The goal of this work is to build speech-based search engines for low resource languages. There are several challenges in building such engines — this project focuses on two: mitigating the verbosity of spoken queries, and utilizing methods of speech processing that do not require a language model.
We find that spoken queries tend to be much longer than their written counterparts. This is both because of the nature of speech — think of the last time you asked something of a customer service agent — and because of the nature of our users. Many of our subjects have not been trained by Google to use one or two-word queries. Our goal is thus to develop systems which can distill a user's information need as the query proceeds.
Zero resource term detection (ZRT) is a method of speech processing that does not require a language model. As such, we can build search engines from a much broader set of audio copora than could be accomplished relying on traditional speech recognizers. Our work addresses the challenges in building such engines by developing techniques for indexing the data, and tools for visualizing it.
Oard, Douglas; Sankepally, Rashmi; Jansen,Aren; and Harman, Craig (August 2015), "A Test Collection for Spoken Gujarati Queries,". International ACM SIGIR Conference on Research and Development in Information Retrieval.
Douglas Oard, Jiaul Paik, Rashmi Sankepally, and Aren Jansen, "Using Zero-Resource Spoken Term Discovery for Ranked Retrieval," Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies, May 2015
Hardik Joshi. Forum for Information Retrieval Evaluation, "Document Similarity Amid Automatically Detected Terms,", December 2014.
Douglas Oard, Jiaul Paik, Rashmi Sankepally, and Aren Jansen"The FIRE 2013 Question Answering for the Spoken Web Task,". Forum for Information Retrieval Evaluation, December 2013
Douglas Oard, Nitendra Rajput, and Marion Zalk, "Simulating Early-Termination Search for Verbose Spoken Queries,". Conference on Empirical Methods in Natural Language Processing, October 2013.
