Sciweavers

TASLP
2010
102views more  TASLP 2010»
13 years 10 months ago
Representing Musical Sounds With an Interpolating State Model
—A computationally efficient algorithm is proposed for modeling and representing time-varying musical sounds. The aim is to encode individual sounds and not the statistical prop...
Anssi Klapuri, Tuomas Virtanen
TASLP
2008
148views more  TASLP 2008»
14 years 11 days ago
Combining Spectral Representations for Large-Vocabulary Continuous Speech Recognition
In this paper we investigate the combination of complementary acoustic feature streams in large vocabulary continuous speech recognition (LVCSR). We have explored the use of acoust...
Giulia Garau, Steve Renals