@article{AgcharBaumannBraunetal.2024, author = {Agchar, Ismael and Baumann, Ilja and Braun, Franziska and Perez-Toro, Paula Andrea and Riedhammer, Korbinian and Trump, Sebastian and Ullrich, Martin}, title = {A Survey of Music Generation in the Context of Interaction}, doi = {10.48550/arXiv.2402.15294}, pages = {47}, year = {2024}, abstract = {In recent years, machine learning, and in particular generative adversarial neural networks (GANs) and attention-based neural networks (transformers), have been successfully used to compose and generate music, both melodies and polyphonic pieces. Current research focuses foremost on style replication (e.g., generating a Bach-style chorale) or style transfer (e.g., classical to jazz) based on large amounts of recorded or transcribed music, which in turn also allows for fairly straight-forward "performance" evaluation. However, most of these models are not suitable for human-machine co-creation through live interaction, neither is clear, how such models and resulting creations would be evaluated. This article presents a thorough review of music representation, feature analysis, heuristic algorithms, statistical and parametric modelling, and human and automatic evaluation measures, along with a discussion of which approaches and models seem most suitable for live interaction.}, language = {en} } @inproceedings{BraunBayerlHoenigetal.2024, author = {Braun, Franziska and Bayerl, Sebastian and H{\"o}nig, Florian and Lehfeld, Hartmut and Hillemacher, Thomas and Bocklet, Tobias and Riedhammer, Korbinian}, title = {Infusing Acoustic Pause Context into Text-Based Dementia Assessment}, issn = {2958-1796}, doi = {10.21437/Interspeech.2024-2496}, pages = {1980-1984}, year = {2024}, abstract = {Speech pauses, alongside content and structure, offer a valuable and non-invasive biomarker for detecting dementia. This work investigates the use of pause-enriched transcripts in transformer-based language models to differentiate the cognitive states of subjects with no cognitive impairment, mild cognitive impairment, and Alzheimer's dementia based on their speech from a clinical assessment. We address three binary classification tasks: Onset, monitoring, and dementia exclusion. The performance is evaluated through experiments on a German Verbal Fluency Test and a Picture Description Test, comparing the model's effectiveness across different speech production contexts. Starting from a textual baseline, we investigate the effect of incorporation of pause information and acoustic context. We show the test should be chosen depending on the task, and similarly, lexical pause information and acoustic cross-attention contribute differently.}, language = {en} }