This is the website of the "Signal processing and machine learning to foster accessibility in cultural environments" (SPACE) workshop, to be hosted in conjunction with the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing in June 2023 in Rhodes, Greece.

Workshop date and time: 5 June 2023, 08:30 - 12:00, at the Delphi Amphitheater

The right of equal access to educational and cultural content is described in Article 27 of the Universal Declaration of Human Rights of the United Nations. However, there is practically very limited availability of accessible spaces or educational and cultural content for the social groups with special needs such as the Deaf, blind and partially sighted people, people with physical disabilities, to name but a few.

The recent advances in signal processing and machine learning are expected to make the provision of content-related services feasible for the people with special needs who wish to visit spaces of educational and cultural interest (e.g., museums, archaeological sites, exhibitions etc.). Such services aim to enhance the autonomy and provide information in a way that is adapted to the impairment or disability. Such services may be useful before, during or after the visit. 

Signal processing and machine learning can revolutionize the access to cultural or educational content and spaces in many ways: By perception of the environment or of the human motion (e.g., object recognition, hand tracking, localization), by assisting human actions (e.g., navigation, path planning), by facilitating content presentation (e.g., retrieval, graphics, VR, recommendation, summarization), or by supporting human-computer communication tasks (e.g., sign translation, speech interfaces). 

The workshop will seek to bring together the experts and present the recent advancements in all the related fields. The workshop welcomes any work relevant to signal processing and machine learning challenges in accessibility of cultural content and spaces, including but not limited to tackling one or more of the following challenges, within the context of cultural environment accessibility. 

We aim to attract high quality scientific publications in the following topics

• Gaze tracking

• Visual object recognition 

• Localization in cultural spaces

• Navigation in cultural spaces

• Retrieval of cultural or educational content

• Sign language avatars and sign language production

• Sign language interpretation

• Tracking of human motion for signing or HCI

• VR for the blind

• Speech interfaces

• Content-based recommendation

• Content-based summarization

• Datasets

For more details please see our Call for Papers.