Global Patent Index - EP 1777697 A2

EP 1777697 A2 20070425 - Method for speech synthesis without prosody modification

Title (en)

Method for speech synthesis without prosody modification

Title (de)

Verfahren zur Sprachsynthese ohne Änderung der Prosodie

Title (fr)

Procédé de synthèse vocale sans modification de prosodie

Publication

EP 1777697 A2 20070425 (EN)

Application

EP 07002565 A 20011203

Priority

  • EP 01128765 A 20011203
  • US 25116700 P 20001204
  • US 85052701 A 20010507

Abstract (en)

A speech synthesizer is provided that concatenates stored samples of speech units without modifying the prosody of the samples. The present invention is able to achieve a high level of naturalness in synthesized speech with a carefully designed training speech corpus by storing samples based on the prosodic and phonetic context in which they occur. In particular, some embodiments of the present invention limit the training text to those sentences that will produce the most frequent sets of prosodic contexts for each speech unit. Further embodiments of the present invention also provide a multi-tier selection mechanism for selecting a set of samples that will produce the most natural sounding speech.

IPC 8 full level

G10L 13/07 (2013.01); G10L 13/04 (2013.01)

CPC (source: EP)

G10L 13/07 (2013.01); G10L 13/04 (2013.01)

Citation (applicant)

  • US 6064960 A 20000516 - BELLEGARDA JEROME R [US], et al
  • X. HUANG ET AL.: "Recent Improvements on Microsoft's Trainable Text-to-Speech System - Whistler", IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, ICASSP-97, 21 April 1997 (1997-04-21), pages 959 - 962, XP000822608, DOI: doi:10.1109/ICASSP.1997.596097
  • TIEN YING FUNG; HELEN M. MENG: "Concatenating Syllables for Response Generation in Spoken Language Applications", IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 5 June 2000 (2000-06-05), pages 933 - 936
  • HUNT ET AL.: "Unit Selection in a Concatenative Speech Synthesis System using a Large Speech Database", 1996 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING - PROCEEDINGS (ICASSP, vol. 1, no. 21, 7 May 1996 (1996-05-07), pages 373 - 376, XP002133444, DOI: doi:10.1109/ICASSP.1996.541110

Designated contracting state (EPC)

AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE TR

DOCDB simple family (publication)

EP 1777697 A2 20070425; EP 1777697 A3 20080618; EP 1777697 B1 20130320

DOCDB simple family (application)

EP 07002565 A 20011203