中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

13 records (took 0.023 seconds)

    VOICE SYNTHESIS METHOD BY LINK AND PARTIAL OVERLAP OF WAVEFORMS
    1.
    发明专利
    VOICE SYNTHESIS METHOD BY LINK AND PARTIAL OVERLAP OF WAVEFORMS 失效

    公开(公告)号：JPH08110789A

    公开(公告)日：1996-04-30

    申请号：JP17555395

    申请日：1995-06-20

    Applicant: CSELT CENTRO STUDI LAB TELECOM

    Inventor： FOTI ENZO ,  NEBBIA LUCIANO ,  SANDRI STEFANO

    IPC: G10L13/04 ,  G10L3/00 ,  G10L5/04

    Abstract: PURPOSE: To reduce the processing time, and to improve the natural sound of the synthesizing signal by leaving a part of the original signal, which includes the basic information of each block, as it is, and changing the residual part. CONSTITUTION: In this sound signal synthesizing method by connection of waveform, which present the unit of element of the sound signal, with the lapse of time, at least the waveform related to the sound to be output as voice is divided into plural blocks, which are synchronized with the basic frequency of the signal and which correspond to the response of sound pipe in relation to a continuous stimulus impact of a vocal cord, and weighting is performed in each block, and the signal generated by the weighting is substituted with a copy thereof when the time is shifted by the quantity, which depends on the rhythm element information, and the sifted signal are overlapped and added to each other for sound synthesis. In each block of the original signal to be regenerated by the synthesis, a non-changed part of the original signal, which includes the basic information and which is not changed in the synthesized signal so as to be regenerated, is discriminated, and weighting, overlap and addition are performed to the residual block.

    3.
    发明专利
    未知

    公开(公告)号：ITTO940756D0

    公开(公告)日：1994-09-29

    申请号：ITTO940756

    申请日：1994-09-29

    Applicant: CSELT CENTRO STUDI LAB TELECOM

    Inventor： FOTI ENZO ,  NEBBIA LUCIANO ,  SANDRI STEFANO

    IPC: G10L13/04

    Abstract: Method for speech signal synthesis by means of time concatenation of waveforms representing elementary units of speech signal, in which: at least the waveforms associated to voiced sounds are subdivided into a plurality of intervals, corresponding to the responses of the vocal duct to a series of excitation impulses of the vocal cords, synchronous with the fundamental frequency of the signal; each interval is subjected to a weighting; the signals resulting from the weighting are replaced with a replica thereof shifted in time by an amount that depends on a prosodic information; and the synthesis is carried out by overlapping and adding the shifted signals. In each interval of original signal to be reproduced in synthesis, an unchanging part is identified, which contains the fundamental information and which is reproduced unaltered in the synthesized signal, and the operations of weighting, overlapping and adding involve only the remaining part of the interval.

    5.
    发明专利
    未知

    公开(公告)号：DE706170T1

    公开(公告)日：1998-11-19

    申请号：DE95107944

    申请日：1995-05-24

    Applicant: CSELT CENTRO STUDI LAB TELECOM

    Inventor： FOTI ENZO ,  NEBBIA LUCIANO ,  SANDRI STEFANO

    IPC: G10L13/04 ,  G10L5/04

    Abstract: Method for speech signal synthesis by means of time concatenation of waveforms representing elementary units of speech signal, in which: at least the waveforms associated to voiced sounds are subdivided into a plurality of intervals, corresponding to the responses of the vocal duct to a series of excitation impulses of the vocal cords, synchronous with the fundamental frequency of the signal; each interval is subjected to a weighting; the signals resulting from the weighting are replaced with a replica thereof shifted in time by an amount that depends on a prosodic information; and the synthesis is carried out by overlapping and adding the shifted signals. In each interval of original signal to be reproduced in synthesis, an unchanging part is identified, which contains the fundamental information and which is reproduced unaltered in the synthesized signal, and the operations of weighting, overlapping and adding involve only the remaining part of the interval.

