PHASE 1 - Resources & Specifications

Activities	Partners	Results
I.1. Available resources and the speech synthesis system's specifications	C0, P1	D1.1 Available resources and the speech synthesis system's specifications (M6)
I.2. Identification of users' needs and common use-case scenarios	P2, P3	D2.1 Report on the system's functionalities and the predefined scenarios (M6)
I.3. Defining the technical framework for the audio-video database	C0, P1, P2	D3.1 Technical framework for the audio-video database (M6)
I.4. Defining the specifications for the REST interface and the IaaS platform	C0, P1	D6.1 Cloud-based speech synthesis system's specifications (M6)

PHASE 2 - Experimental components development

Activities	Partners	Results
II.1. Speech synthesis system development	C0, P1	D1.2 Preliminary speech synthesis system (M18)
II.2. Evaluation of the synthetic voices for social interaction (I)	C0, P2, P3	D2.2 Report on the psycho-social variables which need personalisation (M18)
II.3. Audio-video database development (I)	C0, P2, P3	D3.2a Database v1.0 (M18)
II.4.1 Text prediction for a limited set of scenarios II.4.2. Visual speech recognition methods and algorithms	C0, P1	D4.1 Context model for text prediction (M18) D4.2 Preliminary text prediction system (M18) D4.3 Report on visual speech recognition methods (M18)
II.5. Speech synthesis Cloud service development (into Phase 3)	C0, P1	D5.2 Experimental version of the Cloud-based speech synthesis system for mobile access (M18)
II.6. Dissemination (into Phase 3)	C0, P1, P2, P3	D7.1 Project webpage (M7) D7.2 Dissemination plan (M12) D7.3 Promotional materials (M12) D7.4 Publications and tutorials (M18)

PHASE 3 - Integration and evaluation

Activities	Partners	Results
III.1. Integration of the high-quality speech synthesis system	C0, P1	D1.3 High-quality speech synthesis system (M24)
III.2.1. Evaluation of the synthetic voices for social interaction (II)	C0, P2, P3	D2.3 Report on user's satisfaction (M26)
III.3.1. Audio-video database development (II) III.3.2 Labelled audio-video database	C0, P2, P3	D3.2a Database v2.0 (M24) D3.3 Labelled audio-video database (M27)
III.4. Fast text input	C0, P1	D4.4 Fast text input demo (M27)
III.5. Dissemination and results exploitation	C0, P1, P2, P3	D7.4a Publications and tutorials (M30) D7.5 IPR agreement (M30) D7.6 Exploitation plan (M24)

PHASE 4 - System adaptation

Activities	Partners	Results
IV.1. Evaluation of the synthesis system's psycho-social impact	C0, P2, P3	D2.4 Scientific report on the synthetic voice's psycho-social impact (M39)
IV.2.3. Algorithms for visual speech recognition	C0, P1	D4.3b Experimental results for the visual speech recognition (M39)
IV.2.1. Preliminary system for speaker adaptation IV.2.2. A fast and efficient speaker adaptation model	C0, P1	D5.1 Preliminary system for speaker adaptation (M34) D5.2 An improved model for speaker adaptation (M39)
IV.3. Cloud-based service for speech synthesis	C0, P1, P2, P3	D6.2a Demo version of the Cloud-based speech synthesis system for mobile access (M39)
IV.4. Dissemination and results exploitation	C0, P1, P2, P3	D7.4b Publications and tutorials (M39) D7.5 IPR agreement (M39) D7.6 Exploitation plan (M39)