An investigation of prosody in Hindi narrative speech

Preethi Jyothi, Jennifer S Cole, Mark Allan Hasegawa-Johnson, Vandana Puri

Research output: Contribution to journalConference article

Abstract

This paper investigates how prosodic elements such as prominences and prosodic boundaries in Hindi are perceived. We approach this using data from three sources: (i) native speakers of Hindi without any linguistic expertise (ii) a linguistically trained expert in Hindi prosody and finally, (iii) classifiers trained on English for automatic prominence and boundary detection. We use speech from a corpus of Hindi narrative speech for our experiments. Our results indicate that non-expert transcribers do not have a consistent notion of prosodic prominences. However, they show considerable agreement regarding the placement of prosodic boundaries. Also, relative to the nonexpert transcribers, there is higher agreement between the expert transcriber and the automatically derived labels for prominence (and prosodic boundaries); this suggests the possibility of using classifiers for the automatic prediction of these prosodic events in Hindi.

Original languageEnglish (US)
Pages (from-to)623-627
Number of pages5
JournalProceedings of the International Conference on Speech Prosody
StatePublished - Jan 1 2014
Event7th International Conference on Speech Prosody, SP 2014 - Dublin, Ireland
Duration: May 20 2014May 23 2014

Fingerprint

expert
narrative
expertise
linguistics
event
experiment
Prosody
Prosodic Boundaries
Classifier
Experiment
Placement
Native Speaker
Expertise
Prediction

Keywords

  • Automatic labeling of prosodic events in Hindi
  • Hindi prosody
  • Perception study

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

An investigation of prosody in Hindi narrative speech. / Jyothi, Preethi; Cole, Jennifer S; Hasegawa-Johnson, Mark Allan; Puri, Vandana.

In: Proceedings of the International Conference on Speech Prosody, 01.01.2014, p. 623-627.

Research output: Contribution to journalConference article

@article{44024b924640438ea2b040b641469a91,
title = "An investigation of prosody in Hindi narrative speech",
abstract = "This paper investigates how prosodic elements such as prominences and prosodic boundaries in Hindi are perceived. We approach this using data from three sources: (i) native speakers of Hindi without any linguistic expertise (ii) a linguistically trained expert in Hindi prosody and finally, (iii) classifiers trained on English for automatic prominence and boundary detection. We use speech from a corpus of Hindi narrative speech for our experiments. Our results indicate that non-expert transcribers do not have a consistent notion of prosodic prominences. However, they show considerable agreement regarding the placement of prosodic boundaries. Also, relative to the nonexpert transcribers, there is higher agreement between the expert transcriber and the automatically derived labels for prominence (and prosodic boundaries); this suggests the possibility of using classifiers for the automatic prediction of these prosodic events in Hindi.",
keywords = "Automatic labeling of prosodic events in Hindi, Hindi prosody, Perception study",
author = "Preethi Jyothi and Cole, {Jennifer S} and Hasegawa-Johnson, {Mark Allan} and Vandana Puri",
year = "2014",
month = "1",
day = "1",
language = "English (US)",
pages = "623--627",
journal = "Proceedings of the International Conference on Speech Prosody",
issn = "2333-2042",

}

TY - JOUR

T1 - An investigation of prosody in Hindi narrative speech

AU - Jyothi, Preethi

AU - Cole, Jennifer S

AU - Hasegawa-Johnson, Mark Allan

AU - Puri, Vandana

PY - 2014/1/1

Y1 - 2014/1/1

N2 - This paper investigates how prosodic elements such as prominences and prosodic boundaries in Hindi are perceived. We approach this using data from three sources: (i) native speakers of Hindi without any linguistic expertise (ii) a linguistically trained expert in Hindi prosody and finally, (iii) classifiers trained on English for automatic prominence and boundary detection. We use speech from a corpus of Hindi narrative speech for our experiments. Our results indicate that non-expert transcribers do not have a consistent notion of prosodic prominences. However, they show considerable agreement regarding the placement of prosodic boundaries. Also, relative to the nonexpert transcribers, there is higher agreement between the expert transcriber and the automatically derived labels for prominence (and prosodic boundaries); this suggests the possibility of using classifiers for the automatic prediction of these prosodic events in Hindi.

AB - This paper investigates how prosodic elements such as prominences and prosodic boundaries in Hindi are perceived. We approach this using data from three sources: (i) native speakers of Hindi without any linguistic expertise (ii) a linguistically trained expert in Hindi prosody and finally, (iii) classifiers trained on English for automatic prominence and boundary detection. We use speech from a corpus of Hindi narrative speech for our experiments. Our results indicate that non-expert transcribers do not have a consistent notion of prosodic prominences. However, they show considerable agreement regarding the placement of prosodic boundaries. Also, relative to the nonexpert transcribers, there is higher agreement between the expert transcriber and the automatically derived labels for prominence (and prosodic boundaries); this suggests the possibility of using classifiers for the automatic prediction of these prosodic events in Hindi.

KW - Automatic labeling of prosodic events in Hindi

KW - Hindi prosody

KW - Perception study

UR - http://www.scopus.com/inward/record.url?scp=84904691178&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904691178&partnerID=8YFLogxK

M3 - Conference article

SP - 623

EP - 627

JO - Proceedings of the International Conference on Speech Prosody

JF - Proceedings of the International Conference on Speech Prosody

SN - 2333-2042

ER -