Torbjørn Svendsen
Scholar

Torbjørn Svendsen

Google Scholar ID: A_-fr8oAAAAJ
Professor, NTNU
Speech recognitionspeech processinglanguage processingsignal processing
Citations & Impact
All-time
Citations
415
 
H-index
12
 
i10-index
13
 
Publications
20
 
Co-authors
5
list available
Contact
No contact links provided.
Publications
1 items
Resume (English only)
Academic Achievements
  • ISCA Fellow.
  • IEEE Life Senior Member.
  • Member of the Editorial Board of Speech Communication journal.
  • Reviewer for numerous international journals including IEEE Transactions (Communications; Signal Processing; Audio, Speech and Language Processing; Multimedia), EURASIP journals, etc.
  • Reviewed projects for EU Language Engineering program, Academy of Finland, and research councils of Norway, Australia, Switzerland, Netherlands, Belgium, and South Africa.
  • Opponent or committee member for 26 doctoral theses.
  • National-level appointments: grant committee member for IKTPLUSS (Research Council of Norway), chair of VERDIKT program board, member of Norwegian Language Council.
  • Advisory board member of the Norwegian Language Bank (Språkbanken).
  • Technical committee member for Eurospeech 2001 and Interspeech 2012.
Background
  • Born in 1955, currently Professor at the Department of Electronic Systems, NTNU.
  • Research interests have centered on speech signal processing since 1979; early work focused on speech compression (source coding), which was the topic of his PhD thesis.
  • Since the mid-1980s, primary focus has been on automatic speech recognition, also including spoken dialogue systems and speech synthesis.
  • Core research areas include speech analysis methods and lexical modeling (e.g., pronunciation modeling).
  • Recently exploring new paradigms for speech recognition by integrating phonetic and linguistic knowledge into a statistical framework based on detection of language-universal phonetic features.
  • Current research challenges include reliable recognition of children's speech and transcription of conversational, accented, and dialectal speech.