中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

23 records (took 0.02 seconds)

    Speech synthesis using dual neural networks
    11.
    发明申请
    Speech synthesis using dual neural networks 审中-公开
    使用双神经网络的语音合成

    公开(公告)号：WO9825260A3

    公开(公告)日：1998-08-06

    申请号：PCT/US9718815

    申请日：1997-10-15

    Applicant: MOTOROLA INC

    Inventor： KARAALI ORHAN ,  MASSEY NOEL ,  CORRIGAN GERALD

    IPC: G10L13/04 ,  G10L15/06 ,  G10L25/30 ,  G10L5/04

    CPC classification number: G10L13/04 ,  G10L15/063 ,  G10L25/30

    Abstract: A method (500, 600), device (201 and 206) and system (203) provide, in response to text/linguistic information, efficient generation of a parametric representation of speech. A coder parameter generating system provides a principal set and a supplementary set of speech parameters, the principal set of speech parameters being the parametric representation of speech. Then feedback is provided to the coder parameter generating system using the supplementary set of speech parameters to modify the principal set of speech parameters.

    12.
    发明专利
    未知

    公开(公告)号：DE69727046D1

    公开(公告)日：2004-02-05

    申请号：DE69727046

    申请日：1997-10-15

    Applicant: MOTOROLA INC

    Inventor： CORRIGAN GERALD ,  KARAALI ORHAN ,  MASSEY NOEL

    IPC: G10L13/08

    Abstract: The present invention teaches a method (400), device and system (300) utilizing at least one of: mapping a sequence of phones to a sequence of articulatory features and utilizing prominence and boundary information, in addition to a predetermined set of rules for type, phonetic context, syntactic and prosodic context for phones to provide provide a system that generates segment durations efficiently with a small training set.

    15.
    发明专利
    未知

    公开(公告)号：FR2767216A1

    公开(公告)日：1999-02-12

    申请号：FR9808596

    申请日：1998-07-06

    Applicant: MOTOROLA INC

    Inventor： KARAALI ORHAN ,  MASSEY NOEL ,  CORRIGAN GERALD

    IPC: G10L13/02 ,  G10L5/04 ,  G06F15/80

    Abstract: A method (400), device and system (300) provide, in response to linguistic information, efficient generation of a parametric representation of speech using a neural network. The method provides, in response to linguistic information efficient generation of a refined parametric representation of speech, comprising the steps of: A) using a data selection module to retrieve representative parameter vectors for each segment description according to the phonetic segment type and the phonetic segment types included in adjacent segment descriptions; B) interpolating between the representative parameter vectors according to the segment descriptions and duration to provide interpolated statistical parameters; C) converting the interpolated statistical parameters and linguistic information to neural network input parameters; D) utilizing a statistically enhanced neural network/neural network with post-processor to provide neural network output parameters that correspond to a parametric representation of speech; and converting the neural network output parameters to a refined parametric representation of speech.

    16.
    发明专利
    未知

    公开(公告)号：DE69727046T2

    公开(公告)日：2004-06-09

    申请号：DE69727046

    申请日：1997-10-15

    Applicant: MOTOROLA INC

    Inventor： CORRIGAN GERALD ,  KARAALI ORHAN ,  MASSEY NOEL

    IPC: G10L13/08

    Abstract: The present invention teaches a method (400), device and system (300) utilizing at least one of: mapping a sequence of phones to a sequence of articulatory features and utilizing prominence and boundary information, in addition to a predetermined set of rules for type, phonetic context, syntactic and prosodic context for phones to provide provide a system that generates segment durations efficiently with a small training set.

Patent Agency Ranking