SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.01145 · 2019

Maximizing Mutual Information for Tacotron

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

End-to-end speech synthesis methods already achieve close-to-human quality performance. However compared to HMM-based and NN-based frame-to-frame regression methods, they are prone to some synthesis errors, such as missing or repeating words and incomplete synthesis. We attribute the comparatively high utterance error rate to the local information preference of conditional autoregressive models, and the ill-posed training objective of the model, which describes mostly the training status of the autoregressive module, but rarely that of the condition module. Inspired by InfoGAN, we propose to maximize the mutual information between the text condition and the predicted acoustic features to strengthen the dependency between them for CAR speech synthesis model, which would alleviate the local information preference issue and reduce the utterance error rate. The training objective of maximizing mutual information can be considered as a metric of the dependency between the autoregressive module and the condition module. Experiment results show that our method can reduce the utterance error rate.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1909.01145")
get_code_for_paper("1909.01145")
have("1909.01145")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1909.01145.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1909.01145.svg)](https://syntology.ai/paper/1909.01145)

Connect an agent — have() is free.