A comparative study of speech and dialed input voice interfaces in rural India

Patel, Neil; Agarwal, Sarla; Rajput, Nitendra; Nanavati, Amit A.; Dave, Paresh; Parikh, Tapan S.

doi:10.1145/1518701.1518709

Cited by 76 publications

(40 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results of user studies conducted in Botswana by Sharma et al [14] in the context of HIV health information systems for the semi and low literate population, also suggest user preference towards touchtone over speech while both systems perform comparably. In contrast, [8] and [15] (which were conducted in a controlled environment) both report that DTMF and numerical input perform better than speech in terms of task completion and performance improvement. Patel et al [15] also report the problem of transitioning between DTMF and speaking as a major challenge.…”

Section: Avaaj Otalomentioning

confidence: 95%

Viral entertainment as a vehicle for disseminating speech-based services to low-literate users

Raza

Pervaiz

Milo

et al. 2012

Proceedings of the Fifth International Conference on Information and Communication Technologies and Development

View full text Add to dashboard Cite

1Entertainment 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 once by 32 low-skilled office workers in a Pakistani university, in 3 weeks Polly amassed 2,032 users and 10,629 interactions. From analyzing the traffic and its content, it is evident that Polly has been used extensively for entertainment and social contact, but it has also been put to an unintended use as a voicemail and group messaging facility. This demonstrated the potential for speech based services, and the pent-up demand for entertainment, among our target population. Also of note, Polly's viral spread crossed gender and age boundaries and even established itself in a female population. However, it appears to have not crossed socioeconomic boundaries. Permission to make digital or hard copies of part or all of this work for Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. ICTD '12, March 12 -15 2012, Atlanta, GA, USA Copyright 2012 ACM 978-1-4503-1045-1/12/03…$10.00. Categories and Subject Descriptors Entertainment as Vehicle for DevelopmentMost ICTD projects focus on core development areas -such as health, agriculture, and education -and design user interfaces suitable for their target users, who are often low literate and inexperienced with technology. Recently, however, Smyth et al.[1] described the remarkable ingenuity exhibited by such users when they are motivated by the desire be to entertained, and concluded that such powerful motivation "turns UI barriers into mere speed bumps" (ibid). Inspired by this powerful demonstration, we set out to systematically develop viral entertainment as a vehicle for dissemination of development related services.Our ultimate goal is to disseminate speech-based communication services for low-literate telephone users throughout the developing world. Such services may include: buying and selling goods and services (i.e. a speech-based equivalent of Craig's List, craigslist.com); finding and communicating with others who share a common interest, and facilitating social and political activism (speech-based message boards); expressing opinions and making them broadly accessible to others (speech-based blogging and tweeting); sending and receiving group messages (speech-based mailing lists); broadcasting and receiving announcement...

show abstract

Section: Avaaj Otalomentioning

confidence: 95%

Viral entertainment as a vehicle for disseminating speech-based services to low-literate users

Raza

Pervaiz

Milo

et al. 2012

Proceedings of the Fifth International Conference on Information and Communication Technologies and Development

View full text Add to dashboard Cite

show abstract

“…[6] It was observed that, that the markets are highly skewed against producers with restrictive practices and non transparency due to their non-linkage with markets and the absolutely no access to information (literacy rates in Rural India is 58.7% with almost 71% males being literate while just 46% females are literate) [6] It is aimed to build a technology driven agriculture and allied services market place and information exchange accessible by the rural farming community in India.…”

Section: Need Of the Systemmentioning

confidence: 99%

“…The basic and most widely used parametric representation are linear predictive coding (LPC), Perceptual Linear Predictive coding (PLP),RASTA( RelAtive SpecTrA) and Melfrequency cepstrum Coefficient (MFCC). [6] The role of the speech recognition system is to create a mapping between the speech vectors and the corresponding symbols. [8] …”

Section: Feature Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Marathi Interactive Voice Response System (IVRS) using MFCC and DTW

Baheti¹,

Gawali²,

Mehrotra³

2015

IJCA

View full text Add to dashboard Cite

The need for quick and broad application of Speech enabled systems is becoming obvious. Studies have shown that there is a substantial "digital divide" that prevents many of our citizens, particularly illiterate rural people, from using the emerging technology. In order to accelerate this essential "technology transfer," this research aims to develop an Interactive Voice Response (IVR) system (IVRS) for rural agricultural purpose, using Marathi speech recognition. The automatic recognition of speech, enabling a natural and easy to use method of communication between human and machine, is an active area of research. The proposed IVR system in this research uses Speech Recognition technology in Marathi language that handles the queries of transactions at "Krushi Utpanna Bajar Samiti".

show abstract

“…For some low-literate users, speech-based interaction has been found to be more effective than traditional touch-tone interfaces [3]. However, such interaction must be based on high quality automatic speech recognition (ASR) and a well-designed user interface [4]. The problem lies with the development of such ASR given the constraints of technical knowledge and training data availability.…”

Section: Introductionmentioning

confidence: 99%

Discriminative pronunciation learning for speech recognition for resource scarce languages

Chan

Rosenfeld

2012

Proceedings of the 2nd ACM Symposium on Computing for Development

View full text Add to dashboard Cite

In this paper, we describe a method to create speech recognition capability for small vocabularies in resource-scarce languages. By resource-scarce languages, we mean languages that have a small or economically disadvantaged user base which are typically ignored by the commercial world. We use a high-quality welltrained speech recognizer as our baseline to remove the dependence on large audio data for an accurate acoustic model. Using cross-language phoneme mapping, the baseline recognizer effectively recognizes words in our target language. We automate the generation of pronunciations and generate a set of initial pronunciations for each word in the vocabulary. Next, we remove potential conflicts in word recognition by discriminative training.

show abstract

A comparative study of speech and dialed input voice interfaces in rural India

Cited by 76 publications

References 6 publications

Viral entertainment as a vehicle for disseminating speech-based services to low-literate users

Viral entertainment as a vehicle for disseminating speech-based services to low-literate users

Marathi Interactive Voice Response System (IVRS) using MFCC and DTW

Discriminative pronunciation learning for speech recognition for resource scarce languages

Contact Info

Product

Resources

About