“The Android application named ‘Rakshak’ detects speech patterns through an audio microphone of any user’s smartphone. When the app receives audio clip with speech commands seeking help or saying stop in distressed tones, it triggers an SOS alert, user location and sends an emergency contact,” a statement from the US-based Marconi Society to IANS by e-mail said on Monday.
The app generates the alert after analyzing emotion and distress speech patterns.
Named after Nobel laureate (Physics) Guglielmo Marconi (1874-1937), who invented the radio in 1908, the Society was set up in 1975 by his daughter Gioia Marconi Baraga through an endowment, which annually gives awards for outstanding contribution in science and the principle of creativity in the service of humanity.
Developed by a team from the privately-run Bharti Vidyapeeth College of Engineering in New Delhi, the working app Rakshak is available on the Google Play store.
“The winning team of Piyush Agrawal, Subham Banga, Aniket Sharma and Ujjwal Upadhyay tackled the issue of women’s safety in India, especially in cities and towns across the country, where incidents of women under attack have become common,” said the statement.
The Society’s Celestini programme is a flagship effort to inspire and connect individuals building new technologies in service of a digitally inclusive world.
The Society and its young scholars select universities with promising telecommunications and engineering undergrads and provide them with support and mentorship to help tap their students’ true potential.
“This is the third year of the Celestini programme in India,” Society Chair Vint Cerf said in the statement.
The winners are awarded under the programme, run for the young scholars the world over.
The 4-member team started with the Google Speech command dataset and added speech commands specific to women’s safety.
“The team crowd-sourced additional data and open-sourced it as the Indian EmoSpeech Command dataset. This enabled them to detect emotion, background noise and Indian accents in the audio with improved precision,” noted the statement.
The Indian Institute of Technology (IIT-Delhi) is the India partner for the programme, with $1,500 (Rs 105,750) for the first prize and $500 (Rs 35,250) as the second prize.
The second prize winning team is also from the same college (Vidyapeeth), which developed the app to address the air quality in the country, which has 14 of the 15 most polluted cities in the world, according to the World Health Oganization’s (WHO) global ambient air quality database.
The 4-member team comprising Harshita Diddee, Shivam Grover, Shivani Jindal and Divyanshu Sharma created a privacy-aware smartphone application called VisionAir, which uses photos of the horizon taken from a smartphone to estimate air quality.
“The new app builds on the work done by last year’s Celestini prize winners, which showed that a machine learning model can be built to estimate air quality from an image by extracting image features such as transmission index or haziness and combining them with meteorological data and historical air quality data,” said the statement.
The VisionAir team also enables other developers to create new machine learning models by open-sourcing smartphone images from several locations in Delhi, from different phones with ground truth air quality data from Central Pollution Control Board monitors and Airveda sensors.
The two winning teams were awarded the cash prizes at a function in IIT-Delhi on Monday evening by Aakanksha Chowdhrey, a researcher in Google Brain and a 2012 Marconi Young Scholar.
The two teams also showcased their innovation at the event where IIT-Delhi alumnus and former Motorola and Cisco Systems Chief Technology Officer (CTO) Padmasree Warrior gave a keynote speech.
IANS
Prasanta Patnaik