Sparse modeling of posterior exemplars for keyword detection
| Autor: | Dhananjay Ram, Afsaneh Asaei, Pranay Dighe, Hervé Bourlard |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
Artificial neural network
business.industry Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing) Pattern recognition Sparse approximation Machine learning computer.software_genre ComputingMethodologies_PATTERNRECOGNITION Computer Science::Computer Vision and Pattern Recognition Artificial intelligence business Hidden Markov model computer Subspace topology |
| Zdroj: | INTERSPEECH |
| DOI: | 10.21437/interspeech.2015-732 |
| Popis: | Sparse representation has been shown to be a powerful modeling framework for classification and detection tasks. In this paper, we propose a new keyword detection algorithm based on sparse representation of the posterior exemplars. The posterior exemplars are phone conditional probabilities obtained from a deep neural network. This method relies on the concept that a keyword exemplar lies in a low-dimensional subspace which can be represented as a sparse linear combination of the training exemplars. The training exemplars are used to learn a dictionary for sparse representation of the keywords and background classes. Given this dictionary, the sparse representation of a test exemplar is used to detect the keywords. The experimental results demonstrate the potential of the proposed sparse modeling approach and it compares favorably with the state-of-the-art HMM-based framework on Numbers’95 database. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|