Allophone DB
Acoustic database management system
| First version: 1996 | Last version: 2000 |
| Application: | ||||
| The system is
used by the team in its R&D activities. Thus, a great
number of listening experiments has been carried out in
order to test the degree of tolerance of physical
parameters of each vowel and consonant allophone to its
inappropriate right and left contexts. These experiments
maked it possible to define the necessary inventory of
allophones, sufficient for the high quality Russian text-to-speech
synthesis. The results are used in the speech synthesis
systems created by the team. The system is also used by the Pronunciation Model, in order to generate sound sequences reflecting various deviations from the pronunciation standard – from dialectal speech and regional accents to social dialects. |
||||
| Description: | ||||
| The system is designed for the storage of the inventory of all theoretically possible Russian allophones. The description and storage unit is allophone. The position of the allophone with regard to stress, its right and left context is included into the description of the allophone. The system makes it possible not only to listen to and analyse selected allophones, but also to compile any word and phrase using them. | ||||
| Languages processed: | ||||
| Russian | ||||
| Hardware/software requirements: | ||||
| IBM PC or compatible, Windows. The system
is implemented in ANSI C. The sound material is represented in the 16 bit Raw PCM format at 16 KHz sample rate. |
||||
| Distribution: | Internal use | |||
| Developer team: | Contact person: | |||
| Department for phonetics and methods of teaching foreign languages, SPbGU | Pavel A. Skrelin Phone: (+7 812) 328 95 65 E-mail: paul@PS1089.spb.edu, paul@phonet.lang.pu.ru |
|||