@inproceedings{GeorgesHuangBocklet2020, author = {Georges, Munir and Huang, Jonathan and Bocklet, Tobias}, title = {Compact Speaker Embedding}, doi = {10.48550/arXiv.2008.05011}, pages = {5}, year = {2020}, abstract = {Deep neural networks (DNN) have recently been widely used in speaker recognition systems, achieving state-of-the-art performance on various benchmarks. The x-vector architecture is especially popular in this research community, due to its excellent performance and manageable computational complexity. In this paper, we present the lrx-vector system, which is the low-rank factorized version of the x-vector embedding network. The primary objective of this topology is to further reduce the memory requirement of the speaker recognition system. We discuss the deployment of knowledge distillation for training the lrx-vector system and compare against low-rank factorization with SVD. On the VOiCES 2019 far-field corpus we were able to reduce the weights by 28\% compared to the full-rank x-vector system while keeping the recognition rate constant (1.83\% EER).}, language = {en} } @article{FreisingerSchneiderHerygersetal.2023, author = {Freisinger, Steffen and Schneider, Fabian and Herygers, Aaricia and Georges, Munir and Riedhammer, Korbinian}, title = {Unsupervised Multilingual Topic Segmentation of Video Lectures: What can Hierarchical Labels tell us about the Performance?}, editor = {Pesak, Krisztina}, doi = {10.21437/slate.2023-27}, year = {2023}, abstract = {The current shift from in-person to online education, e.g., through lecture videos, requires novel techniques for quickly searching for and navigating through media content. At this point, an automatic segmentation of the videos into thematically coherent units can be beneficial. Like in a book, the topics in an educational video are often structured hierarchically. There are larger topics, which in turn are divided into different subtopics. We thus propose a metric that considers the hierarchical levels in the reference segmentation when evaluating segmentation algorithms. In addition, we propose a multilingual, unsupervised topic segmentation approach and evaluate it on three datasets with English, Portuguese and German lecture videos. We achieve WindowDiff scores of up to 0.373 and show the usefulness of our hierarchical metric.}, language = {en} } @inproceedings{RanzenbergerFreierReinoldetal.2024, author = {Ranzenberger, Thomas and Freier, Carolin and Reinold, Luca and Riedhammer, Korbinian and Schneider, Fabian and Simic, Christopher and Simon, Claudia and Freisinger, Steffen and Georges, Munir and Bocklet, Tobias}, title = {A Multidisciplinary Approach to AI-based self-motivated Learning and Teaching with Large Language Models}, series = {Proceedings of DELFI Workshops 2024}, booktitle = {Proceedings of DELFI Workshops 2024}, publisher = {Gesellschaft f{\"u}r Informatik e.V.}, doi = {10.18420/delfi2024_11}, year = {2024}, abstract = {We present a learning experience platform that uses machine learning methods to support students and lecturers in self-motivated online learning and teaching processes. The platform is being developed as an agile open-source collaborative project supported by multiple universities and partners. The development is guided didactically, reviewed, and scientifically evaluated in several cycles. Transparency, data protection and the copyright compliant use of the system is a central part of the project. The system further employs large language models (LLMs). Due to privacy concerns, we utilize locally hosted LLM instances and explicitly do not rely on available cloud products. Students and lecturers can interact with an LLM-based chatbot in the current prototype. The AI-generated outputs contain cross-references to the current educational video's context, indicating if sections are based on the lectures context or world knowledge. We present the prototype and results of our qualitative evaluation from the perspective of lecturers and students.