AutoSpeech 2020: The Second Automated Machine Learning Challenge for Speech Classification

TL;DR

AutoSpeech 2020 is a challenge that advances automated machine learning for speech classification by including more diverse tasks, noisier data, and a new evaluation metric, requiring adaptive solutions for varied speech processing tasks.

Contribution

This paper introduces the second AutoSpeech challenge, expanding on previous work with more tasks, noisier data, and an updated evaluation protocol for automated speech classification.

Findings

Increased number of speech tasks in the challenge

Handling noisier data in speech classification

Modified evaluation metric for better assessment

Abstract

The AutoSpeech challenge calls for automated machine learning (AutoML) solutions to automate the process of applying machine learning to speech processing tasks. These tasks, which cover a large variety of domains, will be shown to the automated system in a random order. Each time when the tasks are switched, the information of the new task will be hinted with its corresponding training set. Thus, every submitted solution should contain an adaptation routine which adapts the system to the new task. Compared to the first edition, the 2020 edition includes advances of 1) more speech tasks, 2) noisier data in each task, 3) a modified evaluation metric. This paper outlines the challenge and describe the competition protocol, datasets, evaluation metric, starting kit, and baseline systems.