O2 - Oral Session: Audio and Speech Segmentation


Date: Wednesday, 21 November

Hour: 15:00 - 16:40

Location: Building C, Sala de Grados.

Chairperson: Eduardo Lleida Solano.


O2-1: On the Influence of Automatic Segmentation and Clustering in Automatic Speech Recognition, Paula Lopez-Otero,  Laura Docio-Fernandez, Carmen Garcia-Mateo, and Antonio Cardenal-Lopez

O2-2: Preliminary Results of Alignment of Text and Audio in News and Song, Darwin Patricio Córdova Lucero and Doroteo Torre Toledano

O2-3: Aligning very long speech signals to bilingual transcriptions of parliamentary sessions, German Bordel, Mikel Penagarikano, Luis Javier Rodríguez Fuentes, and María Amparo Varona Fernández

O2-4: Factor Analysis Segmentation and Classification in Broadcast News Domain, Diego Castán, Alfonso Ortega Giménez, and Eduardo Lleida Solano

O2-5: Prosodic and Phonetic Features for Speaking Styles Classification and Detection, Arlindo Veiga, Dirce Celorico, Jorge Proença, Sara Candeias, and Fernando Perdigão



Additional information