GENERATING SPEECH FROM DIGITALLY STORED COARTICULATED SPEECH SEGMENTS
    1.
    发明授权
    GENERATING SPEECH FROM DIGITALLY STORED COARTICULATED SPEECH SEGMENTS 失效
    语生成基于数字存储的KOARTIKULIERTEN语言句段。

    公开(公告)号:EP0380572B1

    公开(公告)日:1994-07-27

    申请号:EP88909070.0

    申请日:1988-10-07

    IPC分类号: G10L5/04

    CPC分类号: G10L13/07

    摘要: A system (87) for generating high quality speech uses coarticulated speech segment data extracted from spoken carrier syllables and digitally compressed for storage using adaptive differential pulse code modulation (ADPCM). The system includes a programmed digital microprocessor (89) with an associated read only memory (91) containing the compressed coarticulated speech segment library, random access memory (93) containing system variables and the sequence of coarticulated speech segments required to generate a desired spoken message, and text to speech chip (95) which provides the sequence of coarticulated speech segments to the RAM (93). The microprocessor (89) operates in accordance with a program stored in ROM (91) to recover the compressed coarticulated speech segment data stored in ROM (91) in a sequence called for by the text to speech chip (95), to reconstruct or ''blow back'' the stored ADPCM data to PCM data, and to concatenate the PCM data into waveforms to produce a real time digital speech waveform. The digital speech waveform is converted to an analog signal via digital to analog converter (97), amplified in amplifier (99) and applied to an audio speaker (101) which generates a high quality spoken message. In the preferred embodiment of the invention, the coarticulated speech segments are diphones.

    GENERATING SPEECH FROM DIGITALLY STORED COARTICULATED SPEECH SEGMENTS
    2.
    发明公开
    GENERATING SPEECH FROM DIGITALLY STORED COARTICULATED SPEECH SEGMENTS 失效
    从数字存储的语音部分生成语音

    公开(公告)号:EP0380572A4

    公开(公告)日:1991-04-17

    申请号:EP88909070

    申请日:1988-10-07

    CPC分类号: G10L13/07

    摘要: A system (87) for generating high quality speech uses coarticulated speech segment data extracted from spoken carrier syllables and digitally compressed for storage using adaptive differential pulse code modulation (ADPCM). The system includes a programmed digital microprocessor (89) with an associated read only memory (91) containing the compressed coarticulated speech segment library, random access memory (93) containing system variables and the sequence of coarticulated speech segments required to generate a desired spoken message, and text to speech chip (95) which provides the sequence of coarticulated speech segments to the RAM (93). The microprocessor (89) operates in accordance with a program stored in ROM (91) to recover the compressed coarticulated speech segment data stored in ROM (91) in a sequence called for by the text to speech chip (95), to reconstruct or ''blow back'' the stored ADPCM data to PCM data, and to concatenate the PCM data into waveforms to produce a real time digital speech waveform. The digital speech waveform is converted to an analog signal via digital to analog converter (97), amplified in amplifier (99) and applied to an audio speaker (101) which generates a high quality spoken message. In the preferred embodiment of the invention, the coarticulated speech segments are diphones.

    GENERATING SPEECH FROM DIGITALLY STORED COARTICULATED SPEECH SEGMENTS
    3.
    发明公开
    GENERATING SPEECH FROM DIGITALLY STORED COARTICULATED SPEECH SEGMENTS 失效
    语生成基于数字存储的KOARTIKULIERTEN语言句段。

    公开(公告)号:EP0380572A1

    公开(公告)日:1990-08-08

    申请号:EP88909070.0

    申请日:1988-10-07

    IPC分类号: G01L5 G01L9 G10L13

    CPC分类号: G10L13/07

    摘要: Système (87) de production de signaux synthétiques utilisant des données relatives à des segments de signaux vocaux coarticulés extraits des syllabes porteuses prononcées et comprimés numériquement en vue de leur enregistrement, par modulation différentielle adaptative par impulsions codées (ADPCM). Le système comprend un microprocesseur numérique programmé (89) associé à une mémoire morte (91) contenant une bibliothèque de segments de signaux vocaux coarticulés comprimés, une mémoire vive (93) contenant le variables systèmes et la séquence de segments de signaux vocaux coarticulés nécessaire pour générer le message parlé désiré, et une puce texte-parole (95) qui fournit à la mémoire vive (93) la séquence de segments de signaux vocaux coarticulés. Le microprocesseur (89) travaille conformément à un programme stocké dans la mémoire morte (91) pour extraire les données relatives aux segments de signaux vocaux coarticulés comprimé contenues dans la mémoire morte (91), formant une séquence appelée par la puce texte-parole (95), pour reconstruire les données MIC à partir des données ADPCM, et pour réunir par concaténation les données MIC en formes d'onde permettant de produire une forme d'onde vocale numérique en temps réel. La forme d'onde vocale numérique est convertie en un signal analogique par un convertisseur numérique-analogique (97) et amplifiée par un amplificateur (99) pour alimenter un haut-parleur (101) reproduisant un message parlé de grande qualité. Dans la variante préférée de la présente invention, les segments de signaux vocaux coarticulés sont constitués par des diphones.