Classification of Phonation Modes in Classical Singing Using Modulation Power Spectral Features
In singing, the perceptual term “voice quality” is used to describe expressed emotions and singing styles. In voice physiology research, specific voice qualities are discussed using the term phonation modes and are directly related to the voicing produced by the vocal folds. Th...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10078264/ |
| _version_ | 1797850995271663616 |
|---|---|
| author | Manuel Brandner Paul Armin Bereuter Sudarsana Reddy Kadiri Alois Sontacchi |
| author_facet | Manuel Brandner Paul Armin Bereuter Sudarsana Reddy Kadiri Alois Sontacchi |
| author_sort | Manuel Brandner |
| collection | DOAJ |
| description | In singing, the perceptual term “voice quality” is used to describe expressed emotions and singing styles. In voice physiology research, specific voice qualities are discussed using the term phonation modes and are directly related to the voicing produced by the vocal folds. The control and awareness of phonation modes is vital for professional singers to maintain a healthy voice. Most studies on phonation modes have investigated speech and have used glottal inverse filtering to compute features from an estimated excitation signal. The performance of this method is reported to decrease at high pitches, which limits its usability for the singing voice. To overcome this, this study proposes to use features derived from the modulation power spectrum for phonation mode classification in the singing voice. The exploration of the modulation power spectrum is motivated by the fact that, in singing, temporal modulations (known as vocal vibrato) and spectral modulations hold information of the vocal fold tension. Since there exists no large publicly available dataset of phonation modes in singing, we created a new dataset consisting of six female and four male classical singers, who sang five vowels at different pitches in three phonation modes (breathy, modal, and pressed). Experimental results with a support vector machine classifier reveal that the proposed features show better classification performance compared to state-of-the-art reference features. The performance for the current dataset is at least 10% higher compared to the performance of the reference features (such as glottal source features and MFCCs) in the case of target labels and around 6% higher in the case of perceptually assessed labels. |
| first_indexed | 2024-04-09T19:10:33Z |
| format | Article |
| id | doaj.art-bf73d8e9de724c2eb3e583e3066af48d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-09T19:10:33Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-bf73d8e9de724c2eb3e583e3066af48d2023-04-06T23:00:27ZengIEEEIEEE Access2169-35362023-01-0111291492916110.1109/ACCESS.2023.326018710078264Classification of Phonation Modes in Classical Singing Using Modulation Power Spectral FeaturesManuel Brandner0https://orcid.org/0000-0002-3217-3497Paul Armin Bereuter1https://orcid.org/0009-0003-9530-337XSudarsana Reddy Kadiri2https://orcid.org/0000-0001-5806-3053Alois Sontacchi3https://orcid.org/0009-0008-9205-209XInstitute of Electronic Music and Acoustics, University of Music and Performing Arts Graz, Graz, AustriaInstitute of Electronic Music and Acoustics, University of Music and Performing Arts Graz, Graz, AustriaDepartment of Information and Communications Engineering, Aalto University, Espoo, FinlandInstitute of Electronic Music and Acoustics, University of Music and Performing Arts Graz, Graz, AustriaIn singing, the perceptual term “voice quality” is used to describe expressed emotions and singing styles. In voice physiology research, specific voice qualities are discussed using the term phonation modes and are directly related to the voicing produced by the vocal folds. The control and awareness of phonation modes is vital for professional singers to maintain a healthy voice. Most studies on phonation modes have investigated speech and have used glottal inverse filtering to compute features from an estimated excitation signal. The performance of this method is reported to decrease at high pitches, which limits its usability for the singing voice. To overcome this, this study proposes to use features derived from the modulation power spectrum for phonation mode classification in the singing voice. The exploration of the modulation power spectrum is motivated by the fact that, in singing, temporal modulations (known as vocal vibrato) and spectral modulations hold information of the vocal fold tension. Since there exists no large publicly available dataset of phonation modes in singing, we created a new dataset consisting of six female and four male classical singers, who sang five vowels at different pitches in three phonation modes (breathy, modal, and pressed). Experimental results with a support vector machine classifier reveal that the proposed features show better classification performance compared to state-of-the-art reference features. The performance for the current dataset is at least 10% higher compared to the performance of the reference features (such as glottal source features and MFCCs) in the case of target labels and around 6% higher in the case of perceptually assessed labels.https://ieeexplore.ieee.org/document/10078264/Modulation power spectrumphonation modessinging voice analysisvoice qualities |
| spellingShingle | Manuel Brandner Paul Armin Bereuter Sudarsana Reddy Kadiri Alois Sontacchi Classification of Phonation Modes in Classical Singing Using Modulation Power Spectral Features IEEE Access Modulation power spectrum phonation modes singing voice analysis voice qualities |
| title | Classification of Phonation Modes in Classical Singing Using Modulation Power Spectral Features |
| title_full | Classification of Phonation Modes in Classical Singing Using Modulation Power Spectral Features |
| title_fullStr | Classification of Phonation Modes in Classical Singing Using Modulation Power Spectral Features |
| title_full_unstemmed | Classification of Phonation Modes in Classical Singing Using Modulation Power Spectral Features |
| title_short | Classification of Phonation Modes in Classical Singing Using Modulation Power Spectral Features |
| title_sort | classification of phonation modes in classical singing using modulation power spectral features |
| topic | Modulation power spectrum phonation modes singing voice analysis voice qualities |
| url | https://ieeexplore.ieee.org/document/10078264/ |
| work_keys_str_mv | AT manuelbrandner classificationofphonationmodesinclassicalsingingusingmodulationpowerspectralfeatures AT paularminbereuter classificationofphonationmodesinclassicalsingingusingmodulationpowerspectralfeatures AT sudarsanareddykadiri classificationofphonationmodesinclassicalsingingusingmodulationpowerspectralfeatures AT aloissontacchi classificationofphonationmodesinclassicalsingingusingmodulationpowerspectralfeatures |