Histogram Equalization to Model Adaptation for Robust Speech Recognition
We propose a new model adaptation method based on the histogram equalization technique for providing robustness in noisy environments. The trained acoustic mean models of a speech recognizer are adapted into environmentally matched conditions by using the histogram equalization algorithm on a single...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2010-01-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Online Access: | http://dx.doi.org/10.1155/2010/628018 |
| _version_ | 1811245660431712256 |
|---|---|
| author | Hoirin Kim Youngjoo Suh |
| author_facet | Hoirin Kim Youngjoo Suh |
| author_sort | Hoirin Kim |
| collection | DOAJ |
| description | We propose a new model adaptation method based on the histogram equalization technique for providing robustness in noisy environments. The trained acoustic mean models of a speech recognizer are adapted into environmentally matched conditions by using the histogram equalization algorithm on a single utterance basis. For more robust speech recognition in the heavily noisy conditions, trained acoustic covariance models are efficiently adapted by the signal-to-noise ratio-dependent linear interpolation between trained covariance models and utterance-level sample covariance models. Speech recognition experiments on both the digit-based Aurora2 task and the large vocabulary-based task showed that the proposed model adaptation approach provides significant performance improvements compared to the baseline speech recognizer trained on the clean speech data. |
| first_indexed | 2024-04-12T14:42:41Z |
| format | Article |
| id | doaj.art-99381377e4ce4e02af071ea58cf2d204 |
| institution | Directory Open Access Journal |
| issn | 1687-6172 1687-6180 |
| language | English |
| last_indexed | 2024-04-12T14:42:41Z |
| publishDate | 2010-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj.art-99381377e4ce4e02af071ea58cf2d2042022-12-22T03:28:46ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61721687-61802010-01-01201010.1155/2010/628018Histogram Equalization to Model Adaptation for Robust Speech RecognitionHoirin KimYoungjoo SuhWe propose a new model adaptation method based on the histogram equalization technique for providing robustness in noisy environments. The trained acoustic mean models of a speech recognizer are adapted into environmentally matched conditions by using the histogram equalization algorithm on a single utterance basis. For more robust speech recognition in the heavily noisy conditions, trained acoustic covariance models are efficiently adapted by the signal-to-noise ratio-dependent linear interpolation between trained covariance models and utterance-level sample covariance models. Speech recognition experiments on both the digit-based Aurora2 task and the large vocabulary-based task showed that the proposed model adaptation approach provides significant performance improvements compared to the baseline speech recognizer trained on the clean speech data.http://dx.doi.org/10.1155/2010/628018 |
| spellingShingle | Hoirin Kim Youngjoo Suh Histogram Equalization to Model Adaptation for Robust Speech Recognition EURASIP Journal on Advances in Signal Processing |
| title | Histogram Equalization to Model Adaptation for Robust Speech Recognition |
| title_full | Histogram Equalization to Model Adaptation for Robust Speech Recognition |
| title_fullStr | Histogram Equalization to Model Adaptation for Robust Speech Recognition |
| title_full_unstemmed | Histogram Equalization to Model Adaptation for Robust Speech Recognition |
| title_short | Histogram Equalization to Model Adaptation for Robust Speech Recognition |
| title_sort | histogram equalization to model adaptation for robust speech recognition |
| url | http://dx.doi.org/10.1155/2010/628018 |
| work_keys_str_mv | AT hoirinkim histogramequalizationtomodeladaptationforrobustspeechrecognition AT youngjoosuh histogramequalizationtomodeladaptationforrobustspeechrecognition |