Classification of Spontaneous and Scripted Speech for Multilingual Audio
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910747745845248 |
|---|---|
| author | Elisha, Shahar McDowell, Andrew Beguerisse-Díaz, Mariano Benetos, Emmanouil |
| author_facet | Elisha, Shahar McDowell, Andrew Beguerisse-Díaz, Mariano Benetos, Emmanouil |
| contents | Distinguishing scripted from spontaneous speech is an essential tool for better understanding how speech styles influence speech processing research. It can also improve recommendation systems and discovery experiences for media users through better segmentation of large recorded speech catalogues. This paper addresses the challenge of building a classifier that generalises well across different formats and languages. We systematically evaluate models ranging from traditional, handcrafted acoustic and prosodic features to advanced audio transformers, utilising a large, multilingual proprietary podcast dataset for training and validation. We break down the performance of each model across 11 language groups to evaluate cross-lingual biases. Our experimental analysis extends to publicly available datasets to assess the models' generalisability to non-podcast domains. Our results indicate that transformer-based models consistently outperform traditional feature-based techniques, achieving state-of-the-art performance in distinguishing between scripted and spontaneous speech across various languages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_11896 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Classification of Spontaneous and Scripted Speech for Multilingual Audio Elisha, Shahar McDowell, Andrew Beguerisse-Díaz, Mariano Benetos, Emmanouil Computation and Language Sound Audio and Speech Processing Distinguishing scripted from spontaneous speech is an essential tool for better understanding how speech styles influence speech processing research. It can also improve recommendation systems and discovery experiences for media users through better segmentation of large recorded speech catalogues. This paper addresses the challenge of building a classifier that generalises well across different formats and languages. We systematically evaluate models ranging from traditional, handcrafted acoustic and prosodic features to advanced audio transformers, utilising a large, multilingual proprietary podcast dataset for training and validation. We break down the performance of each model across 11 language groups to evaluate cross-lingual biases. Our experimental analysis extends to publicly available datasets to assess the models' generalisability to non-podcast domains. Our results indicate that transformer-based models consistently outperform traditional feature-based techniques, achieving state-of-the-art performance in distinguishing between scripted and spontaneous speech across various languages. |
| title | Classification of Spontaneous and Scripted Speech for Multilingual Audio |
| topic | Computation and Language Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2412.11896 |