Pseudo-Cepstrum: Pitch Modification for Mel-Based Neural Vocoders

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ellinas, Nikolaos, Vioni, Alexandra, Kakoulidis, Panos, Vamvoukakis, Georgios, Christidou, Myrsini, Markopoulos, Konstantinos, Oh, Junkwang, Jho, Gunu, Hwang, Inchul, Chalamandaris, Aimilios, Tsiakoulis, Pirros
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908720086122496
author Ellinas, Nikolaos
Vioni, Alexandra
Kakoulidis, Panos
Vamvoukakis, Georgios
Christidou, Myrsini
Markopoulos, Konstantinos
Oh, Junkwang
Jho, Gunu
Hwang, Inchul
Chalamandaris, Aimilios
Tsiakoulis, Pirros
author_facet Ellinas, Nikolaos
Vioni, Alexandra
Kakoulidis, Panos
Vamvoukakis, Georgios
Christidou, Myrsini
Markopoulos, Konstantinos
Oh, Junkwang
Jho, Gunu
Hwang, Inchul
Chalamandaris, Aimilios
Tsiakoulis, Pirros
contents This paper introduces a cepstrum-based pitch modification method that can be applied to any mel-spectrogram representation. As a result, this method is compatible with any mel-based vocoder without requiring any additional training or changes to the model. This is achieved by directly modifying the cepstrum feature space in order to shift the harmonic structure to the desired target. The spectrogram magnitude is computed via the pseudo-inverse mel transform, then converted to the cepstrum by applying DCT. In this domain, the cepstral peak is shifted without having to estimate its position and the modified mel is recomputed by applying IDCT and mel-filterbank. These pitch-shifted mel-spectrogram features can be converted to speech with any compatible vocoder. The proposed method is validated experimentally with objective and subjective metrics on various state-of-the-art neural vocoders as well as in comparison with traditional pitch modification methods.
format Preprint
id arxiv_https___arxiv_org_abs_2512_16519
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pseudo-Cepstrum: Pitch Modification for Mel-Based Neural Vocoders
Ellinas, Nikolaos
Vioni, Alexandra
Kakoulidis, Panos
Vamvoukakis, Georgios
Christidou, Myrsini
Markopoulos, Konstantinos
Oh, Junkwang
Jho, Gunu
Hwang, Inchul
Chalamandaris, Aimilios
Tsiakoulis, Pirros
Sound
Machine Learning
Audio and Speech Processing
This paper introduces a cepstrum-based pitch modification method that can be applied to any mel-spectrogram representation. As a result, this method is compatible with any mel-based vocoder without requiring any additional training or changes to the model. This is achieved by directly modifying the cepstrum feature space in order to shift the harmonic structure to the desired target. The spectrogram magnitude is computed via the pseudo-inverse mel transform, then converted to the cepstrum by applying DCT. In this domain, the cepstral peak is shifted without having to estimate its position and the modified mel is recomputed by applying IDCT and mel-filterbank. These pitch-shifted mel-spectrogram features can be converted to speech with any compatible vocoder. The proposed method is validated experimentally with objective and subjective metrics on various state-of-the-art neural vocoders as well as in comparison with traditional pitch modification methods.
title Pseudo-Cepstrum: Pitch Modification for Mel-Based Neural Vocoders
topic Sound
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2512.16519