Sciweavers

246 search results - page 24 / 50
» Task-Driven Dictionary Learning
Sort
View
ICASSP
2011
IEEE
14 years 3 months ago
A non-negative approach to semi-supervised separation of speech from noise with the use of temporal dynamics
We present a semi-supervised source separation methodology to denoise speech by modeling speech as one source and noise as the other source. We model speech using the recently pro...
Gautham J. Mysore, Paris Smaragdis
CAIP
2009
Springer
211views Image Analysis» more  CAIP 2009»
15 years 6 months ago
Contextual-Guided Bag-of-Visual-Words Model for Multi-class Object Categorization
Abstract. Bag-of-words model (BOW) is inspired by the text classification problem, where a document is represented by an unsorted set of contained words. Analogously, in the objec...
Mehdi Mirza-Mohammadi, Sergio Escalera, Petia Rade...
ICA
2010
Springer
15 years 24 days ago
Non-negative Hidden Markov Modeling of Audio with Application to Source Separation
Abstract. In recent years, there has been a great deal of work in modeling audio using non-negative matrix factorization and its probabilistic counterparts as they yield rich model...
Gautham J. Mysore, Paris Smaragdis, Bhiksha Raj
LREC
2010
148views Education» more  LREC 2010»
15 years 1 months ago
Tag Dictionaries Accelerate Manual Annotation
Expert human input can contribute in various ways to facilitate automatic annotation of natural language text. For example, a part-of-speech tagger can be trained on labeled input...
Marc Carmen, Paul Felt, Robbie Haertel, Deryle Lon...
NIPS
2008
15 years 1 months ago
Unsupervised Learning of Visual Sense Models for Polysemous Words
Polysemy is a problem for methods that exploit image search engines to build object category models. Existing unsupervised approaches do not take word sense into consideration. We...
Kate Saenko, Trevor Darrell