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
Knowledge-Based Word Lattice Rescoring in a Dynamic Context
2012 (English)In: INTERSPEECH 2012, 13th Annual Conference of the International Speech Communication Association, Portland, OR, USA: International Speech Communication Association, 2012, 1083-1086 p.Conference paper, (Refereed)
Abstract [en]

Recent advances in automatic speech recognition (ASR) technology continue to be based heavily on data-driven methods, meaning that the full benefits of such research are often not enjoyed in domains for which there is little training data. Moreover, tractability is often an issue with these methods when conditioning for long-distance dependencies, entailing that many higher-level knowledge sources such as situational knowledge cannot be easily utilized in classification. This paper describes an effort to circumvent this problem by using dynamic contextual knowledge to rescore ASR lattice output using a dynamic weighted constraint satisfaction function. With this method, it was possible to achieve a roughly 80% reduction in WER for ASR in the context of an air traffic control scenario.

Place, publisher, year, edition, pages
Portland, OR, USA: International Speech Communication Association, 2012. 1083-1086 p.
Keyword [en]
lattice rescoring, knowledge-based, context- sensitivity
National Category
Language Technology (Computational Linguistics)
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:kth:diva-211105OAI: oai:DiVA.org:kth-211105DiVA: diva2:1127536
Conference
INTERSPEECH 2012
Available from: 2017-07-16 Created: 2017-07-16 Last updated: 2017-07-16

Open Access in DiVA

No full text

Other links

http://www.isca-speech.org/archive/interspeech_2012/i12_1083.html
Language Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar

Total: 1 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