Learn More
One of the major hurdles in the development of an Automatic Spontaneous Speech Recognition System is the unavailability of large amounts of transcribed spontaneous speech data for training the system. On the other hand transcribed read speech data is available comparatively easily. This paper explores the possibilities of training a spontaneous speech(More)
Entertainment has recently been shown to be a powerful motivator for mastering new technologies. We therefore set out to use viral entertainment to introduce telephone-based, speech-based services to low-literate people in developing countries. We describe Polly, a simple voice manipulation and forwarding system that went viral in Pakistan last year. Seeded(More)
We explore how telephone-based services might be mass adopted by low-literate users in the developing world. We focus on speech and push-button dialog systems requiring neither literacy nor training. Building on the success of <i>Polly</i>, a simple telephone-based voice manipulation and forwarding system that was first tested in 2011, we report on its(More)
This paper reports the design and development of an 82 speaker Urdu speech corpus for speaker independent spontaneous speech recognition using the CMU Sphinx Open Source Toolkit for Speech Recognition. The corpus consists of 45 hours of spontaneous and read speech data from 82 speakers (42 male and 40 female), recorded over a microphone and a telephone(More)
We have been developing techniques for spreading telephone-based services to low-literate people in the developing world, bypassing the need for explicit user training. We achieve this by using entertainment as a viral conduit to spread and popularize development related voice-based services. <i>Polly</i>, our telephone-based voice manipulation and(More)
This paper presents the development of acoustic and language models for robust Urdu speech recognition using the CMU Sphinx Open Source Toolkit for speech recognition. Three models have been developed incrementally, with the addition of speech data of up to two speakers per pass; one model using data from 40 female speakers only, one from 41 male speakers(More)
Sannad Hussain sarmad.hussain' NUCES Huda Sarfraz huda.sarfraz' NUCES Inam Ullah inam.ullah' NUCES Zahid Sarfraz zahid.sarfraz' NUCES the word and sentence based corpus development process in detail. Sections 5 and 7 analyze the resulting corpus and Section 8 concludes the results. A lot of work has been done on the development of speech resources for many(More)
When a free, catchy application shows up, how quickly will people notify their friends about it? Will the enthusiasm drop exponentially with time, or oscillate? What other patterns emerge? Here we answer these questions using data from the Polly telephone-based application , a large influence network of 72,000 people, with about 173,000 interactions ,(More)
We studied the behavior of users of a simple telephone-based voice modification and forwarding system, which has operated in Pakistan for about a year, attracting 165,000 users who interacted with the system by telephone over 636,000 times and generated very rich interaction data. Trying to cluster the users based on their activity profile, we found that(More)