The INTERSPEECH 2016 Computational Paralinguistics Challenge addresses three different problems for the first time in research competition under well-defined conditions: classification of deceptive vs. non-deceptive speech, the estimation of the degree of sincerity, and the identification of the native language out of eleven L1 classes of English L2 speakers. In this paper, we describe these sub-challenges, their conditions, the baseline feature extraction and classifiers, and the resulting baselines, as provided to the participants.

No abstract

Pain-related emotions are a major barrier to effective self rehabilitation in chronic pain. Automated coaching systems capable of detecting these emotions are a potential solution. This paper lays the foundation for the development of such systems by making three contributions. First, through literature reviews, an overview of how pain is expressed in chronic pain and the motivation for detecting it in physical rehabilitation is provided. Second, a fully labelled multimodal dataset (named ‘EmoPain’) containing high resolution multiple-view face videos, head mounted and room audio signals, full body 3D motion capture and electromyographic signals from back muscles is supplied. Natural unconstrained pain related facial expressions and body movement behaviours were elicited from people with chronic pain carrying out physical exercises. Both instructed and non-instructed exercises were considered to reflect traditional scenarios of physiotherapist directed therapy and home-based self-directed therapy. Two sets of labels were assigned: level of pain from facial expressions annotated by eight raters and the occurrence of six pain-related body behaviours segmented by four experts. Third, through exploratory experiments grounded in the data, the factors and challenges in the automated recognition of such expressions and behaviour are described, the paper concludes by discussing potential avenues in the context of these findings also highlighting differences for the two exercise scenarios addressed.

No abstract

Quarterly conference calls where corporate executives discuss earnings that are later found to be misreported offer an excellent test bed for determining if automated linguistic and vocalic analysis tools can identify potentially fraudulent utterances in prepared versus unscripted remarks. Earnings conference calls from one company that restated their financial reports and were accused of making misleading statements were annotated as restatement-relevant (or not) and as prepared (presentation) or unprepared (Q&A) responses. We submitted more than 1,000 utterances to automated analysis to identify distinct linguistic and vocalic features that characterize various types of utterances. Restatement-related utterances differed significantly on many vocal and linguistic dimensions. These results support the value of language and vocal features in identifying potentially fraudulent utterances and suggest important interplay between utterances that are unscripted responses rather than rehearsed statements.

Milk is a complex fluid whose proteome displays a diverse set of proteins of high abundance such as caseins and medium to low abundance whey proteins such as ß-lactoglobulin, lactoferrin, immunoglobulins, glycoproteins, peptide hormones, and enzymes. A sample preparation method that enables high reproducibility and throughput is key in reliably identifying proteins present or proteins responding to conditions such as a diet, health or genetics. Using skim milk samples from Jersey and Holstein-Friesian cows, we compared three extraction procedures which have not previously been applied to samples of cows' milk. Method A (urea) involved a simple dilution of the milk in a urea-based buffer, method B (TCA/acetone) involved a trichloroacetic acid (TCA)/acetone precipitation, and method C (methanol/chloroform) involved a tri-phasic partition method in chloroform/methanol solution. Protein assays, SDS-PAGE profiling, and trypsin digestion followed by nanoHPLC-electrospray ionization-tandem mass spectrometry (nLC-ESI-MS/MS) analyses were performed to assess their efficiency. Replicates were used at each analytical step (extraction, digestion, injection) to assess reproducibility. Mass spectrometry (MS) data are available via ProteomeXchange with identifier PXD002529. Overall 186 unique accessions, major and minor proteins, were identified with a combination of methods. Method C (methanol/chloroform) yielded the best resolved SDS-patterns and highest protein recovery rates, method A (urea) yielded the greatest number of accessions, and, of the three procedures, method B (TCA/acetone) was the least compatible of all with a wide range of downstream analytical procedures. Our results also highlighted breed differences between the proteins in milk of Jersey and Holstein-Friesian cows.

No abstract

No abstract