-
公开(公告)号:KR101890303B1
公开(公告)日:2018-08-22
申请号:KR1020110096982
申请日:2011-09-26
Applicant: 삼성전자주식회사 , 서울대학교산학협력단
IPC: G10H1/36
Abstract: 가창음성생성방법에있어서, (a) 일반음성데이터와가창음성데이터를기초로상기일반음성데이터와상기가창음성데이터간의상관관계를나타내는제1변환함수를생성하는단계; (b) 음악정보를상기제1변환함수에반영하여제2변환함수를생성하는단계; 및 (c) 상기제2변환함수를이용하여상기일반음성데이터를변환하여가창음성을생성하는단계를포함하는본 발명의일 실시예에따른가창음성생성방법이개시된다.
-
公开(公告)号:KR101145441B1
公开(公告)日:2012-05-15
申请号:KR1020110036463
申请日:2011-04-20
Applicant: 서울대학교산학협력단
Abstract: PURPOSE: A method for combining sounds of a statistical speech combining system using a switching linear dynamic system is provided to apply a voice database and a switching linear dynamic system which learns an existing education system, thereby combining voices. CONSTITUTION: A system learns a statistical model from a voice database. The system learns a system parameter of a switching linear dynamic system using an ML(Maximum Likelihood) method(S100). The system selects a statistical model and a converter corresponding to an input sentence or an input word. The system uses a learnt statistical model value as an input value. The system combines voices which are from a combined feature vector of the switching linear dynamic system(S200).
Abstract translation: 目的:提供一种使用切换线性动态系统组合统计语音组合系统的声音的方法,以应用语音数据库和学习现有教育系统的切换线性动态系统,从而组合语音。 构成:系统从语音数据库学习统计模型。 该系统使用ML(最大似然)方法(S100)学习切换线性动态系统的系统参数。 系统选择对应于输入语句或输入单词的统计模型和转换器。 系统使用学习的统计模型值作为输入值。 该系统组合了来自开关线性动态系统(S200)的组合特征向量的语音。
-
公开(公告)号:KR1020120041656A
公开(公告)日:2012-05-02
申请号:KR1020110096982
申请日:2011-09-26
Applicant: 삼성전자주식회사 , 서울대학교산학협력단
IPC: G10L13/02
CPC classification number: G10H1/366 , G10H2250/455
Abstract: PURPOSE: A method and an apparatus for efficiently generating a singing voice are provided to convert a normal voice data into a singing voice by preventing degradation of a voice quality. CONSTITUTION: An apparatus generates a first conversion function for indicating correlation between normal voice data and singing voice data(S10). The apparatus reflects music information to the first conversion function. The apparatus generates a second conversion function(S20). The apparatus generates the normal voice data as singing voice by using the second conversion function(S30).
Abstract translation: 目的:提供一种用于有效地产生歌声的方法和装置,用于通过防止语音质量的劣化将普通语音数据转换成歌声。 构成:设备产生用于指示正常语音数据和歌唱语音数据之间的相关性的第一转换功能(S10)。 该装置将音乐信息反映到第一转换功能。 该装置产生第二转换功能(S20)。 该装置通过使用第二转换功能将声音数据作为歌声产生(S30)。
-
-