@article{BayerlWagnerBaumannetal.2023, author = {Bayerl, Sebastian P. and Wagner, Dominik and Baumann, Ilja and Bocklet, Tobias and Riedhammer, Korbinian}, title = {Detecting Vocal Fatigue with Neural Embeddings}, series = {Journal of Voice}, journal = {Journal of Voice}, publisher = {Elsevier BV}, issn = {0892-1997}, doi = {10.1016/j.jvoice.2023.01.012}, pages = {11}, year = {2023}, abstract = {Vocal fatigue refers to the feeling of tiredness and weakness of voice due to extended utilization. This paper investigates the effectiveness of neural embeddings for the detection of vocal fatigue. We compare x-vectors, ECAPA-TDNN, and wav2vec 2.0 embeddings on a corpus of academic spoken English. Low-dimensional mappings of the data reveal that neural embeddings capture information about the change in vocal characteristics of a speaker during prolonged voice usage. We show that vocal fatigue can be reliably predicted using all three types of neural embeddings after 40 minutes of continuous speaking when temporal smoothing and normalization are applied to the extracted embeddings. We employ support vector machines for classification and achieve accuracy scores of 81\% using x-vectors, 85\% using ECAPA-TDNN embeddings, and 82\% using wav2vec 2.0 embeddings as input features. We obtain an accuracy score of 76\%, when the trained system is applied to a different speaker and recording environment without any adaptation.}, language = {en} } @incollection{BayerlWagnerNoethetal.2022, author = {Bayerl, Sebastian P. and Wagner, Dominik and N{\"o}th, Elmar and Bocklet, Tobias and Riedhammer, Korbinian}, title = {The Influence of Dataset Partitioning on Dysfluency Detection Systems}, series = {Text, Speech, and Dialogue}, booktitle = {Text, Speech, and Dialogue}, publisher = {Springer International Publishing}, address = {Cham}, isbn = {9783031162695}, issn = {0302-9743}, doi = {10.1007/978-3-031-16270-1_35}, pages = {423 -- 436}, year = {2022}, abstract = {This paper empirically investigates the influence of different data splits and splitting strategies on the performance of dysfluency detection systems. For this, we perform experiments using wav2vec 2.0 models with a classification head as well as support vector machines (SVM) in conjunction with the features extracted from the wav2vec 2.0 model to detect dysfluencies. We train and evaluate the systems with different non-speaker-exclusive and speaker-exclusive splits of the Stuttering Events in Podcasts (SEP-28k) dataset to shed some light on the variability of results w.r.t. to the partition method used. Furthermore, we show that the SEP-28k dataset is dominated by only a few speakers, making it difficult to evaluate. To remedy this problem, we created SEP-28k-Extended (SEP-28k-E), containing semi-automatically generated speaker and gender information for the SEP-28k corpus, and suggest different data splits, each useful for evaluating other aspects of methods for dysfluency detection.}, language = {en} } @inproceedings{WagnerBayerlMarurietal.2023, author = {Wagner, Dominik and Bayerl, Sebastian P. and Maruri, Hector A. Cordourier and Bocklet, Tobias}, title = {Generative Models for Improved Naturalness, Intelligibility, and Voicing of Whispered Speech}, series = {2022 IEEE Spoken Language Technology Workshop (SLT)}, booktitle = {2022 IEEE Spoken Language Technology Workshop (SLT)}, publisher = {IEEE}, isbn = {979-8-3503-9690-4}, doi = {10.1109/SLT54892.2023.10022796}, pages = {943 -- 948}, year = {2023}, abstract = {This work adapts two recent architectures of generative models and evaluates their effectiveness for the conversion of whispered speech to normal speech. We incorporate the normal target speech into the training criterion of vector-quantized variational autoencoders (VQ-VAEs) and Mel-GANs, thereby conditioning the systems to recover voiced speech from whispered inputs. Objective and subjective quality measures indicate that both VQ-VAEs and MelGANs can be modified to perform the conversion task. We find that the proposed approaches significantly improve the Mel cepstral distortion (MCD) metric by at least 25\% relative to a Disco-GAN baseline. Subjective listening tests suggest that the MelGAN-based system significantly improves naturalness, intelligibility, and voicing compared to the whispered input speech. A novel evaluation measure based on differences between latent speech representations also indicates that our MelGAN-based approach yields improvements relative to the baseline.}, language = {en} } @inproceedings{VasquezCorreaBockletOrozcoArroyaveetal.2020, author = {Vasquez-Correa, J. C. and Bocklet, Tobias and Orozco-Arroyave, J. R. and N{\"o}th, E.