Dictionary-Learning-Based Post-Filter for HMM-Based Speech Synthesis

Narayanamurthy, Praneeth Kurpad and Seelamantula, Chandra Sekhar (2015) Dictionary-Learning-Based Post-Filter for HMM-Based Speech Synthesis. In: IEEE Region 10 Conference, NOV 01-04, 2015, Macao, PEOPLES R CHINA.

PDF IEEE_Reg_10_Con_2015.pdf - Published Version Restricted to Registered users only Download (152kB) | 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
Additional Information:	Copy right for this article belongs to the IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	08 Oct 2016 07:29
Last Modified:	08 Oct 2016 07:29
URI:	http://eprints.iisc.ac.in/id/eprint/54804

Actions (login required)

View Item