SP-L2: Speech Synthesis I |
| Session Type: Lecture |
| Time: Tuesday, March 27, 16:30 - 18:30 |
| Location: Room B-1 |
| Session Chairs: Nick Campbell, Trinity College Dublin and Heiga Zen, Google UK Ltd.
|
| |
|
SP-L2.1: ARTICULATORY FEATURES FOR EXPRESSIVE SPEECH SYNTHESIS
|
| Alan Black; Carnegie Mellon University
|
| H Timothy Bunnell; Nemours Biomedical Research
|
| Ying Dou; The Johns Hopkins University
|
| Prasanna Kumar; Carnegie Mellon University
|
| Florian Metze; Carnegie Mellon University
|
| Daniel Perry; University of California at Los Angeles
|
| Tim Polzehl; Technische Universität Berlin
|
| Kishore Prahallad; IIIT Hyderabad
|
| Stefan Steidl; ICSI
|
| Callie Vaughn; Oberlin College
|
| |
|
SP-L2.2: UNSUPERVISED CLUSTERING OF EMOTION AND VOICE STYLES FOR EXPRESSIVE TTS
|
| Florian Eyben; Toshiba Research Europe Limited
|
| Sabine Buchholz; Toshiba Research Europe Limited
|
| Norbert Braunschweiler; Toshiba Research Europe Limited
|
| Javier Latorre; Toshiba Research Europe Limited
|
| Vincent Wan; Toshiba Research Europe Limited
|
| Mark J.F. Gales; Toshiba Research Europe Limited
|
| Kate Knill; Toshiba Research Europe Limited
|
| |
|
SP-L2.3: DATA-DRIVEN PHRASING FOR SPEECH SYNTHESIS IN LOW-RESOURCE LANGUAGES
|
| Alok Parlikar; Carnegie Mellon University
|
| Alan Black; Carnegie Mellon University
|
| |
|
SP-L2.4: MODELING PITCH TRAJECTORY BY HIERARCHICAL HMM WITH MINIMUM GENERATION ERROR TRAINING
|
| Yi-Jian Wu; Microsoft Research Asia
|
| Frank Soong; Microsoft Research Asia
|
| |
|
SP-L2.5: AUTOREGRESSIVE HMM SPEECH SYNTHESIS
|
| Carl Quillen; MIT Lincoln Laboratory
|
| |
|
SP-L2.6: ON MEASURING THE INTELLIGIBILITY OF SYNTHETIC SPEECH IN NOISE --- DO WE NEED A REALISTIC NOISE ENVIRONMENT?
|
| Tuomo Raitio; Aalto University
|
| Marko Takanen; Aalto University
|
| Olli Santala; Aalto University
|
| Antti Suni; University of Helsinki
|
| Martti Vainio; University of Helsinki
|
| Paavo Alku; Aalto University
|
| |