Robust In-Car Speech Recognition Based on Nonlinear Multiple Regressions
<p/> <p>We address issues for improving handsfree speech recognition performance in different car environments using a single distant microphone. In this paper, we propose a nonlinear multiple-regression-based enhancement method for in-car speech recognition. In order to develop a data-d...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2007-01-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Online Access: | http://asp.eurasipjournals.com/content/2007/016921 |
| _version_ | 1818359193876299776 |
|---|---|
| author | Itakura Fumitada Li Weifeng Takeda Kazuya |
| author_facet | Itakura Fumitada Li Weifeng Takeda Kazuya |
| author_sort | Itakura Fumitada |
| collection | DOAJ |
| description | <p/> <p>We address issues for improving handsfree speech recognition performance in different car environments using a single distant microphone. In this paper, we propose a nonlinear multiple-regression-based enhancement method for in-car speech recognition. In order to develop a data-driven in-car recognition system, we develop an effective algorithm for adapting the regression parameters to different driving conditions. We also devise the model compensation scheme by synthesizing the training data using the optimal regression parameters and by selecting the optimal HMM for the test speech. Based on isolated word recognition experiments conducted in 15 real car environments, the proposed adaptive regression approach shows an advantage in average relative word error rate (WER) reductions of 52.5 <inline-formula><graphic file="1687-6180-2007-016921-i1.gif"/></inline-formula> and 14.8 <inline-formula><graphic file="1687-6180-2007-016921-i2.gif"/></inline-formula>, compared to original noisy speech and ETSI advanced front end, respectively.</p> |
| first_indexed | 2024-12-13T20:41:01Z |
| format | Article |
| id | doaj.art-495cccaba263456593432bcf5566031b |
| institution | Directory Open Access Journal |
| issn | 1687-6172 1687-6180 |
| language | English |
| last_indexed | 2024-12-13T20:41:01Z |
| publishDate | 2007-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj.art-495cccaba263456593432bcf5566031b2022-12-21T23:32:09ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61721687-61802007-01-0120071016921Robust In-Car Speech Recognition Based on Nonlinear Multiple RegressionsItakura FumitadaLi WeifengTakeda Kazuya<p/> <p>We address issues for improving handsfree speech recognition performance in different car environments using a single distant microphone. In this paper, we propose a nonlinear multiple-regression-based enhancement method for in-car speech recognition. In order to develop a data-driven in-car recognition system, we develop an effective algorithm for adapting the regression parameters to different driving conditions. We also devise the model compensation scheme by synthesizing the training data using the optimal regression parameters and by selecting the optimal HMM for the test speech. Based on isolated word recognition experiments conducted in 15 real car environments, the proposed adaptive regression approach shows an advantage in average relative word error rate (WER) reductions of 52.5 <inline-formula><graphic file="1687-6180-2007-016921-i1.gif"/></inline-formula> and 14.8 <inline-formula><graphic file="1687-6180-2007-016921-i2.gif"/></inline-formula>, compared to original noisy speech and ETSI advanced front end, respectively.</p>http://asp.eurasipjournals.com/content/2007/016921 |
| spellingShingle | Itakura Fumitada Li Weifeng Takeda Kazuya Robust In-Car Speech Recognition Based on Nonlinear Multiple Regressions EURASIP Journal on Advances in Signal Processing |
| title | Robust In-Car Speech Recognition Based on Nonlinear Multiple Regressions |
| title_full | Robust In-Car Speech Recognition Based on Nonlinear Multiple Regressions |
| title_fullStr | Robust In-Car Speech Recognition Based on Nonlinear Multiple Regressions |
| title_full_unstemmed | Robust In-Car Speech Recognition Based on Nonlinear Multiple Regressions |
| title_short | Robust In-Car Speech Recognition Based on Nonlinear Multiple Regressions |
| title_sort | robust in car speech recognition based on nonlinear multiple regressions |
| url | http://asp.eurasipjournals.com/content/2007/016921 |
| work_keys_str_mv | AT itakurafumitada robustincarspeechrecognitionbasedonnonlinearmultipleregressions AT liweifeng robustincarspeechrecognitionbasedonnonlinearmultipleregressions AT takedakazuya robustincarspeechrecognitionbasedonnonlinearmultipleregressions |