Voice acoustical measurement of the severity of major depression

Cannizzaro, Michael S.; Harel, Brian; Reilly, Nicole; Chappell, Phillip B.; Snyder, Peter J.

doi:10.1016/j.bandc.2004.05.003

Cited by 180 publications

(126 citation statements)

References 15 publications

Supporting

Mentioning

112

Contrasting

Unclassified

Order By: Relevance

“…For research investigating differences in speech rate for pathological populations, this script may also be useful. For instance, Cannizzaro et al (2004) investigated the relation between ratings of major depression and speech rate (measured by hand) and found strong correlations. Depressed and schizophrenic patients may speak monotonously (see, e.g., Covington et al, 2005, for an overview).…”

Section: Speech Data For the Ifa Corpusmentioning

confidence: 99%

Praat script to detect syllable nuclei and measure speech rate automatically

Jong

Wempe

2009

Behavior Research Methods

439

281

View full text Add to dashboard Cite

Covington et al., 2005). However, calculating speech rate by hand is a tedious task, which is therefore often not carried out. In this article, we present a script written in the software program Praat (Boersma & Weenink, 2007) that automatically detects syllable nuclei in order to calculate speech rate. The nucleus of a syllable, also called the peak, is the central part of a syllable (most commonly, the vowel in the syllable). Locating these syllable nuclei allows for a computation of number of syllables, which can be used to calculate speech rate.According to Tavakoli and Skehan (2005), fluency is multifaceted in nature. They distinguish three different facets of fluency: breakdown fluency (number and length of pauses), speed and density per time unit (speech rate), and repair fluency (false starts and repetitions). In second language testing practice, fluency is usually a score awarded by human judges who use several aspects of fluency in their judgment. However, Cucchiarini, Strik, and Boves (2002) have shown that of several objectively measured aspects of fluency, speech rate (as measured by phonemes per time unit) is the best predictor of subjective fluency. Kormos and Dénes (2004) likewise have shown that speech rate (in terms of number of syllables per time unit) is a good predictor of subjective fluency. We conclude that, for researchers wanting to include a measure of fluency, speech rate is an important factor to take into account. However, because of time constraints, this measure is often impossible to carry out. For instance, the script presented in this article was written in order to be able to measure the speech rate of 250 participants in a corpus of over 45 h of speech, a task that would take at least 8 months of full-time work for one person to measure by hand. In the context of a large-scale research project on the correlates of speaking proficiency carried out at the University of Amsterdam (What Is Speaking Proficiency: www.hum.uva.nl/wisp), we developed two tools to measure fluency automatically. For the purpose of measuring pauses in running speech, we wrote a script in the software program Praat to automatically detect silence in speech [a simplified version of which is now incorporated in the button To TextGrid (silences) in the Praat software]. For the purpose of estimating the speech rate of speech performances, we wrote a script in Praat that automatically detects syllable nuclei to compute speech rate in terms of syllables per time unit. In this article, we will present and validate the script for detecting syllable nuclei.For automatic speech recognition, speech rate is an important factor as well. Human listeners are able to understand both fast and slow speech. Speech recognizers implemented in computers, however, perform relatively poorly when In this article, we describe a method for automatically detecting syllable nuclei in order to measure speech rate without the need for a transcription. A script written in the software program Praat (Boersma & Weenink, 2007) detects syl...

show abstract

Section: Speech Data For the Ifa Corpusmentioning

confidence: 99%

Praat script to detect syllable nuclei and measure speech rate automatically

Jong

Wempe

2009

Behavior Research Methods

439

281

View full text Add to dashboard Cite

show abstract

“…Cannizzaro et al (2004) examined the relationship between depression and speech by performing statistical analyses of different acoustic measures, including speaking rate, percent pause time, and pitch variation. Their results demonstrated that speaking rate and pitch variation had a strong correlation with the depression rating scale.…”

Section: Speech Indicatorsmentioning

confidence: 99%

A Cross-modal Review of Indicators for Depression Detection Systems

Morales¹,

Scherer²,

Levitan³

2017

Proceedings of the Fourth Workshop on Computational Linguistics And Clinical Psychology –- From Linguistic Signal to

View full text Add to dashboard Cite

Automatic detection of depression has attracted increasing attention from researchers in psychology, computer science, linguistics, and related disciplines. As a result, promising depression detection systems have been reported. This paper surveys these efforts by presenting the first cross-modal review of depression detection systems and discusses best practices and most promising approaches to this task.

show abstract

“…Such speech recording tasks take place under ideal voice recording conditions (Cannizzaro, Harel, Reilly, Chappell, & Snyder, 2004), while speech analysis is more difficult when conducted outside a controlled setting, because of so-called noisy channel effects (Janssen, Tacke, de Vries, van den Broek, Westerink, Haselager, & IJsselsteijn, 2013). Moreover, controlled speech tasks are cognitively less demanding than free speech tasks (Alpert et al, 2011).…”

Section: Computational Linguistics Speech Analysis and Mental Healtmentioning

confidence: 99%

Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality

2014

View full text Add to dashboard Cite

ii Introduction Mental health problems are among the costliest challenges we face, in every possible sense of cost. The numbers are staggering: to cite just a few, in the United States mental health spending accounted for $33 billion in 1986, $100 billion in 2003, and is projected to increase to $203 billion for 2014; some 25 million American adults will have an episode of major depression this year; and suicide is the third leading cause of death for people between 10 and 24 years old. The importance of clinical psychology as a problem space cannot be overstated.For clinical psychologists, language plays a central role in diagnosis. Indeed, many clinical instruments fundamentally rely on what is, in effect, manual annotation of patient language. Applying language technology in this domain, e.g. in language-based assessment, could potentially have an enormous impact, because many individuals are motivated to underreport psychiatric symptoms (consider active duty soldiers, for example) or lack the self-awareness to report accurately (consider individuals involved in substance abuse who do not recognize their own addiction), and because many people -e.g. those without adequate insurance or in rural areas -cannot even obtain access to a clinician who is qualified to perform a psychological evaluation. Bringing language technology to bear on these problems could potentially lead to inexpensive screening measures that could be administered by a wider array of healthcare professionals, which is particularly important since the majority of individuals who present with symptoms of mental health problems do so in a primary care physician's office. Given the burden on primary care physicians to diagnose mental health disorders in very little time, the American Academy of Family Physicians has recognized the need for diagnostic tools for physicians that are "suited to the realities of their practice".Although automated language analysis connected with mental health conditions goes back at least as far as the 1990s, it has not been a major focus for computational linguistics compared with other application domains. However, recently there has been noticable uptick in research activity on this topic. One recent shared task brings together research on the Big-5 personality traits, and another involved research on identification of emotion in suicide notes. Research has been done on language analysis in the context of, for example, autistic spectrum disorders, dementia, depression, post-partum depression, general life satisfaction , and suicide risk. This increase in attention is consistent with, and gains power from, the recent rise in computational linguistics activity connected with computational social science more broadly.With computational linguistics research on this topic moving toward critical mass, one key goal of this workshop was to bring together researchers to discuss the current state of the art, share methods, and set directions for the future. The workshop had a second goal also, though: to directly engage cli...

show abstract

Voice acoustical measurement of the severity of major depression

Cited by 180 publications

References 15 publications

Praat script to detect syllable nuclei and measure speech rate automatically

Praat script to detect syllable nuclei and measure speech rate automatically

A Cross-modal Review of Indicators for Depression Detection Systems

Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality

Contact Info

Product

Resources

About