SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.17852 · 2024

Scaling A Simple Approach to Zero-Shot Speech Recognition

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

Despite rapid progress in increasing the language coverage of automatic speech recognition, the field is still far from covering all languages with a known writing script. Recent work showed promising results with a zero-shot approach requiring only a small amount of text data, however, accuracy heavily depends on the quality of the used phonemizer which is often weak for unseen languages. In this paper, we present MMS Zero-shot a conceptually simpler approach based on romanization and an acoustic model trained on data in 1,078 different languages or three orders of magnitude more than prior art. MMS Zero-shot reduces the average character error rate by a relative 46% over 100 unseen languages compared to the best previous work. Moreover, the error rate of our approach is only 2.5x higher compared to in-domain supervised baselines, while our approach uses no labeled data for the evaluation languages at all.

For agents

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

get_harvested_code_for_paper("2407.17852")
get_code_for_paper("2407.17852")
have("2407.17852")

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

curl https://syntology.ai/api/ran/2407.17852.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.17852.svg)](https://syntology.ai/paper/2407.17852)

Connect an agent — have() is free.