Digital Story - Empowering Communities with Voice for Crisis Management

Please click here to view the story.

Empowering Communities with Voice-enabled Technologies for Crisis Management on Prezi

Closing the voice-enabled disaster communication project but looking to do more

-->

Summary of the VoiceICT4D project outcomes

• LIRNEasia, through a stakeholder forum, advocated the Sri Lanka Disaster Management Center (DMC) to move towards a multi-agency situational-awareness platform by creating a register of alerting authorities and then sharing it's call center and Interactive Voice Response (IVR) system resources for emergency communication.

• The “Do you Hear Me” video, communicating the need for voice-enabled Information Communication Technologies (ICTs), to empower community-based emergency coordination, was visited by 496 viewers, of which 48 or them shared their knowledge on the subject. UNISDR debut film festival on DRR, selected our video as as one of the best three in the category of “best human interest story”

• Peer-reviewed scientific articles presented the realization study evidence emphasizing the practical technical instabilities and deficits in those technologies. The message was news to most researchers and practitioners. IVR-based solutions are gradually gaining momentum.

“Clickto here read full report”

What next?

A common consensus by various stakeholders are that the Freedom Fone IVR and Sahana disaster management system integration must be completed. The integration would serve non-latin scripting language and lesser computer literate communities. Moreover, develop an off the shelf implementable comprehensive crisis management solution that can be integrated with main stream media or other emergency management organizations.

There are three broad emergency communication use cases that were discovered through the VoiceICT4D activities:

1. a radio station would manage a missing persons registry comforting concerned citizens of who are missing and who were found
2. citizen journalists would share risk information of incident reports to effectively coordinate and respond to those troubled situations
3. community-based disaster management organizations would coordinate their rescue and relief efforts using interactive voice.

The VoiceICT4D project intends to seek resources to complete the integration, implement, and pilot the comprehensive end-to-end crisis management system. The pilot study would investigate the utility and robustness of such an implementation when applied to the three use cases above. Moreover, the pilot would consider implementing them in diverse environments to better understand the adaptability of the technology. VoiceICT4D would transition from the invention stage to an implementation stage; where the technology would be field tested to offer a stable solution to the global crisis management community.

Beyond Tsunami Warning in a Vocal Society

My first public lecture: the 3rd LIRNEasia Public Lecture was conducted at a time when the Sri Lanka National Disaster Management Center (DMC) was being questioned for it's reliability. The Public Lecture follows two major hazard events: 1) 2011 November 21 Matara Mini Cyclone and 2) 2012 April 11 false tsunami evacuation.

The Government of Sri Lanka failed to warn the fishermen of the deadly mini cyclone that lead to 29 deaths. Detection theorist may label this incident as a missed alarm but essentially it is a true alarm with failed actions. There was a lot of finger pointing between agencies for one denying the responsibility over the other. Such a tragic situation could have been over come if a register of alerting authorities with a profile and procedures and a multi-agency situational awareness technology platform had been in place. The DMC held a stakeholder workshop to discuss a way forward.
With respect to incident 2), the tsunami evacuations continued even after the threat was called off, which insinuates a lack of competence. Decision theorist, from the eyes of a Policy-maker's loss function (i.e. government bureaucrats and politicians prospective), would consider this as a success; thus, the ability to warn of any tsunamigenic earthquake. However, from the eyes of Stakeholder's loss function, such as fishermen not going out to sea anticipating a tsunami, the false warning deprive them of a days house hold income.

The Public Lecture was partially funded by the Humanitarian Innovation Fund (HIF) through the VoiceICT4D project. The aim of this action was to strategically address the public at a right time when the message was sure to be heard by those who should hear it. The lecture presented the formula for removing the aforementioned uncertainties. The Director General of the Sri Lanka DMC, himself, was present at this lecture and was appointed the task of moderating this event. His words following the main presentation was “thank you Nuwan this is an eye-opener.”

The public lecture message intended for the Director General and the audience to hear was that the inter-agency rivalry and reduction of false warnings can be achieved through the adoption of interoperable emergency standards along with the policies and procedures that wrap around those standards. The VoiceICT4D project was designed to educate society of the power of voice-enabled technologies and interoperable data standards. A summary of the Public Lecture talks, on LIRNEasia's blog, outlines the key points.

Sri Lankan's, like most other Eastern societies are accustomed to talking to one another over the phone whether it be personal, business, or informing each other of a crisis, more so than text-ing. The video “do you hear me?”, which was produced through the HIF grant, was screened to remind the public and the DMC of the local requirement. Coincidently, the DMC had invested in a call center and an IVR for emergency information collection and dissemination. LIRNEasia has offered to share the lessons learned from it's voice-enabled ICT for Disaster pilot.

Naturally Interactive Voice works for Emergency Communications in Sri Lanka

It's not just Sri Lanka but most developing countries where voice is the predominant mode of communications can be easily adopted for emergency communications. This is my interview with Freedom Fone.

CAP Text not allowed to Speak in USA

The U.S. has banned Emergency Alerting Systems from using Text-To-Speech in broadcasting Common Alerting Protocol generated messages.

Excerpt from the article – Many of those in my community have a hard time understanding the current version of text to speech. In other words, us old folks can’t hear what the computer is saying. There’s also the issue of geographical differences in words. For example, is “soda” and “pop” the same as “soda pop” or “Coke”. If one were to write “I’d like a Coke and fries”, the computer will read that hearer may need more information, ex. “We don’t serve Coke, is Royal Crown Cola OK?”

Here's what I had to say in the LIRNEasia blog relating it to the Freedom Fone and Sahana project.

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