A nifty way to test Speech-To-Text uncertainties with ITU's Difficulty Percentage measure

In these experiments the LIRNEasia researchers used Freedom Fone Interactive Voice Response (IVR) system. First they conducted a survey with known values for the subjects to pick from. These answers were submitted through the IVR. Since the values were known to the human quality testers, this part of the experiment was associated with a speech-to-text trained system (or a speaker-dependent system or voice recognition type system). The second part involved the subjects submitting data that was not based on preset values. They were free to submit answers to questions as they pleased. This was regarded as an untrained or speaker-independent system.

Emulating Speech-To-Text Reliability with ITU Difficulty Scores

"The results show that with a speaker dependent system 95% of the information could be clearly deciphered opposed a speaker independent system that was only 70% clear (blue areas in Figure 1 and Figure 2). It is not surprising, the outcomes are intuitive. In our study reliability had two components, one was efficiency and the other was voice quality. The voice quality also took in to consideration the Mean Opinion Score and the Comparison Categorical Rating. The researchers wish to acknowledge that their may be disagreements in the sample sizes and number of Evaluators. These results are not ideal for drawing a ‘for-all” kind of conclusion. However, at this realize stage of the research it provides a quick and easy method to draw initial conclusions." ...Click to read full article

Interactive voice for a volunteer organization to manage disasters

Crowd sourcing emergency information with Interactive Voice:

"CERT members call one of the four telephone numbers to access Freedom Fone; then press the “reporting” menu item number on their phone keypad to record a “field observation report”. That report is received and stored in the Freedom Fone inbox as an audio file (MP3) at Sarvodaya’s Hazard Information Hub (essentially the data center belonging to the Sarvodaya Community Disaster Management Center). Trained HIH Operators (HIHO) listen to those local language spoken incident field observations, then transform them in to English language text to feed in to the Sahana Eden, Emergency Data Exchange Language Situational Reporting (SITREP) application."
click to read full story

A decision support system for managing politicians during a disaster

Crisis mapping, disasters and aid: A new paradigm:

Prezi presentation on ICCM 2011 by Geeks Without Borders

"It offered key actors and their proxies – some of whom could not be seen together, many of whom were out of Sri Lanka – the ability to in real time or asynchronously, communicate ideas, conduct discussions, upload documents for review, jointly edit them, map out positions and interests of political parties and non-state actors, flesh out and debate public stances and be informed by a range of decision support tools, including a library I curated with resources on peacebuilding. When the tsunami hit, the local and international networks connected via Groove were in a matter of hours turned into a decision support system for relief and aid work. At its peak, over 300 national and international entities, including the Prime Minister’s Office, Sarvodaya and even the US Southern Command, involved in relief efforts in South East Asia, were part of the Groove workspaces set up in Sri Lanka."

Published in The Nation newspaper on 20th November 2011.

Filed under: ICT for Peacebuilding