aLDA-based selection of acoustic training data significantly outperforms random selection, posterior-based selection, and using all available data for ASR on meeting recordings.
Factor analysis for audio-based video genre classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Latent Dirichlet Allocation Based Acoustic Data Selection for Automatic Speech Recognition
aLDA-based selection of acoustic training data significantly outperforms random selection, posterior-based selection, and using all available data for ASR on meeting recordings.