}, title = {Comparison of User Models Based on GMM-UBM and I-Vectors for Speech, Handwriting, and Gait Assessment of Parkinson's Disease Patients}, series = {ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, booktitle = {ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher = {IEEE}, isbn = {978-1-5090-6631-5}, doi = {10.1109/icassp40776.2020.9054348}, pages = {6544 -- 6548}, year = {2020}, abstract = {Parkinson's disease is a neurodegenerative disorder characterized by the presence of different motor impairments. Information from speech, handwriting, and gait signals have been considered to evaluate the neurological state of the patients. On the other hand, user models based on Gaussian mixture models - universal background models (GMMUBM) and i-vectors are considered the state-of-the-art in biometric applications like speaker verification because they are able to model specific speaker traits. This study introduces the use of GMM-UBM and i-vectors to evaluate the neurological state of Parkinson's patients using information from speech, handwriting, and gait. The results show the importance of different feature sets from each type of signal in the assessment of the neurological state of the patients.}, language = {en} } @article{SchusterAriasVergaraMuellerHoerneretal.2020, author = {Schuster, Maria and Arias-Vergara, Tom{\´a}s and M{\"u}ller-H{\"o}rner, Rainer and Winterholler, Cordula and Bocklet, Tobias}, title = {"Verstehen mich mit der Maske eigentlich noch alle?"}, series = {Geriatrie-Report}, volume = {15}, journal = {Geriatrie-Report}, number = {3}, publisher = {Springer Science and Business Media LLC}, issn = {1862-5363}, doi = {10.1007/s42090-020-0627-3}, pages = {8 -- 9}, year = {2020}, language = {de} } @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{BundschererSchmittBocklet2024, author = {Bundscherer, Maximilian and Schmitt, Thomas and Bocklet, Tobias}, title = {Machine Learning in Industrial Quality Control of Glass Bottle Prints}, doi = {10.48550/arXiv.2409.20132}, pages = {8}, year = {2024}, abstract = {In industrial manufacturing of glass bottles, quality control of bottle prints is necessary as numerous factors can negatively affect the printing process. Even minor defects in the bottle prints must be detected despite reflections in the glass or manufacturing-related deviations. In cooperation with our medium-sized industrial partner, two ML-based approaches for quality control of these bottle prints were developed and evaluated, which can also be used in this challenging scenario. Our first approach utilized different filters to supress reflections (e.g. Sobel or Canny) and image quality metrics for image comparison (e.g. MSE or SSIM) as features for different supervised classification models (e.g. SVM or k-Neighbors), which resulted in an accuracy of 84\%. The images were aligned based on the ORB algorithm, which allowed us to estimate the rotations of the prints, which may serve as an indicator for anomalies in the manufacturing process. In our second approach, we fine-tuned different pre-trained CNN models (e.g. ResNet or VGG) for binary classification, which resulted in an accuracy of 87\%. Utilizing Grad-Cam on our fine-tuned ResNet-34, we were able to localize and visualize frequently defective bottle print regions. This method allowed us to provide insights that could be used to optimize the actual manufacturing process. This paper also describes our general approach and the challenges we encountered in practice with data collection during ongoing production, unsupervised preselection, and labeling.}, language = {en} } @inproceedings{WagnerBayerlBaumannetal.2024, author = {Wagner, Dominik and Bayerl, Sebastian P. and Baumann, Ilja and Riedhammer, Korbinian and N{\"o}th, Elmar and Bocklet, Tobias}, title = {Large Language Models for Dysfluency Detection in Stuttered Speech}, doi = {10.48550/arXiv.2406.11025}, pages = {6}, year = {2024}, abstract = {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 trend towards the deployment of large language models (LLMs) as universal learners and processors of non-lexical inputs, such as audio and video, we approach the task of multi-label dysfluency detection as a language modeling problem. We present hypotheses candidates generated with an automatic speech recognition system and acoustic representations extracted from an audio encoder model to an LLM, and finetune the system to predict dysfluency labels on three datasets containing English and German stuttered speech. The experimental results show that our system effectively combines acoustic and lexical information and achieves competitive results on the multi-label stuttering detection task.