SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.03541 · 2021

Multilingual Byte2Speech Models for Scalable Low-resource Speech Synthesis

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

To scale neural speech synthesis to various real-world languages, we present a multilingual end-to-end framework that maps byte inputs to spectrograms, thus allowing arbitrary input scripts. Besides strong results on 40+ languages, the framework demonstrates capabilities to adapt to new languages under extreme low-resource and even few-shot scenarios of merely 40s transcribed recording, without the need of per-language resources like lexicon, extra corpus, auxiliary models, or linguistic expertise, thus ensuring scalability. While it retains satisfactory intelligibility and naturalness matching rich-resource models. Exhaustive comparative and ablation studies are performed to reveal the potential of the framework for low-resource languages. Furthermore, we propose a novel method to extract language-specific sub-networks in a multilingual model for a better understanding of its mechanism.

For agents

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

get_harvested_code_for_paper("2103.03541")
get_code_for_paper("2103.03541")
have("2103.03541")

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

curl https://syntology.ai/api/ran/2103.03541.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.03541.svg)](https://syntology.ai/paper/2103.03541)

Connect an agent — have() is free.