Modeling driving performance using in-vehicle speech data from a naturalistic driving study

Jonny Kuo, Judith Lynne Charlton, Sjaanie Narelle Koppel, Christina Rudin-Brown, Suzanne Cross

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Objective: We aimed to (a) describe the development and application of an automated approach for processing in-vehicle speech data from a naturalistic driving study (NDS), (b) examine the influence of child passenger presence on driving performance, and (c) model this relationship using in-vehicle speech data. Background: Parent drivers frequently engage in child-related secondary behaviors, but the impact on driving performance is unknown. Applying automated speech-processing techniques to NDS audio data would facilitate the analysis of in-vehicle driver-child interactions and their influence on driving performance. Method: Speech activity detection and speaker diarization algorithms were applied to audio data from a Melbourne-based NDS involving 42 families. Multilevel models were developed to evaluate the effect of speech activity and the presence of child passengers on driving performance. Results: Speech activity was significantly associated with velocity and steering angle variability. Child passenger presence alone was not associated with changes in driving performance. However, speech activity in the presence of two child passengers was associated with the most variability in driving performance. Conclusion: The effects of in-vehicle speech on driving performance in the presence of child passengers appear to be heterogeneous, and multiple factors may need to be considered in evaluating their impact. This goal can potentially be achieved within large-scale NDS through the automated processing of observational data, including speech. Application: Speech-processing algorithms enable new perspectives on driving performance to be gained from existing NDS data, and variables that were once labor-intensive to process can be readily utilized in future research.
Original languageEnglish
Pages (from-to)833-845
Number of pages13
JournalHuman Factors
Volume58
Issue number6
DOIs
Publication statusPublished - 2016

Keywords

  • child passengers
  • driver distraction
  • naturalistic driving study
  • speaker diarization
  • speech activity detection

Cite this

@article{3b700bf4a32c47f4a5ee6564c65ecc7e,
title = "Modeling driving performance using in-vehicle speech data from a naturalistic driving study",
abstract = "Objective: We aimed to (a) describe the development and application of an automated approach for processing in-vehicle speech data from a naturalistic driving study (NDS), (b) examine the influence of child passenger presence on driving performance, and (c) model this relationship using in-vehicle speech data. Background: Parent drivers frequently engage in child-related secondary behaviors, but the impact on driving performance is unknown. Applying automated speech-processing techniques to NDS audio data would facilitate the analysis of in-vehicle driver-child interactions and their influence on driving performance. Method: Speech activity detection and speaker diarization algorithms were applied to audio data from a Melbourne-based NDS involving 42 families. Multilevel models were developed to evaluate the effect of speech activity and the presence of child passengers on driving performance. Results: Speech activity was significantly associated with velocity and steering angle variability. Child passenger presence alone was not associated with changes in driving performance. However, speech activity in the presence of two child passengers was associated with the most variability in driving performance. Conclusion: The effects of in-vehicle speech on driving performance in the presence of child passengers appear to be heterogeneous, and multiple factors may need to be considered in evaluating their impact. This goal can potentially be achieved within large-scale NDS through the automated processing of observational data, including speech. Application: Speech-processing algorithms enable new perspectives on driving performance to be gained from existing NDS data, and variables that were once labor-intensive to process can be readily utilized in future research.",
keywords = "child passengers, driver distraction, naturalistic driving study, speaker diarization, speech activity detection",
author = "Jonny Kuo and Charlton, {Judith Lynne} and Koppel, {Sjaanie Narelle} and Christina Rudin-Brown and Suzanne Cross",
year = "2016",
doi = "10.1177/0018720816650565",
language = "English",
volume = "58",
pages = "833--845",
journal = "Human Factors",
issn = "0018-7208",
publisher = "SAGE Publications Ltd",
number = "6",

}

Modeling driving performance using in-vehicle speech data from a naturalistic driving study. / Kuo, Jonny; Charlton, Judith Lynne; Koppel, Sjaanie Narelle; Rudin-Brown, Christina; Cross, Suzanne.

In: Human Factors, Vol. 58, No. 6, 2016, p. 833-845.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Modeling driving performance using in-vehicle speech data from a naturalistic driving study

AU - Kuo, Jonny

AU - Charlton, Judith Lynne

AU - Koppel, Sjaanie Narelle

AU - Rudin-Brown, Christina

AU - Cross, Suzanne

PY - 2016

Y1 - 2016

N2 - Objective: We aimed to (a) describe the development and application of an automated approach for processing in-vehicle speech data from a naturalistic driving study (NDS), (b) examine the influence of child passenger presence on driving performance, and (c) model this relationship using in-vehicle speech data. Background: Parent drivers frequently engage in child-related secondary behaviors, but the impact on driving performance is unknown. Applying automated speech-processing techniques to NDS audio data would facilitate the analysis of in-vehicle driver-child interactions and their influence on driving performance. Method: Speech activity detection and speaker diarization algorithms were applied to audio data from a Melbourne-based NDS involving 42 families. Multilevel models were developed to evaluate the effect of speech activity and the presence of child passengers on driving performance. Results: Speech activity was significantly associated with velocity and steering angle variability. Child passenger presence alone was not associated with changes in driving performance. However, speech activity in the presence of two child passengers was associated with the most variability in driving performance. Conclusion: The effects of in-vehicle speech on driving performance in the presence of child passengers appear to be heterogeneous, and multiple factors may need to be considered in evaluating their impact. This goal can potentially be achieved within large-scale NDS through the automated processing of observational data, including speech. Application: Speech-processing algorithms enable new perspectives on driving performance to be gained from existing NDS data, and variables that were once labor-intensive to process can be readily utilized in future research.

AB - Objective: We aimed to (a) describe the development and application of an automated approach for processing in-vehicle speech data from a naturalistic driving study (NDS), (b) examine the influence of child passenger presence on driving performance, and (c) model this relationship using in-vehicle speech data. Background: Parent drivers frequently engage in child-related secondary behaviors, but the impact on driving performance is unknown. Applying automated speech-processing techniques to NDS audio data would facilitate the analysis of in-vehicle driver-child interactions and their influence on driving performance. Method: Speech activity detection and speaker diarization algorithms were applied to audio data from a Melbourne-based NDS involving 42 families. Multilevel models were developed to evaluate the effect of speech activity and the presence of child passengers on driving performance. Results: Speech activity was significantly associated with velocity and steering angle variability. Child passenger presence alone was not associated with changes in driving performance. However, speech activity in the presence of two child passengers was associated with the most variability in driving performance. Conclusion: The effects of in-vehicle speech on driving performance in the presence of child passengers appear to be heterogeneous, and multiple factors may need to be considered in evaluating their impact. This goal can potentially be achieved within large-scale NDS through the automated processing of observational data, including speech. Application: Speech-processing algorithms enable new perspectives on driving performance to be gained from existing NDS data, and variables that were once labor-intensive to process can be readily utilized in future research.

KW - child passengers

KW - driver distraction

KW - naturalistic driving study

KW - speaker diarization

KW - speech activity detection

UR - http://www.scopus.com/inward/record.url?scp=84982812091&partnerID=8YFLogxK

U2 - 10.1177/0018720816650565

DO - 10.1177/0018720816650565

M3 - Article

VL - 58

SP - 833

EP - 845

JO - Human Factors

JF - Human Factors

SN - 0018-7208

IS - 6

ER -