121 search results - page 17 / 25 » Corrected tandem features for acoustic model training |
EMNLP
2008
13 years 9 months ago
2008
We present a discriminative method for learning selectional preferences from unlabeled text. Positive examples are taken from observed predicate-argument pairs, while negatives ar...
ISMIR
2004
Springer
14 years 1 months ago
2004
Springer
In this paper is described a data-driven algorithm for the functionally correct spelling of MIDI pitch values in terms of Western musical notation. Input is in the form of MIDI fi...
IKE
2008
13 years 9 months ago
2008
One major source of performance decline in speaker recognition system is channel mismatch between training and testing. This paper focuses on improving channel robustness of speake...
EJASMP
2010
13 years 2 months ago
2010
Computer Assisted Language Learning (CALL) applications for improving the oral skills of low-proficient learners have to cope with nonnative speech that is particularly challengin...
SDM
2012
SIAM
11 years 10 months ago
2012
SIAM
To date, many active learning techniques have been developed for acquiring labels when training data is limited. However, an important aspect of the problem has often been neglect...