利用多语言 STEN-TTS 与 BERT 语言识别的印尼语-英语语码转换语音合成器
Indonesian-English Code-Switching Speech Synthesizer Utilizing Multilingual STEN-TTS and Bert LID
AI总结：
本研究针对印尼语-英语语码转换问题，通过在 STEN-TTS 中引入基于微调 BERT 的逐词语言识别组件并移除语言嵌入，实现了优于单语基线模型的自然度和可懂度。
摘要：
多语言文本转语音系统可将文本转换为多种语言的语音。在许多情况下，文本句子可能包含不同语言的片段，这种现象称为语码转换。这在印度尼西亚尤为常见，尤其是印尼语与英语之间的语码转换。尽管这一现象具有重要意义，但目前尚无研究开发出能够处理这两种语言之间语码转换的多语言 TTS 系统。本研究针对 STEN-TTS 中的印尼语-英语语码转换问题展开。关键修改包括：在文本到音素转换过程中加入语言识别组件，使用微调后的 BERT 进行逐词语言识别，同时从基础模型中移除语言嵌入。实验结果表明，与印尼语和英语基线 STEN-TTS 模型相比，语码转换模型在自然度和语音可懂度方面均取得了更优的表现。
英文摘要：
Multilingual text-to-speech systems convert text into speech across multiple languages. In many cases, text sentences may contain segments in different languages, a phenomenon known as code-switching. This is particularly common in Indonesia, especially between Indonesian and English. Despite its significance, no research has yet developed a multilingual TTS system capable of handling code-switching between these two languages. This study addresses Indonesian-English code-switching in STEN-TTS. Key modifications include adding a language identification component to the text-to-phoneme conversion using finetuned BERT for per-word language identification, as well as removing language embedding from the base model. Experimental results demonstrate that the code-switching model achieves superior naturalness and improved speech intelligibility compared to the Indonesian and English baseline STEN-TTS models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
