| Paper: | SP-P9.15 | ||
| Session: | Topics in Speech Synthesis | ||
| Time: | Wednesday, May 19, 15:30 - 17:30 | ||
| Presentation: | Poster | ||
| Topic: | Speech Processing: Speech Synthesis (including TTS) | ||
| Title: | SPEECH SYNTHESIS FROM REAL TIME ULTRASOUND IMAGES OF THE TONGUE | ||
| Authors: | Bruce Denby; Université Pierre et Marie Curie | ||
| Maureen Stone; University of Maryland Dental School | |||
| Abstract: | A machine learning technique is used to match reconstructed tongue contours in 30 frame per second ultrasound images to speaker vocal tract parameters obtained from a synchronized audio track. Speech synthesized using the learned parameters and noise as an activation function displays many of the time and frequency domain characteristics of the original audio, and for isolated passages, is remarkably clear – although no articulators other than the tongue are included. | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops