An optimal Bhattacharyya centroid algorithm for Gaussian clustering with applications in automatic speech recognition
By Luca Rigazio, Brice Tsakam, Jean-Claude Junqua. 2000
17 citations recorded by the source corpus.
The problem of clustering Gaussian distributions can be effectively solved by standard vector quantization algorithms where the metric is defined by the Bhattacharyya distance. This paper presents a novel algorithm for computing the optimal centroid for a cluster of Gaussian distributions according to the Bhattacharyya metric. We show that this centroid maximizes an upper bound on the probability of representing the population modeled by the distributions associated with the cluster. The proposed method is evaluated in clustering distributions of hidden Markov model speech recognizers to reduce the overall memory consumption and runtime complexity of the decoding. Experimental results show that, depending on the task, the number of distributions can be reduced by a factor of 2 to 6 with an increase in recognition accuracy. When compared to a maximum likelihood centroid, the Bhattacharyya centroid provides a 13% error rate reduction in a 2k word recognition task.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
Citations in the corpus
- Deep Clustered Convolutional Kernels (2015, methodology): “Our approach takes inspiration by previous work in the area of Gaussian kernel HMMs (Sankar, 1998; Rigazio et al., 2000; Bocchieri & Mak, 2001; Lee et al., 2001), and is philosophically based on Occam’s razor principle whereby a smaller model with similar performance on a given data-set is likely…”