SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.03191 · ACL · 2022

Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Features

Ngoc Vu, Florian Lux

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

While neural text-to-speech systems perform remarkably well in high-resource scenarios, they cannot be applied to the majority of the over 6,000 spoken languages in the world due to a lack of appropriate training data. In this work, we use embeddings derived from articulatory vectors rather than embeddings derived from phoneme identities to learn phoneme representations that hold across languages. In conjunction with language agnostic meta learning, this enables us to fine-tune a high-quality textto-speech model on just 30 minutes of data in a previously unseen language spoken by a previously unseen speaker.

For agents

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

get_harvested_code_for_paper("2203.03191")
get_code_for_paper("2203.03191")
have("2203.03191")

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

curl https://syntology.ai/api/ran/2203.03191.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.03191.svg)](https://syntology.ai/paper/2203.03191)

Connect an agent — have() is free.