Meta-Learning in Audio and Speech Processing: An End to End Comprehensive Review

TL;DR

This comprehensive review analyzes various meta-learning techniques applied to audio and speech processing, highlighting their applications, datasets, and future research directions to improve model performance with minimal data.

Contribution

It provides the first systematic survey of meta-learning methods in audio processing, covering methodologies, datasets, and real-world applications.

Findings

Meta-learning enhances low-sample audio processing performance.

The survey identifies key datasets and use cases in audio meta-learning.

Future research directions include data augmentation and task selection strategies.

Abstract

This survey overviews various meta-learning approaches used in audio and speech processing scenarios. Meta-learning is used where model performance needs to be maximized with minimum annotated samples, making it suitable for low-sample audio processing. Although the field has made some significant contributions, audio meta-learning still lacks the presence of comprehensive survey papers. We present a systematic review of meta-learning methodologies in audio processing. This includes audio-specific discussions on data augmentation, feature extraction, preprocessing techniques, meta-learners, task selection strategies and also presents important datasets in audio, together with crucial real-world use cases. Through this extensive review, we aim to provide valuable insights and identify future research directions in the intersection of meta-learning and audio processing.