PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTS

Abstract: Previous pitch-controllable text-to-speech (TTS) models rely on directly modeling fundamental frequency, leading to low variance in synthesized speech. To address this issue, we propose PITS, an end-to-end pitch-controllable TTS model that utilizes variational inference to model pitch. Based on VITS, PITS incorporates the Yingram encoder, the Yingram decoder, and adversarial training of pitch-shifted synthesis to achieve pitch-controllability. Experiments demonstrate that PITS generates high-quality speech that is indistinguishable from ground truth speech and has high pitch-controllability without quality degradation. Code and audio samples will be available at https://github.com/anonymous-pits/pits.

Training code is uploaded.

Demo and Checkpoint are uploaded at Hugging Face Space🤗

Audio samples are uploaded at github.io.

For the pitch-shifted Inference, we unify to use the notation in scope-shift, s, instead of pitch-shift.

Preprint version contains some errors! Please wait for the update!

README IS WIP...

• Pytorch>=1.7.0 for alias-free-torch and phaseaug
• The requirements are highlighted in requirements.txt.
• We also provide docker setup Dockerfile.

docker build -t=pits .

• Download VCTK (version 0.92) at link
• Resample files to 22050 Hz, 16 bit, .wav format.

• Resample files to 22050 Hz, 16 bit, .wav format.
• Check configs/config_en.yaml and change data section (e.g. path, files, speakers).
• To utilize a different phoneme set, you will need to modify the Python files located in the text folder.

• Run train.py, check train.py for detailed options.

python train.py -c configs/config_en.yaml -m {MODEL_NAME} {-i:if you change yingram setup or etc}

Demo and Checkpoint are uploaded at Hugging Face Space🤗

We are currently working in progress to make dockerfile for local demo. Please wait for it.

• Official VITS Implementation: https://github.com/jaywalnut310/vits
• NANSY Implementation from dhchoi99: https://github.com/dhchoi99/NANSY
• Official Avocodo Implementation: https://github.com/ncsoft/avocodo
• Official PhaseAug Implementation: https://github.com/mindslab-ai/phaseaug
• Tacotron Implementation from keithito: https://github.com/keithito/tacotron
• CSTR VCTK Corpus (version 0.92): https://datashare.ed.ac.uk/handle/10283/3443
• G2P for demo, g2p_en from Kyubyong: https://github.com/Kyubyong/g2p