Zobrazeno 1 - 10
of 258
pro vyhledávání: '"Riedhammer, Korbinian"'
Autor:
Braun, Franziska, Bayerl, Sebastian P., Hönig, Florian, Lehfeld, Hartmut, Hillemacher, Thomas, Bocklet, Tobias, Riedhammer, Korbinian
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 state
Externí odkaz:
http://arxiv.org/abs/2408.15188
With the advancement of multimedia technologies, news documents and user-generated content are often represented as multiple modalities, making Multimedia Event Extraction (MEE) an increasingly important challenge. However, recent MEE methods employ
Externí odkaz:
http://arxiv.org/abs/2406.12420
Autor:
Wagner, Dominik, Bayerl, Sebastian P., Baumann, Ilja, Riedhammer, Korbinian, Nöth, Elmar, Bocklet, Tobias
Accurately detecting dysfluencies in spoken language can help to improve the performance of automatic speech and language processing components and support the development of more inclusive speech and language technologies. Inspired by the recent tre
Externí odkaz:
http://arxiv.org/abs/2406.11025
This paper explores the improvement of post-training quantization (PTQ) after knowledge distillation in the Whisper speech foundation model family. We address the challenge of outliers in weights and activation tensors, known to impede quantization q
Externí odkaz:
http://arxiv.org/abs/2406.11022
Autor:
Wagner, Dominik, Lee, Seanie, Baumann, Ilja, Seeberger, Philipp, Riedhammer, Korbinian, Bocklet, Tobias
In this work, we optimize speculative sampling for parallel hardware accelerators to improve sampling speed. We notice that substantial portions of the intermediate matrices necessary for speculative sampling can be computed concurrently. This allows
Externí odkaz:
http://arxiv.org/abs/2406.11016
Autor:
Agchar, Ismael, Baumann, Ilja, Braun, Franziska, Perez-Toro, Paula Andrea, Riedhammer, Korbinian, Trump, Sebastian, Ullrich, Martin
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. Cur
Externí odkaz:
http://arxiv.org/abs/2402.15294
Automatic summarization of mass-emergency events plays a critical role in disaster management. The second edition of CrisisFACTS aims to advance disaster summarization based on multi-stream fact-finding with a focus on web sources such as Twitter, Re
Externí odkaz:
http://arxiv.org/abs/2402.09008
User-generated information content has become an important information source in crisis situations. However, classification models suffer from noise and event-related biases which still poses a challenging task and requires sophisticated task-adaptat
Externí odkaz:
http://arxiv.org/abs/2312.11020
Autor:
Braun, Franziska, Bayerl, Sebastian P., Pérez-Toro, Paula A., Hönig, Florian, Lehfeld, Hartmut, Hillemacher, Thomas, Nöth, Elmar, Bocklet, Tobias, Riedhammer, Korbinian
Automated dementia screening enables early detection and intervention, reducing costs to healthcare systems and increasing quality of life for those affected. Depression has shared symptoms with dementia, adding complexity to diagnoses. The research
Externí odkaz:
http://arxiv.org/abs/2308.08306
Autor:
Bayerl, Sebastian P., Wagner, Dominik, Baumann, Ilja, Hönig, Florian, Bocklet, Tobias, Nöth, Elmar, Riedhammer, Korbinian
Most stuttering detection and classification research has viewed stuttering as a multi-class classification problem or a binary detection task for each dysfluency type; however, this does not match the nature of stuttering, in which one dysfluency se
Externí odkaz:
http://arxiv.org/abs/2305.19255