Academic Journal

Fast-VGAN: Lightweight Voice Conversion with Explicit Control of F0 and Duration Parameters

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Fast-VGAN: Lightweight Voice Conversion with Explicit Control of F0 and Duration Parameters
Συγγραφείς: Abrassart, Mathilde, Obin, Nicolas, Roebel, Axel
Συνεισφορές: Abrassart, Mathilde
Πηγή: 13th edition of the Speech Synthesis Workshop. :181-188
Publication Status: Preprint
Στοιχεία εκδότη: ISCA, 2025.
Έτος έκδοσης: 2025
Θεματικοί όροι: Controllability, [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], FOS: Computer and information sciences, Sound (cs.SD), [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, [INFO] Computer Science [cs], Durations Control, [INFO.INFO-SD] Computer Science [cs]/Sound [cs.SD], Pitch, Sound, Artificial Intelligence (cs.AI), Artificial Intelligence, Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Phonemes Control, Speech Synthesis, Audio and Speech Processing, Voice conversion
Περιγραφή: Precise control over speech characteristics, such as pitch, duration, and speech rate, remains a significant challenge in the field of voice conversion. The ability to manipulate parameters like pitch and syllable rate is an important element for effective identity conversion, but can also be used independently for voice transformation, achieving goals that were historically addressed by vocoder-based methods. In this work, we explore a convolutional neural network-based approach that aims to provide means for modifying fundamental frequency (F0), phoneme sequences, intensity, and speaker identity. Rather than relying on disentanglement techniques, our model is explicitly conditioned on these factors to generate mel spectrograms, which are then converted into waveforms using a universal neural vocoder. Accordingly, during inference, F0 contours, phoneme sequences, and speaker embeddings can be freely adjusted, allowing for intuitively controlled voice transformations. We evaluate our approach on speaker conversion and expressive speech tasks using both perceptual and objective metrics. The results suggest that the proposed method offers substantial flexibility, while maintaining high intelligibility and speaker similarity.
8 pages, 4 figures
Τύπος εγγράφου: Article
Conference object
Περιγραφή αρχείου: application/pdf
DOI: 10.21437/ssw.2025-28
DOI: 10.48550/arxiv.2507.04817
Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2507.04817
https://hal.science/hal-05148026v1
Rights: CC BY
Αριθμός Καταχώρησης: edsair.doi.dedup.....5a29ed0033ea65db047ebac04e1be3be
Βάση Δεδομένων: OpenAIRE