Meta-Learning in Audio and Speech Processing: An End to End Comprehensive Review
This is an incremental contribution as it fills a gap by offering a systematic survey for researchers in audio processing, but it does not present new experimental results or methods.
This paper provides a comprehensive review of meta-learning approaches in audio and speech processing, addressing the need for efficient model performance with minimal annotated samples, and it systematically covers methodologies, datasets, and real-world applications to guide future research.
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.