arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.01033eess.AS
收藏

KazEmoTTS:一个用于哈萨克语情感文本到语音合成的数据集

KazEmoTTS: A Dataset for Kazakh Emotional Text-to-Speech Synthesis

Adal Abilbekov, Saida Mussakhojayeva, Rustem Yeshpanov, Huseyin Atakan Varol

AI总结:

本文构建了包含54,760个音频-文本对、覆盖六种情感的哈萨克语情感TTS数据集KazEmoTTS,并训练TTS模型,通过客观与主观评估验证了合成语音质量。

摘要:

本研究聚焦于 KazEmoTTS 数据集的构建,该数据集面向哈萨克语情感文本到语音(TTS)应用。KazEmoTTS 包含 54,760 个音频-文本对,总时长 74.85 小时,其中女性叙述者提供 34.23 小时,两位男性叙述者提供 40.62 小时。所考虑的情感列表包括“中性”、“愤怒”、“高兴”、“悲伤”、“害怕”和“惊讶”。我们还开发了一个在 KazEmoTTS 数据集上训练的 TTS 模型。采用客观和主观评估来评价合成语音的质量,得到的 MCD 分数在 6.02 至 7.67 范围内,同时 MOS 在 3.51 至 3.57 之间。为便于复现并启发进一步研究,我们已在 GitHub 仓库中公开了代码、预训练模型和数据集。

英文摘要:

This study focuses on the creation of the KazEmoTTS dataset, designed for emotional Kazakh text-to-speech (TTS) applications. KazEmoTTS is a collection of 54,760 audio-text pairs, with a total duration of 74.85 hours, featuring 34.23 hours delivered by a female narrator and 40.62 hours by two male narrators. The list of the emotions considered include "neutral", "angry", "happy", "sad", "scared", and "surprised". We also developed a TTS model trained on the KazEmoTTS dataset. Objective and subjective evaluations were employed to assess the quality of synthesized speech, yielding an MCD score within the range of 6.02 to 7.67, alongside a MOS that spanned from 3.51 to 3.57. To facilitate reproducibility and inspire further research, we have made our code, pre-trained model, and dataset accessible in our GitHub repository.

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。

↑