Sparse hidden Markov models for purer clusters
- Resource Type
- Conference
- Authors
- Bharadwaj, Sujeeth; Hasegawa-Johnson, Mark; Ajmera, Jitendra; Deshmukh, Om; Verma, Ashish
- Source
- 2013 IEEE International Conference on Acoustics, Speech and Signal Processing Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on. :3098-3102 May, 2013
- Subject
- Signal Processing and Analysis
Hidden Markov models
Clustering algorithms
Entropy
Vectors
Speech
Measurement
Estimation
hidden Markov model
sequence clustering
sparsity
cluster purity
Renyi entropy
- Language
- ISSN
- 1520-6149
2379-190X
The hidden Markov model (HMM) is widely popular as the de facto tool for representing temporal data; in this paper, we add to its utility in the sequence clustering domain - we describe a novel approach that allows us to directly control purity in HMM-based clustering algorithms. We show that encouraging sparsity in the observation probabilities increases cluster purity and derive an algorithm based on l p regularization; as a corollary, we also provide a different and useful interpretation of the value of p in Renyi p-entropy. We test our method on the problem of clustering non-speech audio events from the BBC sound effects corpus. Experimental results confirm that our approach does learn purer clusters, with (unweighted) average purity as high as 0.88 - a considerable improvement over both the baseline HMM (0.72) and k-means clustering (0.69).