Speech synthesis system

• US 3,892,919 A
• Filed: 11/12/1973
• Issued: 07/01/1975
• Est. Priority Date: 11/13/1972
• Status: Expired due to Term

• Current Assignee: Akira Ichikawa
• Original Assignee: Akira Ichikawa
• Inventors: Ichikawa, Akira
• Primary Examiner(s): Claffy, Kathleen H.
• Assistant Examiner(s): Kemeny, E. S. Matt
• Application Number:
  US05/414,746
• Time in Patent Office: 596 Days
• Field of Search: 179/1SM 340/148-152
• US Class Current: 704/267
• CPC Class Codes: G10L 13/07 Concatenation rules

Abstract

In a system in which a plurality of previously recorded waveforms corresponding to phonetic elements separately picked up from natural voice and having a pitch length, are connected to form any required speech, the degradation in the quality of the synthesized speech due to the discontinuity in the waveform of the synthesized speech is prevented by so controlling the period of reading out each phonetic element as to change the period stepwise at intervals of several phonetic elements (i.e., pitch lengths).

Claims

1. A speech synthesis system comprising:

a speech segment memory which stores a plurality of speech segments;

a synthesizing apparatus, coupled to said speech segment memory, including first means for selecting desired speech segments from said speech segment memory, second means, coupled to said first means, for controlling the pitch period of each of said desired speech segments, so as to change the pitch frequency of the synthesized speech stepwise, and third means, coupled to said first means and said second means, for connecting the desired pitch controlled speech segments together.

2. A speech synthesis system according to claim 1, wherein said second means includes means for adjusting the intervals of the stepwise change between a quarter of a syllable and a full syllable.

3. A speech synthesis system comprising:

a. a data processing circuit to convert code signals representative of the syllables of words to be synthesized into control signals for speech synthesis;

b. a speech segment memory to store speech segments each having a waveform of about a pitch length;

c. a speech synthesizing apparatus, coupled to said data processing circuit and to said speech segment memory, and including first means for selecting desired speech segments in said speech segment memory second means, coupled to said first means, for controlling the read time of each of the selected speech segments, so as to change the pitch period of the synthesized speech stepwise at intervals of a quarter of a syllable to a full syllable and, third means, coupled to said first means and to said second means, for synthesizing speech sound waveform signals by connecting the selected and pitch controlled speech segment signals together, in response to the control signals from the data processing circuit; and

d. an electro-acoustic converting device, coupled to said speech segment memory and said speech synthesizing apparatus, for converting the speech sound waveform signals into corresponding speech sounds.