Pitch- and Formant-Based Order Adaptation of the Fractional Fourier Transform and Its Application to Speech Recognition
<p/> <p>Fractional Fourier transform (FrFT) has been proposed to improve the time-frequency resolution in signal analysis and processing. However, selecting the FrFT transform order for the proper analysis of multicomponent signals like speech is still debated. In this work, we investiga...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2009-01-01
|
| Series: | EURASIP Journal on Audio, Speech, and Music Processing |
| Online Access: | http://asmp.eurasipjournals.com/content/2009/304579 |
| _version_ | 1818765869632716800 |
|---|---|
| author | Yin Hui Nadeu Climent Hohmann Volker |
| author_facet | Yin Hui Nadeu Climent Hohmann Volker |
| author_sort | Yin Hui |
| collection | DOAJ |
| description | <p/> <p>Fractional Fourier transform (FrFT) has been proposed to improve the time-frequency resolution in signal analysis and processing. However, selecting the FrFT transform order for the proper analysis of multicomponent signals like speech is still debated. In this work, we investigated several order adaptation methods. Firstly, FFT- and FrFT- based spectrograms of an artificially-generated vowel are compared to demonstrate the methods. Secondly, an acoustic feature set combining MFCC and FrFT is proposed, and the transform orders for the FrFT are adaptively set according to various methods based on pitch and formants. A tonal vowel discrimination test is designed to compare the performance of these methods using the feature set. The results show that the FrFT-MFCC yields a better discriminability of tones and also of vowels, especially by using multitransform-order methods. Thirdly, speech recognition experiments were conducted on the clean intervocalic English consonants provided by the Consonant Challenge. Experimental results show that the proposed features with different order adaptation methods can obtain slightly higher recognition rates compared to the reference MFCC-based recognizer.</p> |
| first_indexed | 2024-12-18T08:24:57Z |
| format | Article |
| id | doaj.art-2190009719904f27b85ef902405c3753 |
| institution | Directory Open Access Journal |
| issn | 1687-4714 1687-4722 |
| language | English |
| last_indexed | 2024-12-18T08:24:57Z |
| publishDate | 2009-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Audio, Speech, and Music Processing |
| spelling | doaj.art-2190009719904f27b85ef902405c37532022-12-21T21:14:38ZengSpringerOpenEURASIP Journal on Audio, Speech, and Music Processing1687-47141687-47222009-01-0120091304579Pitch- and Formant-Based Order Adaptation of the Fractional Fourier Transform and Its Application to Speech RecognitionYin HuiNadeu ClimentHohmann Volker<p/> <p>Fractional Fourier transform (FrFT) has been proposed to improve the time-frequency resolution in signal analysis and processing. However, selecting the FrFT transform order for the proper analysis of multicomponent signals like speech is still debated. In this work, we investigated several order adaptation methods. Firstly, FFT- and FrFT- based spectrograms of an artificially-generated vowel are compared to demonstrate the methods. Secondly, an acoustic feature set combining MFCC and FrFT is proposed, and the transform orders for the FrFT are adaptively set according to various methods based on pitch and formants. A tonal vowel discrimination test is designed to compare the performance of these methods using the feature set. The results show that the FrFT-MFCC yields a better discriminability of tones and also of vowels, especially by using multitransform-order methods. Thirdly, speech recognition experiments were conducted on the clean intervocalic English consonants provided by the Consonant Challenge. Experimental results show that the proposed features with different order adaptation methods can obtain slightly higher recognition rates compared to the reference MFCC-based recognizer.</p>http://asmp.eurasipjournals.com/content/2009/304579 |
| spellingShingle | Yin Hui Nadeu Climent Hohmann Volker Pitch- and Formant-Based Order Adaptation of the Fractional Fourier Transform and Its Application to Speech Recognition EURASIP Journal on Audio, Speech, and Music Processing |
| title | Pitch- and Formant-Based Order Adaptation of the Fractional Fourier Transform and Its Application to Speech Recognition |
| title_full | Pitch- and Formant-Based Order Adaptation of the Fractional Fourier Transform and Its Application to Speech Recognition |
| title_fullStr | Pitch- and Formant-Based Order Adaptation of the Fractional Fourier Transform and Its Application to Speech Recognition |
| title_full_unstemmed | Pitch- and Formant-Based Order Adaptation of the Fractional Fourier Transform and Its Application to Speech Recognition |
| title_short | Pitch- and Formant-Based Order Adaptation of the Fractional Fourier Transform and Its Application to Speech Recognition |
| title_sort | pitch and formant based order adaptation of the fractional fourier transform and its application to speech recognition |
| url | http://asmp.eurasipjournals.com/content/2009/304579 |
| work_keys_str_mv | AT yinhui pitchandformantbasedorderadaptationofthefractionalfouriertransformanditsapplicationtospeechrecognition AT nadeucliment pitchandformantbasedorderadaptationofthefractionalfouriertransformanditsapplicationtospeechrecognition AT hohmannvolker pitchandformantbasedorderadaptationofthefractionalfouriertransformanditsapplicationtospeechrecognition |