Restructuring speech representations using a pitch-adaptive time–frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds

1999/04/01 by Hideki Kawahara, Ikuyo Masuda-Katsuse, Alain de Cheveigné · 8 citations
Computer Science · #Music and Audio Processing #Speech Recognition and Synthesis #Speech and Audio Processing

paper · doi:10.1016/s0167-6393(98)00085-5

crossref issued 1999/04/01 · crossref published 1999/04/01 · crossref published-print 1999/04/01 · openalex publication_date 1999/04/01 · crossref created 2003/04/05 · crossref deposited 2023/04/16 · openalex created_date 2025/10/10 · crossref indexed 2026/07/30 · openalex updated_date 2026/07/30

Citations

• Speech analysis/Synthesis based on a sinusoidal representation

Cited by

• Significance of Maximum Spectral Amplitude in Sub-bands for Spectral Envelope Estimation and Its Application to Statistical Parametric Speech Synthesis
• Synthesis of Tongue Motion and Acoustics From Text Using a Multimodal Articulatory Database
• An acoustic study of Georgian stop consonants
• Many-to-Many Voice Conversion with Out-of-Dataset Speaker Support
• Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks
• EMA2S: An End-to-End Multimodal Articulatory-to-Speech System
• Noise Robust TTS for Low Resource Speakers using Pre-trained Model and Speech Enhancement
• Formant [wikipedia]