Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams
In this paper, we present an unsupervised learning framework to address the problem of detecting spoken keywords. Without any transcription information, a Gaussian Mixture Model is trained to label speech frames with a Gaussian posteriorgram. Given one or more spoken examples of a keyword, we use se...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2012
|
| Online Access: | http://hdl.handle.net/1721.1/73507 https://orcid.org/0000-0002-3097-360X |
| _version_ | 1826217699709026304 |
|---|---|
| author | Glass, James R. Zhang, Yaodong, Ph. D. Massachusetts Institute of Technology |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Glass, James R. Zhang, Yaodong, Ph. D. Massachusetts Institute of Technology |
| author_sort | Glass, James R. |
| collection | MIT |
| description | In this paper, we present an unsupervised learning framework to address the problem of detecting spoken keywords. Without any transcription information, a Gaussian Mixture Model is trained to label speech frames with a Gaussian posteriorgram. Given one or more spoken examples of a keyword, we use segmental dynamic time warping to compare the Gaussian posteriorgrams between keyword samples and test utterances. The keyword detection result is then obtained by ranking the distortion scores of all the test utterances. We examine the TIMIT corpus as a development set to tune the parameters in our system, and the MIT Lecture corpus for more substantial evaluation. The results demonstrate the viability and effectiveness of our unsupervised learning framework on the keyword spotting task. |
| first_indexed | 2024-09-23T17:07:46Z |
| format | Article |
| id | mit-1721.1/73507 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T17:07:46Z |
| publishDate | 2012 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/735072022-09-29T23:50:13Z Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams Glass, James R. Zhang, Yaodong, Ph. D. Massachusetts Institute of Technology Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Glass, James R. Glass, James R. Zhang, Yaodong In this paper, we present an unsupervised learning framework to address the problem of detecting spoken keywords. Without any transcription information, a Gaussian Mixture Model is trained to label speech frames with a Gaussian posteriorgram. Given one or more spoken examples of a keyword, we use segmental dynamic time warping to compare the Gaussian posteriorgrams between keyword samples and test utterances. The keyword detection result is then obtained by ranking the distortion scores of all the test utterances. We examine the TIMIT corpus as a development set to tune the parameters in our system, and the MIT Lecture corpus for more substantial evaluation. The results demonstrate the viability and effectiveness of our unsupervised learning framework on the keyword spotting task. 2012-10-01T16:23:45Z 2012-10-01T16:23:45Z 2010-01 2009-12 Article http://purl.org/eprint/type/ConferencePaper 978-1-4244-5478-5 978-1-4244-5479-2 http://hdl.handle.net/1721.1/73507 Zhang, Yaodong, and James R. Glass. “Unsupervised Spoken Keyword Spotting via Segmental DTW on Gaussian Posteriorgrams.” Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU 2009) IEEE, 2009. 398–403. (c) 2009 IEEE https://orcid.org/0000-0002-3097-360X en_US http://dx.doi.org/10.1109/ASRU.2009.5372931 IEEE Workshop on Automatic Speech Recognition & Understanding, 2009 (ASRU 2009) Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Institute of Electrical and Electronics Engineers (IEEE) IEEE |
| spellingShingle | Glass, James R. Zhang, Yaodong, Ph. D. Massachusetts Institute of Technology Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams |
| title | Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams |
| title_full | Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams |
| title_fullStr | Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams |
| title_full_unstemmed | Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams |
| title_short | Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams |
| title_sort | unsupervised spoken keyword spotting via segmental dtw on gaussian posteriorgrams |
| url | http://hdl.handle.net/1721.1/73507 https://orcid.org/0000-0002-3097-360X |
| work_keys_str_mv | AT glassjamesr unsupervisedspokenkeywordspottingviasegmentaldtwongaussianposteriorgrams AT zhangyaodongphdmassachusettsinstituteoftechnology unsupervisedspokenkeywordspottingviasegmentaldtwongaussianposteriorgrams |