Chaos and speech rhythm

Skljarov, O.P.; Bortnik, T.N.

doi:10.1109/ijcnn.2005.1556219

Cited by 4 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Voiced-speech detection and pitch frequency estimation have been done using the PRAAT software [ 25 ]. Of two commonly used ways of Poincare maps visualization: sample-scatter plots ( i.e., x i +1 versus x i ) and first-order difference plots ( i.e., x i +2 – x i +1 versus x i +1 – x i ) [ 19 ], the former is used throughout the paper.…”

Section: Introductionmentioning

confidence: 99%

Application of Poincare-Mapping of Voiced-Speech Segments for Emotion Sensing

Ślot

Bronakowski

Cichosz

et al. 2009

Sensors

View full text Add to dashboard Cite

The following paper introduces a group of novel speech-signal descriptors that reflect phoneme-pronunciation variability and that can be considered as potentially useful features for emotion sensing. The proposed group includes a set of statistical parameters of Poincare maps, derived for formant-frequency evolution and energy evolution of voiced-speech segments. Two groups of Poincare-map characteristics were considered in the research: descriptors of sample-scatter, which reflect magnitudes of phone-uttering variations and descriptors of cross-correlations that exist among samples and that evaluate consistency of variations. It has been shown that inclusion of the proposed characteristics into the pool of commonly used speech descriptors, results in a noticeable increase—at the level of 10%—in emotion sensing performance. Standard pattern recognition methodology has been adopted for evaluation of the proposed descriptors, with the assumption that three- or four-dimensional feature spaces can provide sufficient emotion sensing. Binary decision trees have been selected for data classification, as they provide with detailed information on emotion-specific discriminative power of various speech descriptors.

show abstract

Section: Introductionmentioning

confidence: 99%