Development and suitability of Indian languages speech database for building watson based ASR system

@article{Pandey2013DevelopmentAS,
  title={Development and suitability of Indian languages speech database for building watson based ASR system},
  author={Dipti Pandey and Tapabrata Mondal and Shyam Sunder Agrawal and Srinivas Bangalore},
  journal={2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)},
  year={2013},
  pages={1-6}
}
  • Dipti Pandey, Tapabrata Mondal, S. Bangalore
  • Published 1 November 2013
  • Linguistics, Computer Science
  • 2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE)
In this paper, we discuss our efforts in the development of Indian spoken languages corpora for building large vocabulary speech recognition systems using WATSON Toolkit. The current paper demonstrates that these corpora can be reduced to a varied degree for various phonemes by comparing the similarity among phonemes of different languages. We also discuss the design and methodology of collection of speech databases and the challenges we have faced during database creation. The experiments have… 

Figures and Tables from this paper

ASRoIL: a comprehensive survey for automatic speech recognition of Indian languages

TLDR
The purpose of this systematic survey is to sum up the best available research on automatic speech recognition of Indian languages that is done by synthesizing the results of several studies by analyzing the possible opportunities, challenges, techniques, methods and the evidence from studies.

Automatic Speech Recognition-A Literature Survey on Indian languages and Ground Work for Isolated Kannada Digit Recognition using MFCC and ANN

TLDR
An overview of Automatic Speech Recognition (ASR) in Indian Languages is presented and an efficient algorithm for isolated Kannada digits recognition is developed using Mel Frequency Cepstral Coefficients as feature vector and Artificial Neural Network as classifier.

SEECAT: ASR & Eye-tracking enabled computer-assisted translation

TLDR
The integration of automatic speech recognition (ASR) in a CAT workbench testing its real use by human translators while post-editing machine translation (MT) outputs and the use of MT combined with ASR in order to improve recognition accuracy in a workbench integrating eye-tracking functionalities to collect process-oriented information about translators’ performance are investigated.

Understanding Document Semantics from Summaries

TLDR
Two stages of LSA remodeling are presented to understand document semantics in the Indian context, specifically from Hindi text summaries to suggest that summaries of documents efficiently capture the semantic structure of documents and is an alternative to full-length documents for understanding document semantics.

References

SHOWING 1-8 OF 8 REFERENCES

HINDI SPEECH RECOGNITION SYSTEM USING HTK

TLDR
A speech recognition system for Hindi language using Hidden Markov Model Toolkit (HTK) to develop the system, which recognizes the isolated words using acoustic word model.

Hindi speech database

Jesper,"Mobile speech Hindi database, " OCOCOSDA-2011, Hshinchu- Taiwan

  • 2011

Recognition AndSynthesis in the Hindi Language

  • Proceedings of the Workshop on Speech Technology, IIT,
  • 1992

P.V.S.Rao, and S.S.Agrawal," Hindi speech database

  • Proc. Int. Conf. on Spoken Language processing(ICSLP00),
  • 2000

Hindi speech recognition under noisy conditions

  • J. Acoust. Soc
  • 2007

andChandwani , " Phonetic ally rich Hindi sentences corpus forcreation of speech database

    Text and Speech Corpora Development in Indian Languages

    • Proceedings of ICSLT-O-COCOSDA
    • 2004