Improvements in Spoken Query System to Access the Agricultural Commodity Prices and Weather Information in Kannada Language/Dialects
In this paper, the improvements in the recently developed end to end spoken query system to access the agricultural commodity prices and weather information in Kannada language/dialects is demonstrated. The spoken query system consists of interactive voice response system (IVRS) call flow, automatic...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2018-06-01
|
| Series: | Journal of Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/jisys-2018-0120 |
| _version_ | 1818597365798404096 |
|---|---|
| author | Yadava Thimmaraja G. Jayanna H.S. |
| author_facet | Yadava Thimmaraja G. Jayanna H.S. |
| author_sort | Yadava Thimmaraja G. |
| collection | DOAJ |
| description | In this paper, the improvements in the recently developed end to end spoken query system to access the agricultural commodity prices and weather information in Kannada language/dialects is demonstrated. The spoken query system consists of interactive voice response system (IVRS) call flow, automatic speech recognition (ASR) models and agricultural commodity prices, and weather information databases. The task specific speech data used in the earlier spoken query system had a high level of background and other types of noises as it is collected from the farmers of Karnataka state (a state in India that speaks the Kannada language) under uncontrolled environment. The different types of noises present in collected speech data had an adverse effect on the on-line and off-line recognition performances. To improve the recognition accuracy in spoken query system, a noise elimination algorithm is proposed in this work, which is a combination of spectral subtraction with voice activity detection (SS-VAD) and minimum mean square error spectrum power estimator based on zero crossing (MMSE-SPZC). The noise elimination algorithm is added in the system before the feature extraction part. In addition to this, alternate acoustic models are developed using subspace Gaussian mixture models (SGMM) and deep neural network (DNN). The experimental results show that these modeling techniques are more powerful than the conventional Gaussian mixture model (GMM) – hidden Markov model (HMM), which was used as a modeling technique for the development of ASR models to design earlier spoken query systems. The fusion of noise elimination technique and SGMM/DNN-based modeling gives a better relative improvement of 7% accuracy compared to the earlier GMM-HMM-based ASR system. The least word error rate (WER) acoustic models could be used in spoken query system. The on-line speech recognition accuracy testing of developed spoken query system (with the help of Karnataka farmers) is also presented in this work. |
| first_indexed | 2024-12-16T11:46:39Z |
| format | Article |
| id | doaj.art-1ef0950137cc40f6a46c8ca8cb77ffb3 |
| institution | Directory Open Access Journal |
| issn | 0334-1860 2191-026X |
| language | English |
| last_indexed | 2024-12-16T11:46:39Z |
| publishDate | 2018-06-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Journal of Intelligent Systems |
| spelling | doaj.art-1ef0950137cc40f6a46c8ca8cb77ffb32022-12-21T22:32:49ZengDe GruyterJournal of Intelligent Systems0334-18602191-026X2018-06-0129166468710.1515/jisys-2018-0120Improvements in Spoken Query System to Access the Agricultural Commodity Prices and Weather Information in Kannada Language/DialectsYadava Thimmaraja G.0Jayanna H.S.1Research Scholar, Panini Research Center, 3rd Floor, Department of ECE, Siddaganga Institute of Technology, Tumkur, Karnataka 572103, IndiaDepartment of ISE, Siddaganga Institute of Technology, Tumkur, Karnataka, IndiaIn this paper, the improvements in the recently developed end to end spoken query system to access the agricultural commodity prices and weather information in Kannada language/dialects is demonstrated. The spoken query system consists of interactive voice response system (IVRS) call flow, automatic speech recognition (ASR) models and agricultural commodity prices, and weather information databases. The task specific speech data used in the earlier spoken query system had a high level of background and other types of noises as it is collected from the farmers of Karnataka state (a state in India that speaks the Kannada language) under uncontrolled environment. The different types of noises present in collected speech data had an adverse effect on the on-line and off-line recognition performances. To improve the recognition accuracy in spoken query system, a noise elimination algorithm is proposed in this work, which is a combination of spectral subtraction with voice activity detection (SS-VAD) and minimum mean square error spectrum power estimator based on zero crossing (MMSE-SPZC). The noise elimination algorithm is added in the system before the feature extraction part. In addition to this, alternate acoustic models are developed using subspace Gaussian mixture models (SGMM) and deep neural network (DNN). The experimental results show that these modeling techniques are more powerful than the conventional Gaussian mixture model (GMM) – hidden Markov model (HMM), which was used as a modeling technique for the development of ASR models to design earlier spoken query systems. The fusion of noise elimination technique and SGMM/DNN-based modeling gives a better relative improvement of 7% accuracy compared to the earlier GMM-HMM-based ASR system. The least word error rate (WER) acoustic models could be used in spoken query system. The on-line speech recognition accuracy testing of developed spoken query system (with the help of Karnataka farmers) is also presented in this work.https://doi.org/10.1515/jisys-2018-0120noise eliminationivrsasraccuracyspoken query system |
| spellingShingle | Yadava Thimmaraja G. Jayanna H.S. Improvements in Spoken Query System to Access the Agricultural Commodity Prices and Weather Information in Kannada Language/Dialects Journal of Intelligent Systems noise elimination ivrs asr accuracy spoken query system |
| title | Improvements in Spoken Query System to Access the Agricultural Commodity Prices and Weather Information in Kannada Language/Dialects |
| title_full | Improvements in Spoken Query System to Access the Agricultural Commodity Prices and Weather Information in Kannada Language/Dialects |
| title_fullStr | Improvements in Spoken Query System to Access the Agricultural Commodity Prices and Weather Information in Kannada Language/Dialects |
| title_full_unstemmed | Improvements in Spoken Query System to Access the Agricultural Commodity Prices and Weather Information in Kannada Language/Dialects |
| title_short | Improvements in Spoken Query System to Access the Agricultural Commodity Prices and Weather Information in Kannada Language/Dialects |
| title_sort | improvements in spoken query system to access the agricultural commodity prices and weather information in kannada language dialects |
| topic | noise elimination ivrs asr accuracy spoken query system |
| url | https://doi.org/10.1515/jisys-2018-0120 |
| work_keys_str_mv | AT yadavathimmarajag improvementsinspokenquerysystemtoaccesstheagriculturalcommoditypricesandweatherinformationinkannadalanguagedialects AT jayannahs improvementsinspokenquerysystemtoaccesstheagriculturalcommoditypricesandweatherinformationinkannadalanguagedialects |