Special Issue
Table of Contents
- Call for Papers
- Speech Processing with Wearable & Multimodal Technologies
- Topics in Focus
- Who Should Submit
- Important Dates
- Submission Guidelines
Call for Papers
A one-page, LRAC-focused overview of the call for papers, highlighting the topics most relevant to this community:
For the complete scope, topics, and submission details, see the official call for papers on the CSL journal website.
Speech Processing with Wearable & Multimodal Technologies
The Elsevier Computer Speech & Language (CSL) journal is running a special issue on speech processing for wearable and multimodal technologies—smart glasses, earbuds, hearing aids, and headsets operating in everyday, real-world conditions. Emerging from the HSCMA-CHiME and LRAC workshops and associated challenges, this special issue invites papers addressing speech and audio processing with wearable, multimodal, and egocentric sensing technologies. Such technologies create new challenges and opportunities in designing systems for hands-free speech communication that are robust, adaptive, privacy-aware, resource-efficient, and effective in unconstrained real-world conditions.
Building on their respective challenges and workshops, researchers from the CHiME, HSCMA, and LRAC communities are invited to publish expanded accounts of challenge outcomes, workshop contributions, and related follow-up work, while importantly connecting and relating their findings to the overarching theme of advancing speech processing for wearable and multimodal technologies—addressing the fundamental challenges of robustness, efficiency, privacy-awareness, and adaptability in real-world, hands-free communication scenarios where these emerging devices operate.
Topics in Focus
The special issue welcomes a broad range of topics. Those most relevant to the LRAC audience center on efficient on-device speech processing for real-time communication, including:
- Low-resource neural speech coding, quantization and model compression
- Joint speech coding, enhancement and robust transmission for real-time communication
- Resource-constrained speech processing for wearable, mobile and embedded communication systems
- Speech quality and intelligibility measures for evaluating neural speech codecs
For the full list of topics, please refer to the call for papers on the CSL journal website.
Who Should Submit
The special issue provides a publication venue for work emerging from CHiME-9, HSCMA, and LRAC, while remaining open to relevant contributions from the wider research community.
Challenge entries and system-description papers are explicitly welcome, including expanded studies of challenge and workshop contributions, datasets, evaluation frameworks, system implementations, and related follow-up research.
Important Dates
| Date | Milestone |
|---|---|
| August 1, 2026 | Submissions open date |
| December 1, 2026 | Submission deadline |
| October 30, 2027 | Editorial acceptance deadline |
Submission Guidelines
All manuscripts should be submitted electronically through the Editorial Manager®. When submitting papers, please select the Article Type as VSI: WearableSpeechProcessing.
For further details, refer to the call for papers on the CSL journal website.