A vocoder-based speech synthesis system, named WORLD, was developed in an effort to
improve the sound quality of real-time applications using speech. Speech analysis …

This paper proposes a novel voice conversion (VC) method based on non-autoregressive
sequence-to-sequence (NAR-S2S) models. Inspired by the great success of NAR-S2S …

This paper introduces a general and flexible framework for F0 and aperiodicity (additive non
periodic component) analysis, specifically intended for high-quality speech synthesis and …

This article focuses on developing a system for high-quality synthesized and converted
speech by addressing three fundamental principles. Although the noise-like component in …

This article introduces a set of interactive tools for studying fundamentals of speech
production, perception and processing. In addition to this voice production simulator, it …

In this paper, a novel vocoder is proposed for a Statistical Voice Conversion (SVC)
framework using deep neural network, where multiple features from the speech of two …

Realistic reconstruction and manipulation of strong vocal expressions found in singing
voices is a challenging and exciting topic. A speech analysis, modification and resynthesis …

We introduce Multi-level feature Fusion-based Periodicity Analysis Model (MF-PAM), a novel
deep learning-based pitch estimation model that accurately estimates pitch trajectory in …

Deep neural networks Page 1 http://smartlab.tmit.bme.hu Continuous vocoder in feed-forward
deep neural network based speech synthesis Mohammed Salah Al-Radhi, Tamás Gábor …

We propose a fundamental frequency (F0) estimation method which is fast, accurate and
suitable for real-time use. While the proposed method is based on the same framework as …