}, language = {en} } @techreport{SchmittBundschererBocklet2024, author = {Schmitt, Thomas and Bundscherer, Maximilian and Bocklet, Tobias}, title = {Semmeldetector: Application of Machine Learning in Commercial Bakeries}, doi = {10.48550/arXiv.2406.04050}, pages = {6}, year = {2024}, abstract = {The Semmeldetector, is a machine learning application that utilizes object detection models to detect, classify and count baked goods in images. Our application allows commercial bakers to track unsold baked goods, which allows them to optimize production and increase resource efficiency. We compiled a dataset comprising 1151 images that distinguishes between 18 different types of baked goods to train our detection models. To facilitate model training, we used a Copy-Paste augmentation pipeline to expand our dataset. We trained the state-of-the-art object detection model YOLOv8 on our detection task. We tested the impact of different training data, model scale, and online image augmentation pipelines on model performance. Our overall best performing model, achieved an AP@0.5 of 89.1\% on our test set. Based on our results, we conclude that machine learning can be a valuable tool even for unforeseen industries like bakeries, even with very limited datasets.}, language = {en} } @article{KammerbauerSchmittBocklet2023, author = {Kammerbauer, Roland and Schmitt, Thomas and Bocklet, Tobias}, title = {Segmenting Wood Rot using Computer Vision Models}, pages = {14}, year = {2023}, abstract = {In the woodworking industry, a huge amount of effort has to be invested into the initial quality assessment of the raw material. In this study we present an AI model to detect, quantify and localize defects on wooden logs. This model aims to both automate the quality control process and provide a more consistent and reliable quality assessment. For this purpose a dataset of 1424 sample images of wood logs is created. A total of 5 annotators possessing different levels of expertise is involved in dataset creation. An inter-annotator agreement analysis is conducted to analyze the impact of expertise on the annotation task and to highlight subjective differences in annotator judgement. We explore, train and fine-tune the state-of-the-art InternImage and ONE-PEACE architectures for semantic segmentation. The best model created achieves an average IoU of 0.71, and shows detection and quantification capabilities close to the human annotators.}, language = {en} } @inproceedings{BaumannUngerWagneretal.2024, author = {Baumann, Ilja and Unger, Nicole and Wagner, Dominik and Riedhammer, Korbinian and Bocklet, Tobias}, title = {Automatic Evaluation of a Sentence Memory Test for Preschool Children}, doi = {10.21437/Interspeech.2024-2125}, pages = {5158 -- 5162}, year = {2024}, abstract = {Assessment of memory capabilities in preschool-aged children is crucial for early detection of potential speech development impairments or delays. We present an approach for the automatic evaluation of a standardized sentence memory test specifically for preschool children. Our methodology leverages automatic transcription of recited sentences and evaluation based on natural language processing techniques. We demonstrate the effectiveness of our approach on a dataset comprised of recited sentences from preschool-aged children, incorporating ratings of semantic and syntactic correctness. The best performing systems achieve an F1 score of 91.7\% for semantic correctness and 86.1\% for syntactic correctness using automatic transcripts. Our results showcase the potential of automated evaluation systems in providing reliable and efficient assessments of memory capabilities in early childhood, facilitating timely interventions and support for children with language development needs.}, language = {en} } @article{SchmittBundschererBocklet2024, author = {Schmitt, Thomas and Bundscherer, Maximilian and Bocklet, Tobias}, title = {Training a Computer Vision Model for Commercial Bakeries with Primarily Synthetic Images}, doi = {10.48550/arXiv.2409.20122}, pages = {10}, year = {2024}, abstract = {In the food industry, reprocessing returned product is a vital step to increase resource efficiency. [SBB23] presented an AI application that automates the tracking of returned bread buns. We extend their work by creating an expanded dataset comprising 2432 images and a wider range of baked goods. To increase model robustness, we use generative models pix2pix and CycleGAN to create synthetic images. We train state-of-the-art object detection model YOLOv9 and YOLOv8 on our detection task. Our overall best-performing model achieved an average precision AP@0.5 of 90.3\% on our test set.}, language = {en} }