# A Neural Text-to-Speech Model Utilizing Broadcast Data Mixed with Background Music

arXiv: https://arxiv.org/abs/2103.03049 · HTML: https://mlsanity.com/paper/2103.03049/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 20 references that are in the map.
- First posted on arXiv 4 Mar 2021.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis](https://mlsanity.com/paper/1803.09017/) (2018)
- [Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation](https://mlsanity.com/paper/1806.03185/) (2018)
- [VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking](https://mlsanity.com/paper/1810.04826/) (2018)
- [Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention](https://mlsanity.com/paper/1710.08969/) (2017)

## Built on by (most cited first, 1 of 1)

- [Enhancement of Pitch Controllability using Timbre-Preserving Pitch Augmentation in FastPitch](https://mlsanity.com/paper/2204.05753/) (2022)

## Abstract (arXiv)

Recently, it has become easier to obtain speech data from various media such as the internet or YouTube, but directly utilizing them to train a neural text-to-speech (TTS) model is difficult. The proportion of clean speech is insufficient and the remainder includes background music. Even with the global style token (GST). Therefore, we propose the following method to successfully train an end-to-end TTS model with limited broadcast data. First, the background music is removed from the speech by introducing a music filter. Second, the GST-TTS model with an auxiliary quality classifier is trained with the filtered speech and a small amount of clean speech. In particular, the quality classifier makes the embedding vector of the GST layer focus on representing the speech quality (filtered or clean) of the input speech. The experimental results verified that the proposed method synthesized much more high-quality speech than conventional methods.