Dual channel based speech enhancement using novelty filter for robust speech recognition in automobile environment

Jounghoon Beh, Robert H. Baran, Hanseok Ko

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

In this paper, a simple and effective dual channel speech enhancement algorithm is proposed. The proposed algorithm incorporates a novelty filter scheme, performing associative memory and aiming at improving the performance of the dual channel Generalized Sidelobe Canceller (GSC.) The novelty filter is demonstrated as effective for enhancing the reference noise used in the dual channel GSC, such that the assumptions required for adaptive noise cancellation are satisfied. In this paper, the concept of a novelty filter scheme is described, in addition to the conditions required to guarantee the performance of the dual channel GSC and the method of applying the novelty filter scheme to speech enhancement objectives. In representative experiments, superiority of the proposed algorithm is demonstrated using three objective measures; segmental Signal to Noise Ratio (SNR), Log Spectral Distance (LSD) and word accuracy, which are evaluated via speech data recorded in real automobile environments.

Original languageEnglish
Pages (from-to)583-589
Number of pages7
JournalIEEE Transactions on Consumer Electronics
Volume52
Issue number2
DOIs
Publication statusPublished - 2006 May 1

Fingerprint

Speech enhancement
Speech recognition
Automobiles
Signal to noise ratio
Data storage equipment
Experiments

Keywords

  • Generalized Sidelobe Canceller
  • Novelty filter
  • Speech enhancement
  • Speech recognition

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Dual channel based speech enhancement using novelty filter for robust speech recognition in automobile environment. / Beh, Jounghoon; Baran, Robert H.; Ko, Hanseok.

In: IEEE Transactions on Consumer Electronics, Vol. 52, No. 2, 01.05.2006, p. 583-589.

Research output: Contribution to journalArticle

@article{5055897098384a64b88e7ea005bcb90d,
title = "Dual channel based speech enhancement using novelty filter for robust speech recognition in automobile environment",
abstract = "In this paper, a simple and effective dual channel speech enhancement algorithm is proposed. The proposed algorithm incorporates a novelty filter scheme, performing associative memory and aiming at improving the performance of the dual channel Generalized Sidelobe Canceller (GSC.) The novelty filter is demonstrated as effective for enhancing the reference noise used in the dual channel GSC, such that the assumptions required for adaptive noise cancellation are satisfied. In this paper, the concept of a novelty filter scheme is described, in addition to the conditions required to guarantee the performance of the dual channel GSC and the method of applying the novelty filter scheme to speech enhancement objectives. In representative experiments, superiority of the proposed algorithm is demonstrated using three objective measures; segmental Signal to Noise Ratio (SNR), Log Spectral Distance (LSD) and word accuracy, which are evaluated via speech data recorded in real automobile environments.",
keywords = "Generalized Sidelobe Canceller, Novelty filter, Speech enhancement, Speech recognition",
author = "Jounghoon Beh and Baran, {Robert H.} and Hanseok Ko",
year = "2006",
month = "5",
day = "1",
doi = "10.1109/TCE.2006.1649683",
language = "English",
volume = "52",
pages = "583--589",
journal = "IEEE Transactions on Consumer Electronics",
issn = "0098-3063",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Dual channel based speech enhancement using novelty filter for robust speech recognition in automobile environment

AU - Beh, Jounghoon

AU - Baran, Robert H.

AU - Ko, Hanseok

PY - 2006/5/1

Y1 - 2006/5/1

N2 - In this paper, a simple and effective dual channel speech enhancement algorithm is proposed. The proposed algorithm incorporates a novelty filter scheme, performing associative memory and aiming at improving the performance of the dual channel Generalized Sidelobe Canceller (GSC.) The novelty filter is demonstrated as effective for enhancing the reference noise used in the dual channel GSC, such that the assumptions required for adaptive noise cancellation are satisfied. In this paper, the concept of a novelty filter scheme is described, in addition to the conditions required to guarantee the performance of the dual channel GSC and the method of applying the novelty filter scheme to speech enhancement objectives. In representative experiments, superiority of the proposed algorithm is demonstrated using three objective measures; segmental Signal to Noise Ratio (SNR), Log Spectral Distance (LSD) and word accuracy, which are evaluated via speech data recorded in real automobile environments.

AB - In this paper, a simple and effective dual channel speech enhancement algorithm is proposed. The proposed algorithm incorporates a novelty filter scheme, performing associative memory and aiming at improving the performance of the dual channel Generalized Sidelobe Canceller (GSC.) The novelty filter is demonstrated as effective for enhancing the reference noise used in the dual channel GSC, such that the assumptions required for adaptive noise cancellation are satisfied. In this paper, the concept of a novelty filter scheme is described, in addition to the conditions required to guarantee the performance of the dual channel GSC and the method of applying the novelty filter scheme to speech enhancement objectives. In representative experiments, superiority of the proposed algorithm is demonstrated using three objective measures; segmental Signal to Noise Ratio (SNR), Log Spectral Distance (LSD) and word accuracy, which are evaluated via speech data recorded in real automobile environments.

KW - Generalized Sidelobe Canceller

KW - Novelty filter

KW - Speech enhancement

KW - Speech recognition

UR - http://www.scopus.com/inward/record.url?scp=33746948299&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33746948299&partnerID=8YFLogxK

U2 - 10.1109/TCE.2006.1649683

DO - 10.1109/TCE.2006.1649683

M3 - Article

AN - SCOPUS:33746948299

VL - 52

SP - 583

EP - 589

JO - IEEE Transactions on Consumer Electronics

JF - IEEE Transactions on Consumer Electronics

SN - 0098-3063

IS - 2

ER -