The 2015 Afeka Conference for Speech Processing Conference will feature workgroups on speech processing related topics.

Participation is included in the standard registration fee.

The goal of each workgroup is to generate a discussion between the industry and academia on a specific speech processing technology or application. Workgroup discussions will focus on data exchange, identifying barriers, deliberating possible solutions and developing recommendations for advancing technologies in the field. Each workgroup will be chaired by a research or technology professional from the field and will include several short presentations from the academia, industry and application/technology end-users and a discussion.

If you are interested in giving a presentation in any of the workgroups, please contact: SPD-Technical@afeka.ac.il

All conference participants will be invited to join the workgroup of their choice.

WORKGROUPS

Language Resources: Challenges and Applications

Chairman: Dr. Vered Silber-Varod, Open University of Israel

The focus of this workgroup will be on speech processing language resources (LR) - on the challenges involved in collecting LRs, and in their use for existing and future applications. We will ask to what extent speech technologies depend on LRs; discuss how technology copes with under-resourced languages; and ask whether research can do more to improve the portability of speech and language technologies for multilingual applications, particularly for under-resourced languages.

Speakers:

• Prof. Alon Itai, Technion Israel Institute of Technology – The Graphical User Interface for KWIC in Hebrew
• Alex Borodin, Samion Buchas,  Lev Kapnulin,  Bogdan Tsiganiyk,  Nissim Harel & Dr. Nava Shaked, Holon Institute of Technology – A Speech Crawler as Acoustic DB Generator
• Michal Gishri, ACLP, Afeka Tel Aviv Academic College of Engineering – Using ‘Very Limited’ Language Resources for Keyword Spotting
• Dr. Vered Silber-Varod, Jacob Azogui, and Dr. Anat Lerner, Open University of Israel – Towards the compilation of a Hebrew Map Task Corpus

Speech & Language Technologies for Security/Intelligence Applications
Chairmen: Dr. Itsik Lapidot & Dr. Irit Opher, ACLP, Afeka

This workgroup will focus on using speech & language technologies for Security and Intelligence applications. We will address the unique conditions of the Security / Intelligence world and see how they are reflected in the special requirements of each application. We will discuss how commercial applications can be utilized for Security / Intelligence needs - is it only a question of finding the right working point, or is it more complex? We will also cover different aspects of the uniqueness of Security & Intelligence applications such as acoustic conditions, domain-specific channels, special syntax and jargon, as well as, rapid deployment of new languages and topics.

Speakers:

• Maor Nissan, Research and Location Engine TL, Cyber & Intelligence Solution Division, Nice Systems – Speech Analytics Challenges for Security/Intelligence Applications
• Dr. Dina Lisnyansky, Research Fellow, Dept. of Political Sciences, Bar-Ilan University – Text Recognition in Cultural Context: The Case of Islamic Jargon
• Almog Aley-raz, GM & VP Voice Biometrics and Security Solutions, Nuance Communications
• Dr. Itsik Lapidot, ACLP, Afeka – Data Homogeneity Measure for Forensic Voice Comparison
• Dr. Irit Opher, ACLP, Afeka – Intelligence Production using Speech & Language Technologies

The Future of Speech Applications - Cloud, Embedded or Hybrid?
Chairman: Eran Aharonson, Afeka

The introduction of smartphones with advanced operating systems (iOS, Android), the upcoming IoT era and cloud service along with endless free services have all created new opportunities for speech integration. In the speech applications workgroup, we will discuss the future of speech will be within applications. Will speech recognition be embedded as devices becoming stronger? or will cloud services offer a better solution? Or is it possible a hybrid integration will offer the best of all worlds.

Speakers:

• Eran Aharonson, Afeka – Speech Applications Historical Overview and Introduction
• Dr. Alexander Goldin, CEO, Alango Technologies  – Voice Enhancement
• Shlomo Peller, Founder, Chairman & CEO,  Rubidium Signal Technologies  – Advanced Challenges in Implementing Embedded Speech User Interface
• Ron Hoory, Mgr. Speech Technologies, IBM Haifa Research Lab & IBM Watson TTS Lead – Speech in the Cognitive Computing Era
  
• Dr. Yoav Medan, Researcher, Inventor, Entrepreneur, TED Speaker  – Voice of Things
• Jens Baron,  Product Manager UX,  Waze/Google – Natural Man-Machine Interaction