Contact Member Areapopup icon

Public Documents

Publishable Final Activity Report (pdf, 710 KB)
This document summarizes the project objectives, the methodologies and approaches, the main technical achievements, and the possible impact of the project for future applications. It also describes the dissemination activities conducted during the project, and it reports on the publishable results of the final plan for using and disseminating the knowledge.

Executive_Summary_Year2 (pdf, 184 KB)

Executive_Summary_Year1 (pdf, 178 KB)

Robust Speech Recognition (pdf, 124 KB)
This report provides a brief summary of the current state-of-the-art for speech recognition technology in the consumer TV and Set-Top Box (STB) market, examining and comparing several different speechenabled solutions which are available today. It also provides a brief summary of the market opportunity for speech technology in STB and DVR consumer devices. In particular, the report addresses the use of hands-free remote control devices.

Market Study (pdf, 42 KB)
An Automatic Speech Recognition (ASR) component can degrade its on-field performance significantly if it was not designed taking into account the variabilities that can be found in the real-world. According to the early literature in the field, the term "robustness" was initially associated to the main variability factors in the input speech due to the environmental noise, which now is called as "environmental robustness". Beside this, today other types of robustness are investigated as, for instance, the robustness "to distortion in the transmission channel", "to speaker variability", "to distant-talking interaction", and "of spoken dialogue systems"...

Public Deliverables

Month 36

- D6.5 - Final prototype evaluation (pdf, 3655 KB)

Month 32

- D4.2 - Advanced front-end for acoustic scene analysis, distant-talking ASR and speaker verification in the DICIT scenario (pdf, 1528 KB)

Month 30

- D2.4 - Hardware and software architecture for the final STB prototype (pdf, 1601 KB)

- D3.2 - MC-AEC and BSS algorithms for an advanced distant-talking ASR front-end optimized for an interactive TV scenario (pdf, 3513 KB)

Month 23

- D6.4 - First prototype performance evaluation (pdf, 1601 KB)

Month 18

- D3.1 - MC-AEC, acoustic source localization, and beamforming algorithms for distant-talking ASR and surveillance (pdf, 1526 KB)
- D4.1 - Baseline components of speech activity detection, acoustic/speech event classification and distanttalking ASR for the DICIT scenario (pdf, 1700 KB)
- D5.1 - Language modelling, dialogue and user interface in the first set-top-box related DICIT prototype (pdf, 2323 KB)
- D6.2 - Multi-microphone data collection and WOZ experiments for the analysis of user behaviour in the DICIT scenarios (pdf, 2847 KB)

Month 11

- D2.1 - DICIT architecture: tools, standards, hardware and software for the first prototypes (pdf, 3581 KB)

Month 6

- D7.1 - Project Presentation, Dissemination and Use Plan (pdf, 1019 KB)