Adaptive Refinements of Pitch Tracking and HNR Estimation within a Vocoder for Statistical Parametric Speech Synthesis
Recent studies in text-to-speech synthesis have shown the benefit of using a continuous pitch estimate; one that interpolates fundamental frequency (F0) even when voicing is not present. However, continuous F0 is still sensitive to additive noise in speech signals and suffers from short-term errors...
Main Authors: | Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Géza Németh |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-06-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/9/12/2460 |
Similar Items
-
The men of the hnr
by: Izold Guegan
Published: (2020-12-01) -
Identification of Minimal Pairs of Japanese Pitch Accent in Noise-Vocoded Speech
by: Yukiko Sugiyama
Published: (2022-05-01) -
Quality differences in male and female vocoded speech.
by: Christopher, Deborah Kaye.
Published: (2024) -
A Smart Control System for the Oil Industry Using Text-to-Speech Synthesis Based on IIoT
by: Ali Raheem Mandeel, et al.
Published: (2023-08-01) -
Anàlisi de la qualitat de la veu dels Mestres d'Educació Infantil i Primària
by: Assumpció Segura Huguet, et al.
Published: (2020-02-01)