究，评估了适应多语言环境的预训练单语言文本转语音模型的学习方法，即监督微调和迁移学习。结果表明，与监督微调相比，迁移学习可以显著提高性能，平均 MOS 得分高出 1.53 点，RA 增加 37.5%，MCD 改善了约 7.8 个点。这些发现对于建立低资源语言的文本转语音模型具有重要意义。

多语种语调转换：比较监督和迁移学习

Multilingual Prosody Transfer: Comparing Supervised & Transfer Learning

Modern speech synthesis systems have improved significantly, with synthetic
speech being indistinguishable from real speech. However, efficient and
holistic evaluation of synthetic speech still remains a significant challenge.
Human evaluation using Mean Opinion Score (MOS) is ideal, but inefficient due
to high costs. Therefore, researchers have developed auxiliary automatic
metrics like Word Error Rate (WER) to measure intelligibility. Prior works
focus on evaluating synthetic speech based on pre-trained speech recognition
models, however, this can be limiting since this approach primarily measures
speech intelligibility. In this paper, we propose an evaluation technique
involving the training of an ASR model on synthetic speech and assessing its
performance on real speech. Our main assumption is that by training the ASR
model on the synthetic speech, the WER on real speech reflects the similarity
between distributions, a broader assessment of synthetic speech quality beyond
intelligibility. Our proposed metric demonstrates a strong correlation with
both MOS naturalness and MOS intelligibility when compared to SpeechLMScore and
MOSNet on three recent Text-to-Speech (TTS) systems: MQTTS, StyleTTS, and
YourTTS.

论文提出了一种基于训练合成语音自动识别模型并评估其在真实语音上表现的评估技术，该指标与意见分数自然性和可懂性均呈现出强相关性。