}, language = {en} } @inproceedings{RanzenbergerBockletFreisingeretal.2024, author = {Ranzenberger, Thomas and Bocklet, Tobias and Freisinger, Steffen and Georges, Munir and Glockner, Kevin and Herygers, Aaricia and Riedhammer, Korbinian and Schneider, Fabian and Simic, Christopher and Zakaria, Khabbab}, title = {EXTENDING HANS: LARGE LANGUAGE MODELS FOR QUESTION ANSWERING, SUMMARIZATION, AND TOPIC SEGMENTATION IN AN ML-BASED LEARNING EXPERIENCE PLATFORM}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, publisher = {TUPress}, address = {Dresden}, isbn = {978-3-95908-325-6}, pages = {219-224}, year = {2024}, abstract = {Abstract: The use of chatbots based on large language models (LLMs) and their impact on society are influencing our learning experience platform Hochschul Assistenz-System (HAnS). HAnS uses machine learning (ML) methods to support students and lecturers in the online learning and teaching processes [1]. This paper introduces LLM-based features available in HAnS which are using the transcript of our improved Automatic Speech Recognition (ASR) pipeline with an average transcription duration of 45 seconds and an average word error rate (WER) of 6.66\% on over 8 hours of audio data of 7 lecture videos. A LLM-based chatbot could be used to answer questions on the lecture content as the ASR transcript is provided as context. The summarization and topic segmentation uses the LLM to improve our learning experience platform. We generate multiple choice questions using the LLM and the ASR transcript as context during playback in a period of 3 minutes and display them in the HAnS frontend}, language = {en} } @inproceedings{GeorgesHuangBocklet2020, author = {Georges, Munir and Huang, Jonathan and Bocklet, Tobias}, title = {Compact Speaker Embedding: lrx-Vector}, series = {Interspeech 2020}, booktitle = {Interspeech 2020}, publisher = {ISCA}, address = {ISCA}, issn = {2958-1796}, doi = {10.21437/interspeech.2020-2106}, pages = {3236 -- 3240}, year = {2020}, abstract = {Deep neural networks (DNN) have recently been widely used in speaker recognition systems, achieving state-of-the-art performance on various benchmarks. The x-vector architecture is especially popular in this research community, due to its excellent performance and manageable computational complexity. In this paper, we present the lrx-vector system, which is the low-rank factorized version of the x-vector embedding network. The primary objective of this topology is to further reduce the memory requirement of the speaker recognition system. We discuss the deployment of knowledge distillation for training the lrx-vector system and compare against low-rank factorization with SVD. On the VOiCES 2019 far-field corpus we were able to reduce the weights by 28\% compared to the full-rank x-vector system while keeping the recognition rate constant (1.83\% EER).}, language = {en} } @inproceedings{RanzenbergerFreierReinoldetal.2024, author = {Ranzenberger, Thomas and Freier, Carolin and Reinold, Luca and Riedhammer, Korbinian and Schneider, Fabian and Simic, Christopher and Simon, Claudia and Freisinger, Steffen and Georges, Munir and Bocklet, Tobias}, title = {A Multidisciplinary Approach to AI-based self-motivated Learning and Teaching with Large Language Models}, series = {Proceedings of DELFI 2024}, booktitle = {Proceedings of DELFI 2024}, publisher = {Gesellschaft f{\"u}r Informatik e.V.}, address = {Bonn}, issn = {2944-7682}, doi = {10.18420/delfi2024_11}, pages = {133-140}, year = {2024}, abstract = {We present a learning experience platform that uses machine learning methods to support students and lecturers in self-motivated online learning and teaching processes. The platform is being developed as an agile open-source collaborative project supported by multiple universities and partners. The development is guided didactically, reviewed, and scientifically evaluated in several cycles. Transparency, data protection and the copyright compliant use of the system is a central part of the project. The system further employs large language models (LLMs). Due to privacy concerns, we utilize locally hosted LLM instances and explicitly do not rely on available cloud products. Students and lecturers can interact with an LLM-based chatbot in the current prototype. The AI-generated outputs contain cross-references to the current educational video's context, indicating if sections are based on the lectures context or world knowledge. We present the prototype and results of our qualitative evaluation from the perspective of lecturers and students.}, language = {en} }