| Paper: | SP-L1.4 | ||
| Session: | Voice Conversion and Morphing Algorithms for TTS Systems | ||
| Time: | Tuesday, May 18, 16:30 - 16:50 | ||
| Presentation: | Lecture | ||
| Topic: | Speech Processing: Speech Synthesis (including TTS) | ||
| Title: | ALGORITHM AMALGAM: MORPHING WAVEFORM BASED METHODS, SINUISOIDAL MODELS AND STRAIGHT | ||
| Authors: | Hideki Kawahara; Wakayama University | ||
| Hideki Banno; Wakayama University | |||
| Toshio Irino; Wakayama University | |||
| Parham Zolfaghari; NTT Communication Science Laboratories | |||
| Abstract: | A tool to investigate an important fundamental question in speech processing is proposed aiming to promote research on voice quality and para and non linguistic aspects of speech. The proposed method effectively emulates waveform-based methods, sinusoidal models and the high quailty source filter model STRAIGHT. The Key idea that enables blending these seemingly disjoint algorithms is a group delay based representation of signal excitation. By using a STRAIGHT-based smoothed time-frequency representation that is shared by these three types of speech processing methods, a unified source representation is used to implement the proposed system. Informal listening tests using the proposed system indicated that phase manipulation introduces different timbre, but it does not need to reproduce the exact waveform to reproducethe same timbre. This may suggest that there exists a room for further information reduction in close to natural quality region. | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops