Speech recognition chip for monosyllables

K. Nakamura, Qiang Zhu, S. Maruoka, T. Horiyama, Shinji Kimura, K. Watanabe

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

In the paper, we present a real-time speech recognition chip for monosyllables such as A,B,..., etc. The chip recognizes up to 64 monosyllables based on the Hidden Markov Model (HMM), which is a well known speaker-independent recognition method. The chip accepts a short-speech frame including 256 16-bit digitized samples corresponding to 11.6 ms period, and outputs the 6-bit symbol code of monosyllables for 16 short-frames (corresponding to 185.6 ms). A learning circuit to update HMM parameters for the recognition chip has also been designed, and the recognition chip includes an interface to the learning circuit. We have fabricated the recognition chip by the VDEC Rohm 0.6 μm process on a 4.5 mmx4.5 mm chip. We have also made a layout of the entire circuit including the learning circuit by the VDEC Rohm 0.35 μm process on a 4.9 mmx4.9 mm chip.

Original languageEnglish
Title of host publicationProceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages396-399
Number of pages4
Volume2001-January
ISBN (Print)0780366336
DOIs
Publication statusPublished - 2001
Externally publishedYes
EventAsia and South Pacific Design Automation Conference 2001, ASP-DAC 2001 - Yokohama, Japan
Duration: 2001 Jan 302001 Feb 2

Other

OtherAsia and South Pacific Design Automation Conference 2001, ASP-DAC 2001
CountryJapan
CityYokohama
Period01/1/3001/2/2

Fingerprint

Speech recognition
Networks (circuits)
Hidden Markov models

Keywords

  • Algorithm design and analysis
  • Circuits
  • Feature extraction
  • Hardware
  • Hidden Markov models
  • Linear predictive coding
  • Speech analysis
  • Speech coding
  • Speech recognition
  • Vectors

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Cite this

Nakamura, K., Zhu, Q., Maruoka, S., Horiyama, T., Kimura, S., & Watanabe, K. (2001). Speech recognition chip for monosyllables. In Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC (Vol. 2001-January, pp. 396-399). [913339] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ASPDAC.2001.913339

Speech recognition chip for monosyllables. / Nakamura, K.; Zhu, Qiang; Maruoka, S.; Horiyama, T.; Kimura, Shinji; Watanabe, K.

Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC. Vol. 2001-January Institute of Electrical and Electronics Engineers Inc., 2001. p. 396-399 913339.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nakamura, K, Zhu, Q, Maruoka, S, Horiyama, T, Kimura, S & Watanabe, K 2001, Speech recognition chip for monosyllables. in Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC. vol. 2001-January, 913339, Institute of Electrical and Electronics Engineers Inc., pp. 396-399, Asia and South Pacific Design Automation Conference 2001, ASP-DAC 2001, Yokohama, Japan, 01/1/30. https://doi.org/10.1109/ASPDAC.2001.913339
Nakamura K, Zhu Q, Maruoka S, Horiyama T, Kimura S, Watanabe K. Speech recognition chip for monosyllables. In Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC. Vol. 2001-January. Institute of Electrical and Electronics Engineers Inc. 2001. p. 396-399. 913339 https://doi.org/10.1109/ASPDAC.2001.913339
Nakamura, K. ; Zhu, Qiang ; Maruoka, S. ; Horiyama, T. ; Kimura, Shinji ; Watanabe, K. / Speech recognition chip for monosyllables. Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC. Vol. 2001-January Institute of Electrical and Electronics Engineers Inc., 2001. pp. 396-399
@inproceedings{beb1bb9ea77541a08f2bbeaf42720ee1,
title = "Speech recognition chip for monosyllables",
abstract = "In the paper, we present a real-time speech recognition chip for monosyllables such as A,B,..., etc. The chip recognizes up to 64 monosyllables based on the Hidden Markov Model (HMM), which is a well known speaker-independent recognition method. The chip accepts a short-speech frame including 256 16-bit digitized samples corresponding to 11.6 ms period, and outputs the 6-bit symbol code of monosyllables for 16 short-frames (corresponding to 185.6 ms). A learning circuit to update HMM parameters for the recognition chip has also been designed, and the recognition chip includes an interface to the learning circuit. We have fabricated the recognition chip by the VDEC Rohm 0.6 μm process on a 4.5 mmx4.5 mm chip. We have also made a layout of the entire circuit including the learning circuit by the VDEC Rohm 0.35 μm process on a 4.9 mmx4.9 mm chip.",
keywords = "Algorithm design and analysis, Circuits, Feature extraction, Hardware, Hidden Markov models, Linear predictive coding, Speech analysis, Speech coding, Speech recognition, Vectors",
author = "K. Nakamura and Qiang Zhu and S. Maruoka and T. Horiyama and Shinji Kimura and K. Watanabe",
year = "2001",
doi = "10.1109/ASPDAC.2001.913339",
language = "English",
isbn = "0780366336",
volume = "2001-January",
pages = "396--399",
booktitle = "Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Speech recognition chip for monosyllables

AU - Nakamura, K.

AU - Zhu, Qiang

AU - Maruoka, S.

AU - Horiyama, T.

AU - Kimura, Shinji

AU - Watanabe, K.

PY - 2001

Y1 - 2001

N2 - In the paper, we present a real-time speech recognition chip for monosyllables such as A,B,..., etc. The chip recognizes up to 64 monosyllables based on the Hidden Markov Model (HMM), which is a well known speaker-independent recognition method. The chip accepts a short-speech frame including 256 16-bit digitized samples corresponding to 11.6 ms period, and outputs the 6-bit symbol code of monosyllables for 16 short-frames (corresponding to 185.6 ms). A learning circuit to update HMM parameters for the recognition chip has also been designed, and the recognition chip includes an interface to the learning circuit. We have fabricated the recognition chip by the VDEC Rohm 0.6 μm process on a 4.5 mmx4.5 mm chip. We have also made a layout of the entire circuit including the learning circuit by the VDEC Rohm 0.35 μm process on a 4.9 mmx4.9 mm chip.

AB - In the paper, we present a real-time speech recognition chip for monosyllables such as A,B,..., etc. The chip recognizes up to 64 monosyllables based on the Hidden Markov Model (HMM), which is a well known speaker-independent recognition method. The chip accepts a short-speech frame including 256 16-bit digitized samples corresponding to 11.6 ms period, and outputs the 6-bit symbol code of monosyllables for 16 short-frames (corresponding to 185.6 ms). A learning circuit to update HMM parameters for the recognition chip has also been designed, and the recognition chip includes an interface to the learning circuit. We have fabricated the recognition chip by the VDEC Rohm 0.6 μm process on a 4.5 mmx4.5 mm chip. We have also made a layout of the entire circuit including the learning circuit by the VDEC Rohm 0.35 μm process on a 4.9 mmx4.9 mm chip.

KW - Algorithm design and analysis

KW - Circuits

KW - Feature extraction

KW - Hardware

KW - Hidden Markov models

KW - Linear predictive coding

KW - Speech analysis

KW - Speech coding

KW - Speech recognition

KW - Vectors

UR - http://www.scopus.com/inward/record.url?scp=1542568711&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1542568711&partnerID=8YFLogxK

U2 - 10.1109/ASPDAC.2001.913339

DO - 10.1109/ASPDAC.2001.913339

M3 - Conference contribution

AN - SCOPUS:1542568711

SN - 0780366336

VL - 2001-January

SP - 396

EP - 399

BT - Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC

PB - Institute of Electrical and Electronics Engineers Inc.

ER -