Cinc-gan For Effective F0 Prediction For Whisper-to-normal Speech Conversion
2020 · Maitreya Patel, Mirali Purohit, Jui Shah, et al.
Abstract
Recently, Generative Adversarial Networks (GAN)-based methods have shown remarkable performance for the Voice Conversion and WHiSPer-to-normal SPeeCH (WHSP2SPCH) conversion. One of the key challenges in WHSP2SPCH conversion is the prediction of fundamental frequency (F0). Recently, authors have proposed state-of-the-art method Cycle-Consistent Generative Adversarial Networks (CycleGAN) for WHSP2SPCH conversion. The CycleGAN-based method uses two different models, one for Mel Cepstral Coefficients (MCC) mapping, and another for F0 prediction, where F0 is highly dependent on the pre-trained model of MCC mapping. This leads to additional non-linear noise in predicted F0. To suppress this noise, we propose Cycle-in-Cycle GAN (i.e., CinC-GAN). It is specially designed to increase the effectiveness in F0 prediction without losing the accuracy of MCC mapping. We evaluated the proposed method on a non-parallel setting and analyzed on speaker-specific, and gender-specific tasks. The objective a
Authors
(none)
Tags
Stats
Related papers
- Vocoder-free Non-parallel Conversion Of Whispered Speech With Masked Cycle-consistent Generative Adversarial Networks (2023)0.00
- Transforming Spectrum And Prosody For Emotional Voice Conversion With Non-parallel Training Data (2020)12.54
- Attention-guided Generative Adversarial Network For Whisper To Normal Speech Conversion (2021)5.84
- High-quality Nonparallel Voice Conversion Based On Cycle-consistent Adversarial Network (2018)0.00
- Generative Models For Improved Naturalness, Intelligibility, And Voicing Of Whispered Speech (2022)6.34
- Maskcyclegan-vc: Learning Non-parallel Voice Conversion With Filling In Frames (2021)0.00
- Spectrum And Prosody Conversion For Cross-lingual Voice Conversion With Cyclegan (2020)0.00
- Joint Magnitude Estimation And Phase Recovery Using Cycle-in-cycle GAN For Non-parallel Speech Enhancement (2021)7.81