Convolutional non-negative matrix factorization (CNMF) can be used to discover recurring temporal (sequential) patterns in sequential vector non-negative data such as spectrograms or posteriorgrams. Drawbacks of this approach are the rigidity of the patterns and that it is intrinsically a batch method. However, in speech processing, like in many other applications, the patterns show a great deal of time warping variation and recognition should be on-line (possibly with some processing delay). Therefore, time-coded NMF (TC-NMF) is proposed as an alternative to CNMF to locate temporal patterns in time. TC-NMF is motivated by findings in neuroscience. The sequential data are first processed by a bank of filters such as leaky integrators with different time constants. The responses of these filters are modeled jointly by a constrained NMF. Algorithms for learning, decoding and locating patterns in time are proposed and verified with preliminary ASR experiments.
Weitere Kapitel dieses Buchs durch Wischen aufrufen
Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten
Sie möchten Zugang zu diesem Inhalt erhalten? Dann informieren Sie sich jetzt über unsere Produkte:
- An On-Line NMF Model for Temporal Pattern Learning: Theory with Application to Automatic Speech Recognition
Hugo Van Hamme
- Springer Berlin Heidelberg
ec4u, Neuer Inhalt/© ITandMEDIA