基于转写提示 Whisper 与词典增强解码的日语语音标注
Transcript-Prompted Whisper with Dictionary-Enhanced Decoding for Japanese Speech Annotation
AI总结：
本文面向日语 TTS 数据集构建，提出以真实转写为条件微调 Whisper，并结合词典增强解码同步生成字素与音位、韵律标签，显著提升标注质量且合成语音自然度媲美人工标注。
摘要：
本文提出一种在给定音频-转写对上标注音位标签和韵律标签的方法，旨在构建日语文本转语音（TTS）数据集。我们的方法是对大规模预训练自动语音识别（ASR）模型进行微调，以真实转写作为条件，使其同时输出短语级字素和标注标签。为进一步纠正音位标注中的错误，我们采用了一种利用词典先验知识的解码策略。客观评估结果表明，所提方法优于以往仅依赖文本或音频的方法。主观评估结果显示，使用以本文方法标注的标签训练的 TTS 模型所合成语音的自然度，与使用人工标注训练的模型相当。
英文摘要：
In this paper, we propose a method for annotating phonemic and prosodic labels on a given audio-transcript pair, aimed at constructing Japanese text-to-speech (TTS) datasets. Our approach involves fine-tuning a large-scale pre-trained automatic speech recognition (ASR) model, conditioned on ground truth transcripts, to simultaneously output phrase-level graphemes and annotation labels. To further correct errors in phonemic labeling, we employ a decoding strategy that utilizes dictionary prior knowledge. The objective evaluation results demonstrate that our proposed method outperforms previous approaches relying solely on text or audio. The subjective evaluation results indicate that the naturalness of speech synthesized by the TTS model, trained with labels annotated using our method, is comparable to that of a model trained with manual annotations.
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。
