Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2408.04363 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914905747095552 |
|---|---|
| author | Tandazo, Angelo Ortiz Schatz, Thomas Hueber, Thomas Dupoux, Emmanuel |
| author_facet | Tandazo, Angelo Ortiz Schatz, Thomas Hueber, Thomas Dupoux, Emmanuel |
| contents | As a first step towards a complete computational model of speech learning involving perception-production loops, we investigate the forward mapping between pseudo-motor commands and articulatory trajectories. Two phonological feature sets, based respectively on generative and articulatory phonology, are used to encode a phonetic target sequence. Different interpolation techniques are compared to generate smooth trajectories in these feature spaces, with a potential optimisation of the target value and timing to capture co-articulation effects. We report the Pearson correlation between a linear projection of the generated trajectories and articulatory data derived from a multi-speaker dataset of electromagnetic articulography (EMA) recordings. A correlation of 0.67 is obtained with an extended feature set based on generative phonology and a linear interpolation technique. We discuss the implications of our results for our understanding of the dynamics of biological motion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_04363 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Simulating Articulatory Trajectories with Phonological Feature Interpolation Tandazo, Angelo Ortiz Schatz, Thomas Hueber, Thomas Dupoux, Emmanuel Audio and Speech Processing Computation and Language As a first step towards a complete computational model of speech learning involving perception-production loops, we investigate the forward mapping between pseudo-motor commands and articulatory trajectories. Two phonological feature sets, based respectively on generative and articulatory phonology, are used to encode a phonetic target sequence. Different interpolation techniques are compared to generate smooth trajectories in these feature spaces, with a potential optimisation of the target value and timing to capture co-articulation effects. We report the Pearson correlation between a linear projection of the generated trajectories and articulatory data derived from a multi-speaker dataset of electromagnetic articulography (EMA) recordings. A correlation of 0.67 is obtained with an extended feature set based on generative phonology and a linear interpolation technique. We discuss the implications of our results for our understanding of the dynamics of biological motion. |
| title | Simulating Articulatory Trajectories with Phonological Feature Interpolation |
| topic | Audio and Speech Processing Computation and Language |
| url | https://arxiv.org/abs/2408.04363 |