5 citations · 11 across the 5 of their papers we have counts for
6 papers
Performance of Large Language Models in a Computer Science Degree Program
Tim Krüger, Michael Gref
Large language models such as ChatGPT-3.5 and GPT-4.0 are ubiquitous and dominate the current discourse. Their transformative capabilities have led to a paradigm shift in how we in…
A Study on the Ambiguity in Human Annotation of German Oral History Interviews for Perceived Emotion Recognition and Sentiment Analysis
Michael Gref, Nike Matthiesen, Sreenivasa Hikkal Venugopala +5
For research in audiovisual interview archives often it is not only of interest what is said but also how. Sentiment analysis and emotion recognition can help capture, categorize a…
Human and Automatic Speech Recognition Performance on German Oral History Interviews
Michael Gref, Nike Matthiesen, Christoph Schmidt +2
Automatic speech recognition systems have accomplished remarkable improvements in transcription accuracy in recent years. On some domains, models now achieve near-human performance…
Multitask Learning for Grapheme-to-Phoneme Conversion of Anglicisms in German Speech Recognition
Julia Pritzen, Michael Gref, Dietlind Zühlke +1
Anglicisms are a challenge in German speech recognition. Due to their irregular pronunciation compared to native German words, automatically generated pronunciation dictionaries of…
Multi-Staged Cross-Lingual Acoustic Model Adaption for Robust Speech Recognition in Real-World Applications -- A Case Study on German Oral History Interviews
Michael Gref, Oliver Walter, Christoph Schmidt +2
While recent automatic speech recognition systems achieve remarkable performance when large amounts of adequate, high quality annotated speech data is used for training, the same s…
Two-Staged Acoustic Modeling Adaption for Robust Speech Recognition by the Example of German Oral History Interviews
Michael Gref, Christoph Schmidt, Sven Behnke +1
In automatic speech recognition, often little training data is available for specific challenging tasks, but training of state-of-the-art automatic speech recognition systems requi…