@inproceedings{2fce0c343484461da2d6a2c852675a77,
title = "Fast similarity search on a large speech data set with neighborhood graph indexing",
abstract = "This paper presents a novel graph-based approach for solving a problem of fast finding a speech model acoustically similar to a query model from a large set of speech models. Each speech model in the set is represented by a Gaussian mixture model and dissimilarity from a GMM to another is measured with a Kullback-Leibler divergence (KLD). Conventional pruning techniques based on the triangle inequality for fast similarity search are not available because the model space with a KLD is not a metric space. We propose a search method that is characterized by an index of a degree-reduced nearest neighbor (DRNN) graph. The search method can efficiently find the most similar (closest) GMM to a query, exploring the DRNN graph with a best-first manner. Experimental evaluations on utterance GMM search tasks reveal a significantly low computational cost of the proposed method.",
keywords = "Gaussian mixture model, Graph index, Kullback-Leibler divergence, Similarity search, Utterance retrieval",
author = "Kazuo Aoyama and Shinji Watanabe and Hiroshi Sawada and Yasuhiro Minami and Naonori Ueda and Kazumi Saito",
year = "2010",
doi = "10.1109/ICASSP.2010.5494950",
language = "English",
isbn = "9781424442966",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "5358--5361",
booktitle = "2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings",
note = "2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 ; Conference date: 14-03-2010 Through 19-03-2010",
}