# The MSXF TTS System for ICASSP 2022 ADD Challenge

arXiv: https://arxiv.org/abs/2201.11400 · HTML: https://mlsanity.com/paper/2201.11400/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 15 references that are in the map.
- First posted on arXiv 27 Jan 2022.

## Builds on (most cited first, 13 of 13)

- [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)
- [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)
- [WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition](https://mlsanity.com/paper/2110.03370/) (2021)
- [AdaSpeech: Adaptive Text to Speech for Custom Voice](https://mlsanity.com/paper/2103.00993/) (2021)
- [Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations](https://mlsanity.com/paper/2110.14513/) (2021)
- [End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection](https://mlsanity.com/paper/2107.12710/) (2021)
- [What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure](https://mlsanity.com/paper/2101.00387/) (2021)
- [One TTS Alignment To Rule Them All](https://mlsanity.com/paper/2108.10447/) (2021)
- [MultiSpeech: Multi-Speaker Text to Speech with Transformer](https://mlsanity.com/paper/2006.04664/) (2020)
- [g2pM: A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset](https://mlsanity.com/paper/2004.03136/) (2020)
- [From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint](https://mlsanity.com/paper/2005.04587/) (2020)

## Abstract (arXiv)

This paper presents our MSXF TTS system for Task 3.1 of the Audio Deep Synthesis Detection (ADD) Challenge 2022. We use an end to end text to speech system, and add a constraint loss to the system when training stage. The end to end TTS system is VITS, and the pre-training self-supervised model is wav2vec 2.0. And we also explore the influence of the speech speed and volume in spoofing. The faster speech means the less the silence part in audio, the easier to fool the detector. We also find the smaller the volume, the better spoofing ability, though we normalize volume for submission. Our team is identified as C2, and we got the fourth place in the challenge.