Narayanamurthy, Praneeth Kurpad and Seelamantula, Chandra Sekhar (2015) Dictionary-Learning-Based Post-Filter for HMM-Based Speech Synthesis. In: IEEE Region 10 Conference (TENCON), NOV 01-04, 2015, Macau, PEOPLES R CHINA.
PDF
IEEE_Reg_Con_2015.pdf - Published Version Restricted to Registered users only Download (156kB) | Request a copy |
Abstract
Oversmoothing of speech parameter trajectories is one of the causes for quality degradation of HMM-based speech synthesis. Various methods have been proposed to overcome this effect, the most recent ones being global variance (GV) and modulation-spectrum-based post-filter (MSPF). However, there is still a significant quality gap between natural and synthesized speech. In this paper, we propose a two-fold post-filtering technique to alleviate to a certain extent the oversmoothing of spectral and excitation parameter trajectories of HMM-based speech synthesis. For the spectral parameters, we propose a sparse coding-based post-filter to match the trajectories of synthetic speech to that of natural speech, and for the excitation trajectory, we introduce a perceptually motivated post-filter. Experimental evaluations show quality improvement compared with existing methods.
Item Type: | Conference Proceedings |
---|---|
Series.: | TENCON IEEE Region 10 Conference Proceedings |
Publisher: | IEEE |
Additional Information: | Copy right for this article belongs to theIEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA |
Keywords: | Dictionary learning; HMM-based speech synthesis; over-smoothing; post-filter |
Department/Centre: | Division of Electrical Sciences > Electrical Engineering |
Date Deposited: | 29 Feb 2016 07:06 |
Last Modified: | 29 Feb 2016 07:06 |
URI: | http://eprints.iisc.ac.in/id/eprint/53336 |
Actions (login required)
View Item |