    6.
    发明专利
    未知

    公开(公告)号：ES2113329T1

    公开(公告)日：1998-05-01

    申请号：ES95107944

    申请日：1995-05-24

    Applicant: CSELT CENTRO STUDI LAB TELECOM

    Inventor： FOTI ENZO ,  NEBBIA LUCIANO ,  SANDRI STEFANO

    IPC: G10L13/04 ,  G10L5/04

    Abstract: Method for speech signal synthesis by means of time concatenation of waveforms representing elementary units of speech signal, in which: at least the waveforms associated to voiced sounds are subdivided into a plurality of intervals, corresponding to the responses of the vocal duct to a series of excitation impulses of the vocal cords, synchronous with the fundamental frequency of the signal; each interval is subjected to a weighting; the signals resulting from the weighting are replaced with a replica thereof shifted in time by an amount that depends on a prosodic information; and the synthesis is carried out by overlapping and adding the shifted signals. In each interval of original signal to be reproduced in synthesis, an unchanging part is identified, which contains the fundamental information and which is reproduced unaltered in the synthesized signal, and the operations of weighting, overlapping and adding involve only the remaining part of the interval.

    8.
    发明专利
    未知

    公开(公告)号：DE69521955D1

    公开(公告)日：2001-09-06

    申请号：DE69521955

    申请日：1995-05-24

    Applicant: CSELT CENTRO STUDI LAB TELECOM

    Inventor： FOTI ENZO ,  NEBBIA LUCIANO ,  SANDRI STEFANO

    IPC: G10L13/04 ,  G10L13/06

    Abstract: Method for speech signal synthesis by means of time concatenation of waveforms representing elementary units of speech signal, in which: at least the waveforms associated to voiced sounds are subdivided into a plurality of intervals, corresponding to the responses of the vocal duct to a series of excitation impulses of the vocal cords, synchronous with the fundamental frequency of the signal; each interval is subjected to a weighting; the signals resulting from the weighting are replaced with a replica thereof shifted in time by an amount that depends on a prosodic information; and the synthesis is carried out by overlapping and adding the shifted signals. In each interval of original signal to be reproduced in synthesis, an unchanging part is identified, which contains the fundamental information and which is reproduced unaltered in the synthesized signal, and the operations of weighting, overlapping and adding involve only the remaining part of the interval.

    9.
    发明专利
    未知

    公开(公告)号：IT1266943B1

    公开(公告)日：1997-01-21

    申请号：ITTO940756

    申请日：1994-09-29

    Applicant: CSELT CENTRO STUDI LAB TELECOM

    Inventor： FOTI ENZO ,  NEBBIA LUCIANO ,  SANDRI STEFANO

    IPC: G10L13/04

    Abstract: Method for speech signal synthesis by means of time concatenation of waveforms representing elementary units of speech signal, in which: at least the waveforms associated to voiced sounds are subdivided into a plurality of intervals, corresponding to the responses of the vocal duct to a series of excitation impulses of the vocal cords, synchronous with the fundamental frequency of the signal; each interval is subjected to a weighting; the signals resulting from the weighting are replaced with a replica thereof shifted in time by an amount that depends on a prosodic information; and the synthesis is carried out by overlapping and adding the shifted signals. In each interval of original signal to be reproduced in synthesis, an unchanging part is identified, which contains the fundamental information and which is reproduced unaltered in the synthesized signal, and the operations of weighting, overlapping and adding involve only the remaining part of the interval.

    Method of Speech Synthesis by Means of Concatenation and Partial Overlapping of Waveforms
    10.
    发明专利
    Method of Speech Synthesis by Means of Concatenation and Partial Overlapping of Waveforms 未知

    公开(公告)号：CA2150614A1

    公开(公告)日：1996-03-30

    申请号：CA2150614

    申请日：1995-05-31

    Applicant: CSELT CENTRO STUDI LAB TELECOM

    Inventor： FOTI ENZO ,  NEBBIA LUCIANO ,  SANDRI STEFANO

    IPC: G10L13/04 ,  G10L9/00

    Abstract: Method for speech signal synthesis by means of time concatenation of waveforms representing elementary units of speech signal, in which: at least the waveforms associated to voiced sounds are subdivided into a plurality of intervals, corresponding to the responses of the vocal duct to a series of excitation impulses of the vocal cords, synchronous with the fundamental frequency of the signal; each interval is subjected to a weighting; the signals resulting from the weighting are replaced with a replica thereof shifted in time by an amount that depends on a prosodic information; and the synthesis is carried out by overlapping and adding the shifted signals. In each interval of original signal to be reproduced in synthesis, an unchanging part is identified, which contains the fundamental information and which is reproduced unaltered in the synthesized signal, and the operations of weighting, overlapping and adding involve only the remaining part of the interval.

Patent Agency Ranking