@article{BayerlGerczukBatlineretal.2023, author = {Bayerl, Sebastian P. and Gerczuk, Maurice and Batliner, Anton and Bergler, Christian and Amiriparian, Shahin and Schuller, Bj{\"o}rn and N{\"o}th, Elmar and Riedhammer, Korbinian}, title = {Classification of Stuttering - The ComParE challenge and beyond}, series = {Computer Speech \& Language}, volume = {81}, journal = {Computer Speech \& Language}, doi = {10.1016/j.csl.2023.101519}, pages = {20}, year = {2023}, abstract = {The ACM Multimedia 2022 Computational Paralinguistics Challenge (ComParE) featured a sub-challenge on the classification of stuttering in order to bring attention to this important topic and engage a wider research community. Stuttering is a complex speech disorder characterized by blocks, prolongations of sounds and syllables, and repetitions of sounds and words. Accurately classifying the symptoms of stuttering has implications for the development of self-help tools and specialized automatic speech recognition systems (ASR) that can handle atypical speech patterns. This paper provides a review of the challenge contributions and improves upon them with new state-of-the-art classification results for the KSF-C dataset, and explores cross-language training to demonstrate the potential of datasets in multiple languages. To facilitate further research and reproducibility, the full KSF-C dataset, including test-set labels, is also released.}, language = {en} } @inproceedings{SchullerBatlinerAmiriparianetal.2022, author = {Schuller, Bj{\"o}rn and Batliner, Anton and Amiriparian, Shahin and Bergler, Christian and Gerczuk, Maurice and Holz, Natalie and Larrouy-Maestri, Pauline and Bayerl, Sebastian P. and Riedhammer, Korbinian and Mallol-Ragolta, Adria and Pateraki, Maria and Coppock, Harry and Kiskin, Ivan and Sinka, Marianne and Roberts, Stephen}, title = {The ACM Multimedia 2022 Computational Paralinguistics Challenge}, doi = {10.1145/3503161.3551591}, pages = {7120-7124}, year = {2022}, abstract = {The ACM Multimedia 2022 Computational Paralinguistics Challenge addresses four different problems for the first time in a research competition under well-defined conditions: In the Vocalisations and Stuttering Sub-Challenges, a classification on human non-verbal vocalisations and speech has to be made; the Activity Sub-Challenge aims at beyond-audio human activity recognition from smartwatch sensor data; and in the Mosquitoes Sub-Challenge, mosquitoes need to be detected. We describe the Sub-Challenges, baseline feature extraction, and classifiers based on the 'usual' ComParE and BoAW features, the auDeep toolkit, and deep feature extraction from pre-trained CNNs using the DeepSpectrum toolkit; in addition, we add end-to-end sequential modelling, and a log-mel-128-BNN.}, language = {en} }