An annotation scheme for sighs in spontaneous dialogue

Sighs are non-verbal vocalisations that can carry important information about a speaker's emotional (and psychological) state. Although sighs are commonly associated with negative emotions (e.g. giving up on something, 'a sigh of despair', sadness), sighs can also be associated with positive emotions such as relief. In order to gain a better understanding of sighing as a social and affective signal in dialogue, and to advance towards an automatic classification and interpretation of the emotional content of sighs, it is necessary to learn more about the various phonetic characteristics of sighs. To that end, we developed an annotation scheme for sighs that takes the variation in phonetic form into account. Using this scheme, an oral history corpus containing emotionally-coloured dialogues was annotated for sighs. Results show that sighs can be annotated with a sufficient level of reliability (Cohen's Kappa of 0.713), and that indeed, various types of sighs can be identified as well (Cohen's Kappa between 0.637 and 0.805). Through a preliminary analysis of emotional content words, indications were found that certain types of sighs can be associated with specific emotional contexts.

[1]  Fabio Valente,et al.  The INTERSPEECH 2013 computational paralinguistics challenge: social signals, conflict, emotion, autism , 2013, INTERSPEECH.

[2]  M. Mehl,et al.  Naturalistically observed sighing and depression in rheumatoid arthritis patients: a preliminary study. , 2011, Health psychology : official journal of the Division of Health Psychology, American Psychological Association.

[3]  Jürgen Trouvain,et al.  Comparing non-verbal vocalisations in conversational speech corpora , 2012 .

[4]  Wan Li,et al.  Why do you sigh? Sigh rate during induced stress and relief. , 2009, Psychophysiology.

[5]  Randolph M Nesse,et al.  Persistent respiratory irregularity in patients with panic disorder , 2001, Biological Psychiatry.

[6]  W. Roth,et al.  Respiratory Dysregulation in Anxiety, Functional Cardiac, and Pain Disorders , 2001, Behavior modification.

[7]  Khiet P. Truong,et al.  Detection of nonverbal vocalizations using Gaussian mixture models: looking for fillers and laughter in conversational speech , 2013, INTERSPEECH.

[8]  Franciska de Jong,et al.  Croatian Memories : speech, meaning and emotions in a collection of interviews on experiences of war and trauma. , 2014, LREC 2014.

[9]  Anne H. Anderson,et al.  The Hcrc Map Task Corpus , 1991 .

[10]  Rahul Gupta,et al.  Classification of emotional content of sighs in dyadic human interactions , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[11]  Andreas Stolcke,et al.  The ICSI Meeting Corpus , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[12]  Karl Halvor Teigen,et al.  Is a sigh "just a sigh"? Sighs as emotional signals and responses to a difficult task. , 2008, Scandinavian journal of psychology.

[13]  Jean Carletta,et al.  Unleashing the killer corpus: experiences in creating the multi-everything AMI Meeting Corpus , 2007, Lang. Resour. Evaluation.

[14]  W. Roth,et al.  Physiologic instability in panic disorder and generalized anxiety disorder , 2001, Biological Psychiatry.

[15]  James W. Pennebaker,et al.  Linguistic Inquiry and Word Count (LIWC2007) , 2007 .

[16]  N. Frijda,et al.  Emotions and respiratory patterns: review and critical analysis. , 1994, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.