Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | MLSP-P4.8 |
| Session: | Machine Learning Applications |
| Time: | Thursday, May 20, 09:30 - 11:30 |
| Presentation: |
Poster |
| Topic: |
Machine Learning for Signal Processing: Blind Signal Separation and Independent Component Analysis |
| Title: |
ICA-BASED HIERARCHICAL TEXT CLASSIFICATION FOR MULTI-DOMAIN TEXT-TO-SPEECH SYNTHESIS |
| Authors: |
Xavier Sevillano; Enginyeria i Arquitectura La Salle, Universitat Ramon Llull | | |
| | Francesc Alías; Enginyeria i Arquitectura La Salle, Universitat Ramon Llull | | |
| | Joan Claudi Socoró; Enginyeria i Arquitectura La Salle, Universitat Ramon Llull | | |
| Abstract: |
In the framework of multi-domain Text-to-Speech synthesis it is essential to (i) design a hierarchically structured database for allowing several domains in the same speech corpus and (ii) include a text classification module that, at run time, assigns the input sentences to a domain or set of domains from the database. In this paper, we present a hierarchical text classifier based on Independent Component Analysis (ICA), which is capable of (i) organizing the contents of the corpus in a hierarchical manner and (ii) classifying the texts to be synthesized according to the learned structure. The document organization and classification performance of our ICA-based hierarchical classifier are evaluated in several encouraging experiments conducted on a journalistic-style text corpus for speech synthesis in Catalan. |
| |
| Back | |