Parameter optimisation for a physical model of the vocal system
Abstract This study explores optimisation techniques for refining articulatory parameters in the Pink Trombone, a simplified physical speech synthesiser, to accurately emulate male and female vocal tract characteristics in non-speech sounds. We employ black-box and grey-box approaches, leveraging a...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-07-01
|
| Series: | EURASIP Journal on Audio, Speech, and Music Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13636-025-00414-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849763928563777536 |
|---|---|
| author | Mateo Cámara José Luis Blanco Joshua D. Reiss |
| author_facet | Mateo Cámara José Luis Blanco Joshua D. Reiss |
| author_sort | Mateo Cámara |
| collection | DOAJ |
| description | Abstract This study explores optimisation techniques for refining articulatory parameters in the Pink Trombone, a simplified physical speech synthesiser, to accurately emulate male and female vocal tract characteristics in non-speech sounds. We employ black-box and grey-box approaches, leveraging a genetic optimiser and Mel-spectrogram representations to infer articulatory configurations from human recordings via direct spectral comparison. Optimisation is performed over time windows to ensure temporal coherence, introducing modifications to SOTA objective metrics. We integrate grey-box strategies, incorporating pYIN for fundamental frequency estimation and a ResNet-based neural network as a neural codebook to enhance the optimisation process. Our findings confirm the synthesiser’s ability to replicate human vocalisations, achieving superior performance over existing techniques in subjective evaluations. We refined the perceptual metric ViSQOL, providing a calibrated framework for future auditory assessments in physical speech synthesis. These contributions establish a methodology for articulatory parameter estimation, improving synthesis quality and expanding vocalisation modelling and analysis applications. |
| format | Article |
| id | doaj-art-c6c9924c3bbf4301b25a96cd1f2310fc |
| institution | DOAJ |
| issn | 1687-4722 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Audio, Speech, and Music Processing |
| spelling | doaj-art-c6c9924c3bbf4301b25a96cd1f2310fc2025-08-20T03:05:16ZengSpringerOpenEURASIP Journal on Audio, Speech, and Music Processing1687-47222025-07-012025111510.1186/s13636-025-00414-5Parameter optimisation for a physical model of the vocal systemMateo Cámara0José Luis Blanco1Joshua D. Reiss2Grupo de Aplicaciones del Procesado de Señal, Universidad Politécnica de MadridGrupo de Aplicaciones del Procesado de Señal, Universidad Politécnica de MadridCentre for Digital Music, Queen Mary University of LondonAbstract This study explores optimisation techniques for refining articulatory parameters in the Pink Trombone, a simplified physical speech synthesiser, to accurately emulate male and female vocal tract characteristics in non-speech sounds. We employ black-box and grey-box approaches, leveraging a genetic optimiser and Mel-spectrogram representations to infer articulatory configurations from human recordings via direct spectral comparison. Optimisation is performed over time windows to ensure temporal coherence, introducing modifications to SOTA objective metrics. We integrate grey-box strategies, incorporating pYIN for fundamental frequency estimation and a ResNet-based neural network as a neural codebook to enhance the optimisation process. Our findings confirm the synthesiser’s ability to replicate human vocalisations, achieving superior performance over existing techniques in subjective evaluations. We refined the perceptual metric ViSQOL, providing a calibrated framework for future auditory assessments in physical speech synthesis. These contributions establish a methodology for articulatory parameter estimation, improving synthesis quality and expanding vocalisation modelling and analysis applications.https://doi.org/10.1186/s13636-025-00414-5Analysis-by-synthesisAcoustic-to-articulatory inversionArticulatory copy synthesisPink TromboneProcedural audio |
| spellingShingle | Mateo Cámara José Luis Blanco Joshua D. Reiss Parameter optimisation for a physical model of the vocal system EURASIP Journal on Audio, Speech, and Music Processing Analysis-by-synthesis Acoustic-to-articulatory inversion Articulatory copy synthesis Pink Trombone Procedural audio |
| title | Parameter optimisation for a physical model of the vocal system |
| title_full | Parameter optimisation for a physical model of the vocal system |
| title_fullStr | Parameter optimisation for a physical model of the vocal system |
| title_full_unstemmed | Parameter optimisation for a physical model of the vocal system |
| title_short | Parameter optimisation for a physical model of the vocal system |
| title_sort | parameter optimisation for a physical model of the vocal system |
| topic | Analysis-by-synthesis Acoustic-to-articulatory inversion Articulatory copy synthesis Pink Trombone Procedural audio |
| url | https://doi.org/10.1186/s13636-025-00414-5 |
| work_keys_str_mv | AT mateocamara parameteroptimisationforaphysicalmodelofthevocalsystem AT joseluisblanco parameteroptimisationforaphysicalmodelofthevocalsystem AT joshuadreiss parameteroptimisationforaphysicalmodelofthevocalsystem |