@inproceedings{BockletRiedhammerNoeth2011, author = {Bocklet, Tobias and Riedhammer, Korbinian and N{\"o}th, Elmar}, title = {Drink and Speak: On the automatic classification of alcohol intoxination by acoustic, prosodic and text-based features}, series = {INTERSPEECH 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 2011.}, booktitle = {INTERSPEECH 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 2011.}, pages = {3213 -- 3216}, year = {2011}, abstract = {This paper focuses on the automatic detection of a person's blood level alcohol based on automatic speech processing approaches. We compare 5 different feature types with different ways of modeling. Experiments are based on the ALC corpus of IS2011 Speaker State Challenge. The classification task is restricted to the detection of a blood alcohol level above 0.5 per mille. Three feature sets are based on spectral observations: MFCCs, PLPs, TRAPS. These are modeled by GMMs. Classification is either done by a Gaussian classifier or by SVMs. In the later case classification is based on GMM-based supervectors, i.e. concatenation of GMM mean vectors. A prosodic system extracts a 292-dimensional feature vector based on a voiced-unvoiced decision. A transcription-based system makes use of text transcriptions related to phoneme durations and textual structure. We compare the stand-alone performances of these systems and combine them on score level by logistic regression. The best stand-alone performance is the transcriptionbased system which outperforms the baseline by 4.8\% on the development set. A Combination on score level gave a huge boost when the spectral-based systems were added (73.6\%). This is a relative improvement of 12.7\% to the baseline. On the test-set we achieved an UA of 68.6\% which is a significant improvement of 4.1\% to the baseline system.}, language = {en} } @inproceedings{BockletRiedhammerEysholdtetal.2013, author = {Bocklet, Tobias and Riedhammer, Korbinian and Eysholdt, Ulrich and N{\"o}th, Elmar}, title = {Automatic Phoneme Analysis in Children with Cleft Lip and Palate}, series = {2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, Canada, May 2013.}, booktitle = {2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, Canada, May 2013.}, publisher = {IEEE}, pages = {7572 -- 7576}, year = {2013}, abstract = {Cleft Lip and Palate (CLP) is among the most frequent congenital abnormalities. The impaired facial development affects the articulation, with different phonemes being impacted inhomogeneously among different patients. This work focuses on automatic phoneme analysis of children with CLP for a detailed diagnosis and therapy control. In clinical routine, the state-of-the-art evaluation is based on perceptual evaluations. Perceptual ratings act as ground-truth throughout this work, with the goal to build an automatic system that is as reliable as humans. We propose two different automatic systems focusing on modeling the articulatory space of a speaker: one system models a speaker by a GMM, the other system employs a speech recognition system and estimates fMLLR matrices for each speaker. SVR is then used to predict the perceptual ratings. We show that the fMLLR-based system is able to achieve automatic phoneme evaluation results that are in the same range as perceptual inter-rater-agreements.}, language = {en} }