Static and Dynamic Modelling for the Recognition of Non-verbal Vocalisations in Conversational Speech
نویسندگان
چکیده
Non-verbal vocalisations such as laughter, breathing, hesitation, and consent play an important role in the recognition and understanding of human conversational speech and spontaneous affect. In this contribution we discuss two different strategies for robust discrimination of such events: dynamic modelling by a broad selection of diverse acoustic Low-Level-Descriptors vs. static modelling by projection of these via statistical functionals onto a 0.6k feature space with subsequent de-correlation. As classifiers we employ Hidden Markov Models, Conditional Random Fields, and Support Vector Machines, respectively. For discussion of extensive parameter optimisation test-runs with respect to features and model topology, 2.9k non-verbals are extracted from the spontaneous Audio-Visual Interest Corpus. 80.7% accuracy can be reported with, and 92.6% without a garbage model for the discrimination of the named classes.
منابع مشابه
Comparing Non-Verbal Vocalisations in Conversational Speech Corpora
Conversations do not only consist of spoken words but they also consist of non-verbal vocalisations. Since there is no standard to define and to classify (possible) non-speech sounds the annotations for these vocalisations differ very much for various corpora of conversational speech. There seems to be agreement in the six inspected corpora that hesitation sounds and feedback vocalisations are ...
متن کاملAn investigation into vocal expressions of emotions: the roles of valence, culture, and acoustic factors
This PhD is an investigation of vocal expressions of emotions, mainly focusing on non-verbal sounds such as laughter, cries and sighs. The research examines the roles of categorical and dimensional factors, the contributions of a number of acoustic cues, and the influence of culture. A series of studies established that naive listeners can reliably identify non-verbal vocalisations of positive ...
متن کاملLaughing, Breathing, Clicking - The Prosody of Nonverbal Vocalisations
When analysing human spoken communication the focus on the linguistic side lies on speech with its verbal message, whereas the focus on the non-linguistic side usually is on the visually transported information such as gestures and facial expression. However, speech, especially in talk-in-interaction, also features numerous nonverbal vocalisations including various forms of laughter and inhalat...
متن کاملAn Investigation of Dual Task Effect on The Severity of Stuttering in School-Age Children
Objective: Stuttering is a speech disorder that occurs with frequent and abnormal disruptions in speech, such as sound repetition, sound prolongation, and sound or airflow blockage. Although various hypotheses and factors have been introduced including cognitive and linguistic factors, the etiology of stuttering has not been fully understood. According to the vicious circle hypothesis, increase...
متن کاملVerbal-Auditory Skills in 5-year-Old Children of Semnan/Iran in 2006
Introduction: This research was planned to determine some verbal-auditory skills (verbal-auditory short memory and phonological awareness) that have the closest relationship with speech and language development in 5-year-old children. Method: In this descriptive cross-sectional study, 400 children of pre-school classes affiliated to Education and Welfare organizations in Semnan city were select...
متن کامل