專利授權區國立清華大學國際產學營運總中心 Operations Center for Industry Collaboration

搜尋專利授權區

關鍵字

» 新增關鍵字

選單

專利授權區

專利授權區
專利名稱(中)	透過歌聲轉換設計個人化虛擬歌手的方法及裝置
專利名稱(英)	METHOD AND APPARATUS FOR MULTI-SPEAKER SINGING VOICE SYNTHESIS
專利家族	中華民國：I836255
專利權人	國立清華大學 100.00%
發明人	蘇豐文,江甘霖,蘇時頤
技術領域	文化創意,資訊工程

專利摘要(中)
一種多說話者的歌聲合成方法。此方法包括：解析使用一符號表示的歌譜文件，以擷取出多個歌詞及多個音符；從一音頻資料庫載入所擷取的各音符的音頻資料；使用聲碼器對音頻資料進行聲學建模，以調整各音頻資料並拼接調整後的音頻資料以產生歌聲資料；以及利用一語音轉換模型的生成器將歌聲資料中的多個聲學特徵轉換為以目標屬性為條件的輸出特徵，並根據語音轉換模型的多種損失訓練語音轉換模型，以獲得輸出特徵最佳化的合成歌聲資料。

專利摘要(中)

一種多說話者的歌聲合成方法。此方法包括：解析使用一符號表示的歌譜文件，以擷取出多個歌詞及多個音符；從一音頻資料庫載入所擷取的各音符的音頻資料；使用聲碼器對音頻資料進行聲學建模，以調整各音頻資料並拼接調整後的音頻資料以產生歌聲資料；以及利用一語音轉換模型的生成器將歌聲資料中的多個聲學特徵轉換為以目標屬性為條件的輸出特徵，並根據語音轉換模型的多種損失訓練語音轉換模型，以獲得輸出特徵最佳化的合成歌聲資料。

專利摘要(英)
A method and an apparatus for multi-speaker singing voice synthesis are provided. In the method, a music score file represented by symbols is parsed to extract multiple lyrics and multiple notes. Audio data of each of the notes is loaded from an audio database. A vocoder is used to perform acoustic modeling on the audio data to adjust each audio data and concatenate the adjusted audio data to generate singing voice data. A generator of a voice conversion model generator is used to convert multiple acoustic features in the singing voice data into output features conditioned on target attributes, and the voice conversion model is trained according to multiple types of losses of the voice conversion model to obtain synthetic singing voice data with optimized output features.

專利摘要(英)

A method and an apparatus for multi-speaker singing voice synthesis are provided. In the method, a music score file represented by symbols is parsed to extract multiple lyrics and multiple notes. Audio data of each of the notes is loaded from an audio database. A vocoder is used to perform acoustic modeling on the audio data to adjust each audio data and concatenate the adjusted audio data to generate singing voice data. A generator of a voice conversion model generator is used to convert multiple acoustic features in the singing voice data into output features conditioned on target attributes, and the voice conversion model is trained according to multiple types of losses of the voice conversion model to obtain synthetic singing voice data with optimized output features.

聯絡資訊
承辦人姓名	李曉琪
承辦人電話	03-5715131 #31061
承辦人Email	hsiaochi@mx.nthu.edu.tw