Call for Papers

Non-Archival Track

• This track encourages submissions of not only novel contributions, but also work in progress, already published works, or system demonstrations.

• The paper submission system will use OpenReview.

• This track aims to socialize research ideas with like-minded audiences, so submissions need not be complete research papers. Nevertheless, all submissions will undergo a screening process to ensure they are technically sound. 

• The accepted papers will NOT be published through IEEE Xplore nor the ISCA archive. They will only be available on this website.

• The papers must follow the ICASSP 2026's author guidelines, but papers up to 8 pages (plus one reference-only page) are allowed.

This workshop focuses on speech processing with wearable and multimodal technologies for everyday life.
The topics of interest include, but are not limited to:

• Hands-free speech communication

• Microphone arrays and beamforming techniques

• Single- and multi-channel speech enhancement and separation

• Acoustic echo cancellation

• Speech recognition and robust speech representations

• Speech synthesis and voice conversion

• Speaker identification, diarization, and localization

• Voice-controlled assistants and teleconferencing systems

• Data simulation, augmentation, and adaptation of pre-trained models

• Joint end-to-end training architectures

• Robust speaker, language, and paralinguistic recognition

• Cross-environment and cross-dataset robustness

• Environmental noise modeling

• Multi-modal and ego-centric signal processing approaches

• Hearing instruments, speech quality, and intelligibility measures

• Speech technology for medical and healthcare