Reproducing Tacotron2 qualitative claims

Authors: Priyanka Bose, Chandra Shekhar Pandey

This project validates some of the qualitative claims made in the paper:

J. Shen et al., "Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions," 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada, 2018, pp. 4779-4783, doi: 10.1109/ICASSP.2018.8461368.

which describes Tacotron2, a neural network for predicting mel spectograms from text, which can then be used with a vocoder to synthesize speech.

We reproduced some of the results in this paper for our course project in ECE-GY 6143 Introduction to Machine Learning at NYU Tandon, Fall 2022 (with Prof. Fraida Fund).

22 7 3 1 Mar. 28, 2023, 6:49 PM


Launch on Chameleon

Launching this artifact will open it within Chameleon’s shared Jupyter experiment environment, which is accessible to all Chameleon users with an active allocation.

Download Archive

Download an archive containing the files of this artifact.

Download with git

Clone the git repository for this artifact, and checkout the version's commit

git clone
# cd into the created directory
git checkout 682afd5a7a317b7678802220ff054f2d7fdc4c14

Submit feedback through GitHub issues

Version Stats

22 7 3