Automatic sound recognition for the hearing impaired

In Chul Yoo, Dongsuk Yook

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

We present a wearable sound recognition system to assist the hearing impaired. Traditionally, hearing aid dogs are specially trained to facilitate the daily life of the hearing impaired. However, since training hearing aid dogs is costly and time-consuming, it would be desirable to substitute them with an automatic sound recognition system using speech recognition technologies. As the sound recognition system will be used in home environments where background noises and reverberations are high, conventional speech recognition techniques are not directly applicable, since their performance drops off rapidly in these environments. In this paper, we introduce a new sound recognition algorithm which is optimized for mechanical sounds such as doorbells. The new algorithm uses a new distance measure called the normalized peak domination ratio (NPDR) that is based on the characteristic spectral peaks of these sounds. The proposed algorithm showed a sound recognition accuracy of 99.7%, and noise rejection accuracy of 99.7%.

Original languageEnglish
Pages (from-to)2029-2036
Number of pages8
JournalIEEE Transactions on Consumer Electronics
Volume54
Issue number4
DOIs
Publication statusPublished - 2008 Dec 1

Fingerprint

Audition
Acoustic waves
Hearing aids
Speech recognition
Acoustic noise
Reverberation

Keywords

  • Acoustic fingerprint
  • Acoustic scene analysis
  • Auditory system
  • Dogs
  • Euclidean distance
  • Noise
  • Noise measurement
  • Signal to noise ratio
  • Sound recognition
  • Spectral peak
  • Speech recognition

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Media Technology

Cite this

Automatic sound recognition for the hearing impaired. / Yoo, In Chul; Yook, Dongsuk.

In: IEEE Transactions on Consumer Electronics, Vol. 54, No. 4, 01.12.2008, p. 2029-2036.

Research output: Contribution to journalArticle

@article{ee3c430c4d4f4cf19200da490f215673,
title = "Automatic sound recognition for the hearing impaired",
abstract = "We present a wearable sound recognition system to assist the hearing impaired. Traditionally, hearing aid dogs are specially trained to facilitate the daily life of the hearing impaired. However, since training hearing aid dogs is costly and time-consuming, it would be desirable to substitute them with an automatic sound recognition system using speech recognition technologies. As the sound recognition system will be used in home environments where background noises and reverberations are high, conventional speech recognition techniques are not directly applicable, since their performance drops off rapidly in these environments. In this paper, we introduce a new sound recognition algorithm which is optimized for mechanical sounds such as doorbells. The new algorithm uses a new distance measure called the normalized peak domination ratio (NPDR) that is based on the characteristic spectral peaks of these sounds. The proposed algorithm showed a sound recognition accuracy of 99.7{\%}, and noise rejection accuracy of 99.7{\%}.",
keywords = "Acoustic fingerprint, Acoustic scene analysis, Auditory system, Dogs, Euclidean distance, Noise, Noise measurement, Signal to noise ratio, Sound recognition, Spectral peak, Speech recognition",
author = "Yoo, {In Chul} and Dongsuk Yook",
year = "2008",
month = "12",
day = "1",
doi = "10.1109/TCE.2008.4711269",
language = "English",
volume = "54",
pages = "2029--2036",
journal = "IEEE Transactions on Consumer Electronics",
issn = "0098-3063",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Automatic sound recognition for the hearing impaired

AU - Yoo, In Chul

AU - Yook, Dongsuk

PY - 2008/12/1

Y1 - 2008/12/1

N2 - We present a wearable sound recognition system to assist the hearing impaired. Traditionally, hearing aid dogs are specially trained to facilitate the daily life of the hearing impaired. However, since training hearing aid dogs is costly and time-consuming, it would be desirable to substitute them with an automatic sound recognition system using speech recognition technologies. As the sound recognition system will be used in home environments where background noises and reverberations are high, conventional speech recognition techniques are not directly applicable, since their performance drops off rapidly in these environments. In this paper, we introduce a new sound recognition algorithm which is optimized for mechanical sounds such as doorbells. The new algorithm uses a new distance measure called the normalized peak domination ratio (NPDR) that is based on the characteristic spectral peaks of these sounds. The proposed algorithm showed a sound recognition accuracy of 99.7%, and noise rejection accuracy of 99.7%.

AB - We present a wearable sound recognition system to assist the hearing impaired. Traditionally, hearing aid dogs are specially trained to facilitate the daily life of the hearing impaired. However, since training hearing aid dogs is costly and time-consuming, it would be desirable to substitute them with an automatic sound recognition system using speech recognition technologies. As the sound recognition system will be used in home environments where background noises and reverberations are high, conventional speech recognition techniques are not directly applicable, since their performance drops off rapidly in these environments. In this paper, we introduce a new sound recognition algorithm which is optimized for mechanical sounds such as doorbells. The new algorithm uses a new distance measure called the normalized peak domination ratio (NPDR) that is based on the characteristic spectral peaks of these sounds. The proposed algorithm showed a sound recognition accuracy of 99.7%, and noise rejection accuracy of 99.7%.

KW - Acoustic fingerprint

KW - Acoustic scene analysis

KW - Auditory system

KW - Dogs

KW - Euclidean distance

KW - Noise

KW - Noise measurement

KW - Signal to noise ratio

KW - Sound recognition

KW - Spectral peak

KW - Speech recognition

UR - http://www.scopus.com/inward/record.url?scp=58149402898&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58149402898&partnerID=8YFLogxK

U2 - 10.1109/TCE.2008.4711269

DO - 10.1109/TCE.2008.4711269

M3 - Article

VL - 54

SP - 2029

EP - 2036

JO - IEEE Transactions on Consumer Electronics

JF - IEEE Transactions on Consumer Electronics

SN - 0098-3063

IS - 4

ER -