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

arXiv: https://arxiv.org/abs/2302.12391 · HTML: https://mlsanity.com/paper/2302.12391/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 24 Feb 2023.

## Builds on (most cited first, 30 of 30)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis](https://mlsanity.com/paper/1910.06711/) (2019)
- [Residual Flows for Invertible Generative Modeling](https://mlsanity.com/paper/1906.02735/) (2019)
- [Speech Resynthesis from Discrete Disentangled Self-Supervised Representations](https://mlsanity.com/paper/2104.00355/) (2021)
- [FastPitch: Parallel Text-to-speech with Pitch Prediction](https://mlsanity.com/paper/2006.06873/) (2020)
- [Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations](https://mlsanity.com/paper/2110.14513/) (2021)
- [End-to-End Adversarial Text-to-Speech](https://mlsanity.com/paper/2006.03575/) (2020)
- [VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion](https://mlsanity.com/paper/2106.10132/) (2021)
- [Pushing the limits of raw waveform speaker recognition](https://mlsanity.com/paper/2203.08488/) (2022)
- [One TTS Alignment To Rule Them All](https://mlsanity.com/paper/2108.10447/) (2021)
- [VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis](https://mlsanity.com/paper/2110.08813/) (2021)
- [Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior](https://mlsanity.com/paper/2002.03788/) (2020)
- [VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature](https://mlsanity.com/paper/2204.00768/) (2022)
- [Avocodo: Generative Adversarial Network for Artifact-free Vocoder](https://mlsanity.com/paper/2206.13404/) (2022)
- [WavThruVec: Latent speech representation as intermediate features for neural speech synthesis](https://mlsanity.com/paper/2203.16930/) (2022)
- [FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis](https://mlsanity.com/paper/2106.15123/) (2021)
- [Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques](https://mlsanity.com/paper/2104.00931/) (2021)
- [PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping](https://mlsanity.com/paper/2211.04610/) (2022)
- [Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis](https://mlsanity.com/paper/2212.06397/) (2022)
- [Period VITS: Variational Inference with Explicit Pitch Modeling for End-to-end Emotional Speech Synthesis](https://mlsanity.com/paper/2210.15964/) (2022)
- [GCI detection from raw speech using a fully-convolutional network](https://mlsanity.com/paper/1910.10235/) (2019)

## Built on by (most cited first, 4 of 4)

- [DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training](https://mlsanity.com/paper/2307.16549/) (2023)
- [VIFS: An End-to-End Variational Inference for Foley Sound Synthesis](https://mlsanity.com/paper/2306.05004/) (2023)
- [Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec](https://mlsanity.com/paper/2603.05887/) (2026)
- [Super Monotonic Alignment Search](https://mlsanity.com/paper/2409.07704/) (2024)

## Abstract (arXiv)

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, audio samples, and demo are available at https://github.com/anonymous-pits/pits.