Presentation 2005/12/8
The Speech Recognition System that Decodes Category of Spectrogram
Shinji KARASAWA, Hiroshi SAKURABA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A speech sound spectrogram recognition system is investigated. The device decodes serial data on plural frequency components of speech voice. That is, serially inputting sound spectrograms are shifted intermittently by means of 2-dimensional registers. The subsets of impulses on a speech sound are decoded through pattern matching processes. Here, a new semiconductor device is used for programmable look-up table that memorizes a spectrogram as the preconditions of the decoder. The common part of spectrograms on a same word is memorized in the device. Moreover, spectrograms on speech-waves those amplitude are compressed for normalization are measured.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Speech recognition / Spectrogram / Programmable look-up table / 2-dimentional register
Paper # HIP2005-95
Date of Issue

Conference Information
Committee HIP
Conference Date 2005/12/8(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) The Speech Recognition System that Decodes Category of Spectrogram
Sub Title (in English)
Keyword(1) Speech recognition
Keyword(2) Spectrogram
Keyword(3) Programmable look-up table
Keyword(4) 2-dimentional register
1st Author's Name Shinji KARASAWA
1st Author's Affiliation Miyagi National College of Technology()
2nd Author's Name Hiroshi SAKURABA
2nd Author's Affiliation Miyagi National College of Technology
Date 2005/12/8
Paper # HIP2005-95
Volume (vol) vol.105
Number (no) 479
Page pp.pp.-
#Pages 6
Date of Issue