India is a nation with more than half of its citizens dependent on agriculture for its survival, but only uses 14 percent of its GDP contribution. The nation has divided portions of land, resulting in a significant number of individual farmers with a nearly stagnant productivity. Despite government actions at both the center and the state level, a gap between land and lab our continues. With over 80% of the entire land holdings of tiny and marginal landowners, Karnataka is no exception. The search engine researchers have focused their efforts for years and years on having search engines that are more accurate and faster. In the past, this was more than enough, But the concept of getting everything intelligent became with smart phone appearance. In this paper we attempted to implement a proposed model of a voice-based farmer information system called ("RaitaSnehi") that provides data on the various schemes that farmers can get from various websites. Based on choices that farmers need to know, the user is prompted to give voice input. The word recognition algorithm is then applied using the Python environment and the recognized word is searched from the website in the parsed data and the details of the required data are read out on demand to the farmer. The word recognition algorithm is implemented, which is the template-based comparative algorithm based on hidden markov model, and the results are checked for accuracy. The words are given in the language of Kannada and the results are obtained in the language of Kannada to make the farmers comfortable. Python translation tool is used to convert English to Kannada and when reading from web sources, these words are converted to text to voice in Kannada Language. Through the document we will explain each portion of the proposed model in detail.

Speech Recognition, Hidden Markov Model, Natural Language Processing, Kannada Voice Output

[1] Cemal Hanilc¸et.al., (2013). “Speaker Identification From Shouted Speech: Analysis And Compensation”. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 8027 – 8031, 26-31 May 2013. Vancouver, BC, Canada.
[2] Janne Pylkkönen, (2013). “Towards Efficient and Robust Automatic Speech Recognition: Decoding Techniques and Discriminative Training”. In: Aalto University publication series Doctoral Dissertations, 44/2013. ISSN: 1799-4942 (electronic), 1799-4934 (printed), 1799-4934 (ISSN-L). Aalto University, Finland.
[3] Brahim Patel, Dr.Y.Srinivasa Rao “Speech recognition using Hidden Markov Model With MFCC-Subband Technique.” 2010 International Conference on Recent Trends in Information, Telecommunication and Computing
[4] Johan Schalkwyk,et.al.,(2010). “Google Search by Voice: A Case Study”. In: Advances in Speech Recognition: Mobile Environments, Call Centers and Clinics, Springer, pp. 61-90.
[5] Manas A. Pathak, and Bhiksha Raj,(2013).” Privacy-Preserving Speaker Verification and Identification Using Gaussian Mixture Models” In IEEE Transactions on Audio, Speech & Language Processing, Vol.21,No.2,pp. 397-406.
[6] Qin Jin, (2007). “Robust Speaker Recognition”. In: partial fulfillment of the requirements for the degree of Doctor of Philosophy in Language and Information Technologies, Language Technologies Institute School of Computer Science, Carnegie Mellon University , 5000 Forbes Avenue, Pittsburgh, PA 15213.

[7] Shaikh Salleh, et.al.,(2000). “Speaker Recognition Based On Hidden Markov Model”. In: Natiaonal Conference on Telecommunication Technology 2000, 20th - 21st Nov. 2000, Hyatt Regency Hotel, Johor Bahru.
[8] Ciprian Chelba and Alex Acero, “Position specific posterior lattices for indexing speech”, in ACL, Ann Arbor, 2005, pp. 443-450.
[9] Lin-shan Lee and Berlin Chen, “Spoken Document Understanding and Organization”, IEEE Signal Processing Magazine, Special Issue on Speech Technology in Human-machine Communication, Vol. 22, No.5, Sept. 2005, pp.42-60.
[10] C. Chelba, J. Silva, and A. Acero, “Soft indexing of speech content for search in spoken documents computer speech and language”, Computer Speech and Language, vol. 21, no. 3, pp.458-478, July 2007. [11] Z.-Y. Zhou, P. Yu, C. Chelba, and F. Seide, “Towards spoken-document retrieval for the internet: Lattice indexing for large-scale web-search architectures”, in HLT, 2006, pp. 415–422.
[11] C. Chelba, T. J. Hazen, M. Saraclar, “Retrieval and Browsing of Spoken content”, IEEE Signal Processing Magazine, May 2008, pp.39-49.
[12] Y. Wang, D. Yu, Y.-C. Ju, A. Acero, “An Introduction to Voice Search”, IEEE Signal Processing Magazine, May 2008, pp. 29-38.
[13] A. Moreno-Daniel, B.-H. Juang, J. Wilpon, "A scalable method for voice search to nationwide business listings," icassp, pp.3945-3948, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing, 2009.
[14] Y. Yaguchi, Y. Watanabe, K. Naruse, R. Oka, “Speech and Sound Search on the Web: System Design and Implementation”, IEEE International Conference on Computer and Information Technology 2007.
[15] J. Mamou, B. Ramabhadran, “Phonetic Query Expansion for Spoken Document Retrieval”, Interspeech 2008, pp. 2106-2109.
[16] Speech Recognition, available at: www.learnartificialneuralnetworks.com/speechrecognition.html.
[17] WikipediA: WWW.Wikipedia.org