Vowels formants analysis allows straightforward detection of high arousal emotions

Vlasenko, Bogdan; Philippou-Hübner, David; Prylipko, Dmytro; Böck, Ronald; Siegert, Ingo; Wendemuth, Andreas

doi:10.1109/icme.2011.6012003

Cited by 35 publications

(21 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As one can see from Figure 1, the vowel-level mean values for the first and the second formants are different for depressed and non-depressed speech. As expected, the results differ for each gender; for male speakers we see displacement of mean values to the left (i. e., lower F 1) for depressed speech, as in the case with low-arousal emotional speech described in [17]. In a case of low-arousal detection based on vowel-level formant features, female and males have common tendency: average values for F 1 are shifted left for indicative vowels.…”

Section: Vowel-level Formant Analysissupporting

confidence: 58%

“…The difference in performance of the VL-Formants between the genders is larger than expected but not completely unsurprising. Gender difference in formant difference have been reported for both emotional speech [17] and depression [8].…”

Section: Resultsmentioning

confidence: 99%

“…This result is supported, in part, by studies which show the usefulness of performing gender dependent classification when using formant and spectral features [14,15]. Such results are not unexpected; formant distributions are expected to differ between genders due to physiological differences and variations in emotionality [16,17]. Whilst there are some evidences for differentiation in depression symptoms between men and women (e. g., appetite and weight [18]), possible potential acoustic differences have received very little attention.…”

Section: Introductionmentioning

confidence: 85%

“…This is also demonstrated by [20] who shows that the combined performance of a gender-dependent recogniser is better than that of a gender-independent. In [17], the authors described a gender-dependent analysis of vowel-level formants for straight-forward classification of emotional arousal.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Implementing Gender-Dependent Vowel-Level Analysis for Boosting Speech-Based Depression Recognition

et al. 2017

Self Cite

View full text Add to dashboard Cite

Whilst studies on emotion recognition show that genderdependent analysis can improve emotion classification performance, the potential differences in the manifestation of depression between male and female speech have yet to be fully explored. This paper presents a qualitative analysis of phonetically aligned acoustic features to highlight differences in the manifestation of depression. Gender-dependent analysis with phonetically aligned gender-dependent features are used for speech-based depression recognition. The presented experimental study reveals gender differences in the effect of depression on vowel-level features. Considering the experimental study, we also show that a small set of knowledge-driven gender-dependent vowel-level features can outperform state-of-the-art turn-level acoustic features when performing a binary depressed speech recognition task. A combination of these preselected gender-dependent vowel-level features with turn-level standardised openSMILE features results in additional improvement for depression recognition.

show abstract

Section: Vowel-level Formant Analysissupporting

confidence: 58%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 85%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Implementing Gender-Dependent Vowel-Level Analysis for Boosting Speech-Based Depression Recognition

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, since smart home systems for AAL often concern distress situations, it is unclear whether distress voice will challenge the applicability of these system. Speech signal contains linguistic information but it may be influenced by the health, the social status and the emotional state [61] [62]. Recent studies suggests that ASR performance decreases in case of emotional speech [63][64], however it is still an under-researched area.…”

Section: Smart Home and Aalmentioning

confidence: 99%

On Distant Speech Recognition for Home Automation

2015

View full text Add to dashboard Cite

Abstract. In the framework of Ambient Assisted Living, home automation may be a solution for helping elderly people living alone at home. This study is part of the Sweet-Home project which aims at developing a new home automation system based on voice command to improve support and well-being of people in loss of autonomy. The goal of the study is vocal order recognition with a focus on two aspects: distance speech recognition and sentence spotting. Several ASR techniques were evaluated on a realistic corpus acquired in a 4-room flat equipped with microphones set in the ceiling. This distant speech French corpus was recorded with 21 speakers who acted scenarios of activities of daily living. Techniques acting at the decoding stage, such as our novel approach called Driven Decoding Algorithm (DDA), gave better speech recognition results than the baseline and other approaches. This solution which uses the two best SNR channels and a priori knowledge (voice commands and distress sentences) has demonstrated an increase in recognition rate without introducing false alarms. Generally speaking, a short overview allows then to outline the research challenges that speech technologies must take up for Ambient Assisted Living and Augmentative and Alternative Communication, and the current reseach avenues in this domain.

show abstract