Advancing Audio/Speech Machine Learning: From Static to Continual Learning

Dear Colleagues,

Audio and speech signal processing has traditionally relied on static models developed for fixed datasets. However, real-world audio environments are constantly evolving, with new sounds and contexts emerging over time. In such dynamic settings, conventional models struggle to remain effective without frequent retraining. Continual learning offers a promising solution by enabling audio systems to adapt incrementally to new data while retaining previously acquired knowledge. This capability is particularly important in real-world applications such as healthcare, surveillance, and interactive media, where adaptability, efficiency, and robustness are essential.

Continual learning in audio systems not only enhances model generalization and reduces computational costs but also improves resilience in unpredictable environments. Despite these benefits, current research and practice in audio signal processing rarely support continuous adaptation, and issues such as catastrophic forgetting remain unsolved. Moreover, regular conference sessions often emphasize static learning paradigms and lack dedicated space for addressing the unique challenges associated with continual learning using audio data.

This Special Issue, entitled “Advancing Audio/Speech Machine Learning: From Static to Continual Learning”, therefore welcomes the submission of original research articles, technical reports, reviews, and mini-reviews that address topics including, but not limited to, the following:

• Continual learning algorithms for audio and speech;
• Adaptive audio systems for dynamic environments;
• Real-time speech recognition and adaptation;
• Cognitive and contextual audio processing;
• Audio model generalization and robustness;
• Integration of speech feedback mechanisms;
• Cross-domain continual learning in audio applications;
• Mitigating catastrophic forgetting in sequential audio tasks;
• Evaluation frameworks for continual learning in audio systems;
• Interdisciplinary approaches to adaptive audio processing.

Dr. Kele Xu
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Acoustics is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• audio/speech signal processing
• speech recognition enhancement
• continual learning algorithms
• adaptive audio systems
• real-time speech adaptation
• cognitive audio processing
• audio contextual learning
• speech feedback integration
• audio model generalization
• audio system robustness