# Flavored Tacotron: Conditional Learning for Prosodic-linguistic Features

arXiv: https://arxiv.org/abs/2104.04050 · HTML: https://mlsanity.com/paper/2104.04050/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 22 references that are in the map.
- First posted on arXiv 8 Apr 2021.

## Builds on (most cited first, 11 of 11)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram](https://mlsanity.com/paper/1910.11480/) (2019)
- [An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution](https://mlsanity.com/paper/1807.03247/) (2018)
- [Investigation of enhanced Tacotron text-to-speech synthesis systems with self-attention for pitch accent language](https://mlsanity.com/paper/1810.11960/) (2018)
- [Cross-lingual Multi-speaker Text-to-speech Synthesis for Voice Cloning without Using Parallel Corpus for Unseen Speakers](https://mlsanity.com/paper/1911.11601/) (2019)
- [Prosodic Prominence and Boundaries in Sequence-to-Sequence Speech Synthesis](https://mlsanity.com/paper/2006.15967/) (2020)
- [Investigation of learning abilities on linguistic features in sequence-to-sequence text-to-speech synthesis](https://mlsanity.com/paper/2005.10390/) (2020)
- [Investigating accuracy of pitch-accent annotations in neural network-based speech synthesis and denoising effects](https://mlsanity.com/paper/1808.00665/) (2018)

## Abstract (arXiv)

Neural sequence-to-sequence text-to-speech synthesis (TTS), such as Tacotron-2, transforms text into high-quality speech. However, generating speech with natural prosody still remains a challenge. Yasuda et. al. show that unlike natural speech, Tacotron-2's encoder doesn't fully represent prosodic features (e.g. syllable stress in English) from characters, and result in flat fundamental frequency variations. In this work, we propose a novel carefully designed strategy for conditioning Tacotron-2 on two fundamental prosodic features in English -- stress syllable and pitch accent, that help achieve more natural prosody. To this end, we use of a classifier to learn these features in an end-to-end fashion, and apply feature conditioning at three parts of Tacotron-2's Text-To-Mel Spectrogram: pre-encoder, post-encoder, and intra-decoder. Further, we show that jointly conditioned features at pre-encoder and intra-decoder stages result in prosodically natural synthesized speech (vs. Tacotron-2), and allows the model to produce speech with more accurate pitch accent and stress patterns. Quantitative evaluations show that our formulation achieves higher fundamental frequency contour correlation, and lower Mel Cepstral Distortion measure between synthesized and natural speech. And subjective evaluation shows that the proposed method's Mean Opinion Score of 4.14 fairs higher than baseline Tacotron-2, 3.91, when compared against natural speech (LJSpeech corpus), 4.28.