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)	語音保護方法、系統和語音保護模型的訓練方法
專利名稱(英)	METHOD AND SYSTEM FOR VOICE PROTECTION, AND TRAINING METHOD OF VOICE PROTECTION MODEL
專利家族	中華民國：I911038
專利權人	國立清華大學 100.00%
發明人	李祈均,楊晶宇
技術領域	通信傳輸,資訊工程

專利摘要(中)
本發明提出一種訓練語音保護模型的方法，適用於包括語音庫的系統，方法包括：從語音庫選擇第一語音和第二語音；提取第一語音的多個第一特徵；提取第二語音的多個第二特徵；基於第一語音、多個第一特徵以及多個第二特徵，利用語音保護模型，得到第一混合語音；提取第一混合語音的多個第三特徵；計算多個第三特徵與多個第一特徵之間的第一距離，以及多個第三特徵與多個第二特徵之間的第二距離；根據第一距離和第二距離，計算損失函數；以及根據損失函數更新語音保護模型。上述損失函數與第一距離正相關，並且與第二距離負相關。

專利摘要(中)

本發明提出一種訓練語音保護模型的方法，適用於包括語音庫的系統，方法包括：從語音庫選擇第一語音和第二語音；提取第一語音的多個第一特徵；提取第二語音的多個第二特徵；基於第一語音、多個第一特徵以及多個第二特徵，利用語音保護模型，得到第一混合語音；提取第一混合語音的多個第三特徵；計算多個第三特徵與多個第一特徵之間的第一距離，以及多個第三特徵與多個第二特徵之間的第二距離；根據第一距離和第二距離，計算損失函數；以及根據損失函數更新語音保護模型。上述損失函數與第一距離正相關，並且與第二距離負相關。

專利摘要(英)
A training method for voice protection model is provided. The method includes: selecting a first speech and a second speech from the speech database; extracting multiple first features from the first speech; extracting multiple second features from the second speech; generating a first mixed speech based on the first speech, the first features, and the second features using the voice protection model; extracting multiple third features from the first mixed speech; calculating a first distance between the third features and the first features, and a second distance between the third features and the second features; calculating a loss function based on the first distance and the second distance; and updating the speech protection model based on the loss function. The loss function is positively correlated with the first distance, and negatively correlated with the second distance.

專利摘要(英)

A training method for voice protection model is provided. The method includes: selecting a first speech and a second speech from the speech database; extracting multiple first features from the first speech; extracting multiple second features from the second speech; generating a first mixed speech based on the first speech, the first features, and the second features using the voice protection model; extracting multiple third features from the first mixed speech; calculating a first distance between the third features and the first features, and a second distance between the third features and the second features; calculating a loss function based on the first distance and the second distance; and updating the speech protection model based on the loss function. The loss function is positively correlated with the first distance, and negatively correlated with the second distance.

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