Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Speech Recognition in Severely Disturbed Environments Combining Ear-Mic and Active Noise Control
Responsible organisation
2002 (English)Conference paper, (Refereed) Published
Abstract [en]

A microphone for personal communication is placed inside the external auditory canal of a user. A pair of ear-muffs equippedwith Active Noise Control (ANC) are fitted onto the head of the user. The combination of passive and active noise reduction makes communication more reliable when performed in noisy environments. In this paper, a Hidden Markov Model (HMM) speech recognition system is used to assess the quality of speech signals recorded using an ear-mic combined with ANC. In addition, speech recognition itself can be of interest in many situations. For example, many functions in a vehicle can be controlled by instructions spoken by the user and speech controlled functionality improves safety. Hence, speech recognition is a growing field in vehicular technology. If the speech intelligibility and by that the speech recognition robustness could be increased in a speech recognition controlled system implemented in a vehicle, the safety would be further improved.

Abstract [sv]

En taligenkännare används för att påvisa en förbättring av talkvalitet då en mikrofon för kommunikationsändamål placeras i hörselgången på en användare och detta kombineras med ett par aktiva hörselkåpor.

Place, publisher, year, edition, pages
Detroit, MI, 2002.
Keyword [en]
Speech enhancement, Active noise control, Ear-mic, Speech recognition
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:bth-9448Local ID: oai:bth.se:forskinfoE16BEBE37E53BCC2C1256C6B00400B20OAI: oai:DiVA.org:bth-9448DiVA: diva2:837297
Conference
Internoise 2002
Available from: 2012-09-18 Created: 2002-11-08 Last updated: 2015-06-30Bibliographically approved

Open Access in DiVA

fulltext(545 kB)35 downloads
File information
File name FULLTEXT01.pdfFile size 545 kBChecksum SHA-512
c72561e97f640e3a3bcc39317b6775e11d4c6fcd9eb67cdc793447ab251ad83e3c485c38c9a752a7ce4c4bbf0ba9959d4d22e82594e38e6b4a1b8c759637b1b2
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Dahl, MattiasClaesson, Ingvar
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar
Total: 35 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 201 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf