-
公开(公告)号:GB2328849B
公开(公告)日:2000-07-12
申请号:GB9815620
申请日:1998-07-20
Applicant: MOTOROLA INC
Inventor: MASSEY NOEL , KARAALI ORHAN , SCHNUR OTTO
-
公开(公告)号:GB2326321A
公开(公告)日:1998-12-16
申请号:GB9812479
申请日:1998-06-11
Applicant: MOTOROLA INC
Inventor: MILLER COREY ANDREW , KARAALI ORHAN , MASSEY NOEL
Abstract: A method is presented for providing, in response to a lexical pronunciation, efficient generation of a postlexical pronunciation, including the steps of: determining lexical phones, lexical features, and boundary information for a predetermined portion of text; and utilizing a pretrained neural network that was pretrained using lexical phones, postlexical phones, lexical features, and boundary information to generate a neural network hypothesis for a postlexical pronunciation of the predetermined portion of text.
-
公开(公告)号:GB2325599B
公开(公告)日:2000-01-26
申请号:GB9811008
申请日:1998-05-21
Applicant: MOTOROLA INC
Inventor: CORRIGAN GERALD E , MASSEY NOEL , KARAALI ORHAN
-
4.
公开(公告)号:GB2328849A
公开(公告)日:1999-03-03
申请号:GB9815620
申请日:1998-07-20
Applicant: MOTOROLA INC
Inventor: MASSEY NOEL , KARAALI ORHAN , SCHNUR OTTO
Abstract: A neural network based parameter system 118 is used for generating a virtual actor (visually-rendered model with speech 132) of which the movements are correlated with synthetic speech.Text 102, used to drive the virtual actor, is converted 104 to a linguistic representation of speech 106, which is converted to neural network linguistic parameters 110 by pre-processor 108. The neural network module 112 converts the neural network linguistic parameters into raw spatial parameters 114, which are finally converted into model parameters 120 by a post-processor 116. These model parameters 120 are then used to drive the virtual actors. Alternatively, a non-neural network based linguistics-to-speech module is used to convert the linguistic representation of speech 106. The speaker profile of a linguistics-to-speech module 126 provides data to change the characteristics of the alternatively-synthesized speech 128.
-
公开(公告)号:DE19825205A1
公开(公告)日:1999-01-14
申请号:DE19825205
申请日:1998-06-05
Applicant: MOTOROLA INC
Inventor: MILLER COREY ANDREW , KARAALI ORHAN , MASSEY NOEL
-
公开(公告)号:GB2346788A
公开(公告)日:2000-08-16
申请号:GB0009708
申请日:1998-07-20
Applicant: MOTOROLA INC
Inventor: MASSEY NOEL , KARAALI ORHAN , SCHNURR OTTO
Abstract: A parameter database 218 is created using a recorder 204, a spatial parameter extractor 208, coupled to the recorder and a linguistic labeler 214 coupled to the recorder. Spatial parameters are stored in the parameter database, correlated with the linguistic labels.
-
公开(公告)号:GB2346527A
公开(公告)日:2000-08-09
申请号:GB0009707
申请日:1998-07-20
Applicant: MOTOROLA INC
Inventor: MASSEY NOEL , KARAALI ORHAN , SCHNURR OTTO
Abstract: A set of speaker profiles are provided, including at least visual profile data and voice profile data. These cause a virtual actor to be displayed 514 with a visual appearance determined by the visual profile data and a voice determined by the voice profile data.
-
公开(公告)号:BE1011892A3
公开(公告)日:2000-02-01
申请号:BE9800314
申请日:1998-04-27
Applicant: MOTOROLA INC
Inventor: CORRIGAN GERALD E , MASSEY NOEL , KARAALI ORHAN
Abstract: Méthode (600), dispositif (514,522) et système (502) qui fournissent, en réponse à l'information comprenant l'information linguistique et au moins un des éléments : information sur le style et information sur la netteté, une génération efficace de paramètres vocaux prosodiquement améliorés. La méthode comprend la détermination de l'information prosodique qui décrit le rythme et l'intonation de la parole à générer, à partir d'au moins un des éléments : information sur le style et information sur la netteté, et l'utilisation d'un système statistique pour convertir l'information comprenant l'information linguistique et l'information prosodique en paramètres vocaux qui décrivent des parties de formes d'onde vocale.
-
公开(公告)号:FR2764725A1
公开(公告)日:1998-12-18
申请号:FR9806759
申请日:1998-05-28
Applicant: MOTOROLA INC
Inventor: MILLER COREY ANDREW , KARAALI ORHAN , MASSEY NOEL
-
公开(公告)号:GB2325599A
公开(公告)日:1998-11-25
申请号:GB9811008
申请日:1998-05-21
Applicant: MOTOROLA INC
Inventor: CORRIGAN GERALD E , MASSEY NOEL , KARAALI ORHAN
Abstract: The method includes determining prosodic information that describes rhythm and intonation of speech to be generated, from at least one of: the style information and the focus information 528; and using a statistical system eg neural network 522 to convert information including the linguistic information and the prosodic information into speech parameters, which describe portions of speech waveforms.
-
-
-
-
-
-
-
-
-