Sciweavers

128 search results - page 17 / 26
» speech 2002
Sort
View
CSL
2002
Springer
13 years 10 months ago
Lightly supervised and unsupervised acoustic model training
The last decade has witnessed substantial progress in speech recognition technology, with todays state-of-the-art systems being able to transcribe unrestricted broadcast news audi...
Lori Lamel, Jean-Luc Gauvain, Gilles Adda
TASLP
2002
84views more  TASLP 2002»
13 years 10 months ago
Maximum likelihood multiple subspace projections for hidden Markov models
The first stage in many pattern recognition tasks is to generate a good set of features from the observed data. Usually, only a single feature space is used. However, in some compl...
Mark J. F. Gales
DSS
2002
231views more  DSS 2002»
13 years 10 months ago
Computational aspects of the FLBC framework
Recent research has sought to develop formal languages for business communication as more expressive, flexible and powerful alternatives to current electronic data interchange (ED...
Aspassia Daskalopulu, Marek J. Sergot
CHI
2002
ACM
14 years 11 months ago
Automated message prioritization: making voicemail retrieval more efficient
Navigating through new voicemail messages to find messages of interest is a time-consuming task, particularly for high-volume users. When checking messages under a time constraint...
Meridith Ringel, Julia Hirschberg
INTERSPEECH
2010
13 years 5 months ago
What else is new than the hamming window? robust MFCCs for speaker recognition via multitapering
Usually the mel-frequency cepstral coefficients (MFCCs) are derived via Hamming windowed DFT spectrum. In this paper, we advocate to use a so-called multitaper method instead. Mul...
Tomi Kinnunen, Rahim Saeidi, Johan Sandberg, Maria...