HSCMA 2008 Flyer (237 KB)

Call for Papers

The Joint Workshop on Hands-free Speech Communication and Microphone Arrays will be held on May 6-8, 2008, at Castello del Buonconsiglio in Trento, Italy. It follows the HSCMA held at Rutgers University in 2005, and continues the tradition of previous workshops on Hands-free Speech Communication (HSC) and Microphone Arrays (MA). The HSCMA 2008 workshop is mainly devoted to reviewing the current state-of-the-art, to presenting recent advances in speech and signal processing techniques based upon multi-microphone systems, and to applications for distant-talking speech communication and human/machine interaction. It brings together researchers and practitioners from universities and industry who are working in the fields of robust speech recognition, speech enhancement, high-quality sound capture, and multiple-input/multiple-output (MIMO) acoustic signal processing. A further objective of the workshop is to provide an informal environment for discussions on: integration of multi-microphone technologies with other sensing devices (e.g., vision, haptics, etc); applications in related fields such as ambient intelligence and smart environments; and, common frameworks for evaluation of technologies at the international level. The technical program will be scheduled to assign one day to multi-microphone processing methods, one day to hands-free speech communication issues, and one day to topics which are relevant either to both areas, or to possible new research directions.

Technical Scope

The technical scope of the workshop includes, but it is not limited to:
- Multichannel acoustic signal processing for speech acquisition, interference mitigation and noise suppression, source localization and separation, dereverberation, echo cancellation, and acoustic event detection;
- Microphone array technology and architectures, especially for distant-talking automatic speech recognition (ASR) and acoustic scene analysis;
- ASR technology for hands-free interfaces, robust features, feature-level enhancement and dereverberation, speech corpora for training and benchmarking;
- Microphone arrays for multimodal human/machine communication;
- Spatial audio analysis and virtual sound rendering for immersive acoustics.

Paper submission

Authors are invited to submit papers in any technical areas relevant to the workshop and are encouraged to give demonstrations of their work. The technical committee will select papers for poster-presentation. Due to a limitation in the possible number of participants, authors of accepted papers will have registration priority for the workshop.