A Study of Lexical and Prosodic Cues to Segmentation in a Hindi-English Code-switched Discourse

Preeti Rao, Mugdha Pandya, Kamini Sabu, Kanhaiya Kumar, Nandini Bondale


Bilingualism, almost universal in India, routinely appears in communication in many forms. Code-switching with English is common among city dwellers with the matrix language typically being the speaker's native tongue. While a number of English words have made their way into the lexicon of Indian languages, also prevalent is insertional code-switching, i.e. switching at sentence or clause level. We consider an interesting and widely encountered variety of code-switched speech in the form of public discourses by a popular motivational speaker who uses English, probably for effect, in her Hindi language speeches. We effectively observe three categories of segments in the discourse: Hindi, Hindi with embedded English words and English. In this work, we present the characteristics of our data and investigate the discrimination potential of lexical and prosodic cues on manually segmented fragments. Lexical cues are obtained via Google Speech API for Indian English recognition. Prosodic cues computed from pitch, intensity and syllable duration estimates are found to demonstrate significant differences between Hindi and English segments, indicating more careful articulation of the embedded language.


 DOI: 10.21437/Interspeech.2018-1600

Cite as: Rao, P., Pandya, M., Sabu, K., Kumar, K., Bondale, N. (2018) A Study of Lexical and Prosodic Cues to Segmentation in a Hindi-English Code-switched Discourse. Proc. Interspeech 2018, 1918-1922, DOI: 10.21437/Interspeech.2018-1600.


@inproceedings{Rao2018,
  author={Preeti Rao and Mugdha Pandya and Kamini Sabu and Kanhaiya Kumar and Nandini Bondale},
  title={A Study of Lexical and Prosodic Cues to Segmentation in a Hindi-English Code-switched Discourse},
  year=2018,
  booktitle={Proc. Interspeech 2018},
  pages={1918--1922},
  doi={10.21437/Interspeech.2018-1600},
  url={http://dx.doi.org/10.21437/Interspeech.2018-1600}
}