A Robust Speech Communication into Smart Info-Media System

Yoshikazu MIYANAGA; Wataru TAKAHASHI; Shingo YOSHIZAWA

doi:10.1587/transfun.E96.A.2074

A Robust Speech Communication into Smart Info-Media System

Yoshikazu MIYANAGA, Wataru TAKAHASHI, Shingo YOSHIZAWA

Full Text Views

0

Share
Cite this

Summary :

This paper introduces our developed noise robust speech communication techniques and describes its implementation to a smart info-media system, i.e., a small robot. Our designed speech communication system consists of automatic speech detection, recognition, and rejection. By using automatic speech detection and recognition, an observed speech waveform can be recognized without a manual trigger. In addition, using speech rejection, this system only accepts registered speech phrases and rejects any other words. In other words, although an arbitrary input speech waveform can be fed into this system and recognized, the system responds only to the registered speech phrases. The developed noise robust speech processing can reduce various noises in many environments. In addition to the design of noise robust speech recognition, the LSI design of this system has been introduced. By using the design of speech recognition application specific IC (ASIC), we can simultaneously realize low power consumption and real-time processing. This paper describes the LSI architecture of this system and its performances in some field experiments. In terms of current speech recognition accuracy, the system can realize 85-99% under 0-20dB SNR and echo environments.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E96-A No.11 pp.2074-2080

Publication Date: 2013/11/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E96.A.2074

Type of Manuscript: Special Section INVITED PAPER (Special Section on Smart Multimedia & Communication Systems)

Category

Authors

Yoshikazu MIYANAGA
  Hokkaido University
Wataru TAKAHASHI
  Hokkaido University
Shingo YOSHIZAWA
  Kitami Institute of Technology

Keyword

smart info-media system, robust speech recognition, voice activity detection, speech rejection, ASIC, low power consumption design

Cite this

Copy

Yoshikazu MIYANAGA, Wataru TAKAHASHI, Shingo YOSHIZAWA, "A Robust Speech Communication into Smart Info-Media System" in IEICE TRANSACTIONS on Fundamentals, vol. E96-A, no. 11, pp. 2074-2080, November 2013, doi: 10.1587/transfun.E96.A.2074.
Abstract: This paper introduces our developed noise robust speech communication techniques and describes its implementation to a smart info-media system, i.e., a small robot. Our designed speech communication system consists of automatic speech detection, recognition, and rejection. By using automatic speech detection and recognition, an observed speech waveform can be recognized without a manual trigger. In addition, using speech rejection, this system only accepts registered speech phrases and rejects any other words. In other words, although an arbitrary input speech waveform can be fed into this system and recognized, the system responds only to the registered speech phrases. The developed noise robust speech processing can reduce various noises in many environments. In addition to the design of noise robust speech recognition, the LSI design of this system has been introduced. By using the design of speech recognition application specific IC (ASIC), we can simultaneously realize low power consumption and real-time processing. This paper describes the LSI architecture of this system and its performances in some field experiments. In terms of current speech recognition accuracy, the system can realize 85-99% under 0-20dB SNR and echo environments.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/transfun.E96.A.2074/_p

Copy

@ARTICLE{e96-a_11_2074,
author={Yoshikazu MIYANAGA, Wataru TAKAHASHI, Shingo YOSHIZAWA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Robust Speech Communication into Smart Info-Media System},
year={2013},
volume={E96-A},
number={11},
pages={2074-2080},
abstract={This paper introduces our developed noise robust speech communication techniques and describes its implementation to a smart info-media system, i.e., a small robot. Our designed speech communication system consists of automatic speech detection, recognition, and rejection. By using automatic speech detection and recognition, an observed speech waveform can be recognized without a manual trigger. In addition, using speech rejection, this system only accepts registered speech phrases and rejects any other words. In other words, although an arbitrary input speech waveform can be fed into this system and recognized, the system responds only to the registered speech phrases. The developed noise robust speech processing can reduce various noises in many environments. In addition to the design of noise robust speech recognition, the LSI design of this system has been introduced. By using the design of speech recognition application specific IC (ASIC), we can simultaneously realize low power consumption and real-time processing. This paper describes the LSI architecture of this system and its performances in some field experiments. In terms of current speech recognition accuracy, the system can realize 85-99% under 0-20dB SNR and echo environments.},
keywords={},
doi={10.1587/transfun.E96.A.2074},
ISSN={1745-1337},
month={November},}

Copy

TY - JOUR
TI - A Robust Speech Communication into Smart Info-Media System
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2074
EP - 2080
AU - Yoshikazu MIYANAGA
AU - Wataru TAKAHASHI
AU - Shingo YOSHIZAWA
PY - 2013
DO - 10.1587/transfun.E96.A.2074
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E96-A
IS - 11
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - November 2013
AB - This paper introduces our developed noise robust speech communication techniques and describes its implementation to a smart info-media system, i.e., a small robot. Our designed speech communication system consists of automatic speech detection, recognition, and rejection. By using automatic speech detection and recognition, an observed speech waveform can be recognized without a manual trigger. In addition, using speech rejection, this system only accepts registered speech phrases and rejects any other words. In other words, although an arbitrary input speech waveform can be fed into this system and recognized, the system responds only to the registered speech phrases. The developed noise robust speech processing can reduce various noises in many environments. In addition to the design of noise robust speech recognition, the LSI design of this system has been introduced. By using the design of speech recognition application specific IC (ASIC), we can simultaneously realize low power consumption and real-time processing. This paper describes the LSI architecture of this system and its performances in some field experiments. In terms of current speech recognition accuracy, the system can realize 85-99% under 0-20dB SNR and echo environments.
ER -