@inproceedings{05063b0cdd8c4f9c8a699507ebdc25bd,
title = "Phonetically balanced code-mixed speech corpus for Hindi-English automatic speech recognition",
abstract = "The paper presents the development of a phonetically balanced read speech corpus of code-mixed Hindi-English. Phonetic balance in the corpus has been created by selecting sentences that contained triphones lower in frequency than a predefined threshold. The assumption with a compulsory inclusion of such rare units was that the high frequency triphones will inevitably be included. Using this metric, the Pearson's correlation coefficient of the phonetically balanced corpus with a large code-mixed reference corpus was recorded to be 0.996. The data for corpus creation has been extracted from selected sections of Hindi newspapers.These sections contain frequent English insertions in a matrix of Hindi sentence. Statistics on the phone and triphone distribution have been presented, to graphically display the phonetic likeness between the reference corpus and the corpus sampled through our method.",
author = "Ayushi Pandey and Srivastava, {B. M.L.} and Rohit Kumar and Nellore, {B. T.} and Teja, {K. S.} and Gangashetty, {S. V.}",
year = "2019",
month = jan,
day = "1",
language = "English",
series = "LREC 2018 - 11th International Conference on Language Resources and Evaluation",
publisher = "European Language Resources Association (ELRA)",
pages = "1480--1484",
editor = "Hitoshi Isahara and Bente Maegaard and Stelios Piperidis and Christopher Cieri and Thierry Declerck and Koiti Hasida and Helene Mazo and Khalid Choukri and Sara Goggi and Joseph Mariani and Asuncion Moreno and Nicoletta Calzolari and Jan Odijk and Takenobu Tokunaga",
booktitle = "LREC 2018 - 11th International Conference on Language Resources and Evaluation",
note = "11th International Conference on Language Resources and Evaluation, LREC 2018 ; Conference date: 07-05-2018 Through 12-05-2018",
}