Tobias Watzel

Mr. Tobias Watzel

Technical University of Munich

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 September 2020
Verified
Book Chapter
Closed access
LKLudwig Kürzinger
Ludwig Kürzinger
DWDominik Winkelbauer
Dominik Winkelbauer
LLLujun Li
Lujun Li
TWTobias Watzel
Tobias Watzel
GRGerhard Rigoll
Gerhard Rigoll

30 June 2021 in Electronics
Verified
Journal Article
Open access
PDF file
LLLujun Li
Lujun Li
Zhenxing LuZhenxing Lu
Zhenxing Lu
TWTobias Watzel
Tobias Watzel
LKLudwig Kürzinger
Ludwig Kürzinger
GRGerhard Rigoll
Gerhard Rigoll
Generative adversarial networks (GANs) have shown their superiority for speech enhancement. Nevertheless, most previous attempts had convolutional layers as the backbone, which may obscure long-range dependencies across an input sequence due to the convolution operator’s local receptive field. One popular solution is substituting recurrent neural networks (RNNs) for convolutional neural networks, but RNNs are computationally inefficient, caused by the unparallelization of their temporal iterations. To circumvent this limitation, we propose an end-to-end system for speech enhancement by applying the self-attention mechanism to GANs. We aim to achieve a system that is flexible in modeling both long-range and local interactions and can be computationally efficient at the same time. Our work is implemented in three phases: firstly, we apply the stand-alone self-attention layer in speech enhancement GANs. Secondly, we employ locality modeling on the stand-alone self-attention layer. Lastly, we investigate the functionality of the self-attention augmented convolutional speech enhancement GANs. Systematic experiment results indicate that equipped with the stand-alone self-attention layer, the system outperforms baseline systems across classic evaluation criteria with up to 95% fewer parameters. Moreover, locality modeling can be a parameter-free approach for further performance improvement, and self-attention augmentation also overtakes all baseline systems with acceptably increased parameters.

18 August 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
LLLujun Li
Lujun Li
WWwudamu wudamu
wudamu wudamu
LKLudwig Kürzinger
Ludwig Kürzinger
TWTobias Watzel
Tobias Watzel
GRGerhard Rigoll
Gerhard Rigoll
Generative adversarial networks (GANs) have recently garnered significant attention for their use in speech enhancement tasks, in which they generally process and reconstruct speech waveforms directly. Existing GANs for speech enhancement rely solely on the convolution operation, which may not accurately characterize the local information of speech signals—particularly high-frequency components. Sinc convolution has been proposed in order to allow the GAN to learn more meaningful filters in the input layer, and has achieved remarkable success in several speech signal processing tasks. Nevertheless, Sinc convolution for speech enhancement is still an under-explored research direction. This paper proposes Sinc–SEGAN, a novel generative adversarial architecture for speech enhancement, which usefully merges two powerful paradigms: Sinc convolution and the speech enhancement GAN (SEGAN). There are two highlights of the proposed system. First, it works in an end-to-end manner, overcoming the distortion caused by imperfect phase estimation. Second, the system derives a customized filter bank, tuned for the desired application compactly and efficiently. We empirically study the influence of different configurations of Sinc convolution, including the placement of the Sinc convolution layer, length of input signals, number of Sinc filters, and kernel size of Sinc convolution. Moreover, we employ a set of data augmentation techniques in the time domain, which further improve the system performance and its generalization abilities. Compared to competitive baseline systems, Sinc–SEGAN overtakes all of them with drastically reduced system parameters, demonstrating its effectiveness for practical usage, e.g., hearing aid design and cochlear implants. Additionally, data augmentation methods further boost Sinc–SEGAN performance across classic objective evaluation criteria for speech enhancement.

24 July 2019
Verified
Book Chapter
Closed access
PDF file
LKLudwig Kürzinger
Ludwig Kürzinger
TWTobias Watzel
Tobias Watzel
LLLujun Li
Lujun Li
RBRobert Baumgartner
Robert Baumgartner
GRGerhard Rigoll
Gerhard Rigoll

8 March 2021 in IEEE Access
Verified
Journal Article
Open access
LLLujun Li
Lujun Li
TWTobias Watzel
Tobias Watzel
LKLudwig Kurzinger
Ludwig Kurzinger
GRGerhard Rigoll
Gerhard Rigoll
For decades, acoustic models in speech recognition systems pivot on Hidden Markov Models (HMMs), e.g., Gaussian Mixture Model-HMM system, Deep Neural Network-HMM system, etc., and achieve remarkable results. However, the popular HMM model is the three-state left-to-right structure, without the superiority certainty. There are multiple studies on the HMM structure’s optimization, but none of them addresses this problem leveraging deep learning algorithms. For the first time, this paper proposes a new training method based on Deep Neural Fenonic Baseform Growing to optimize the HMM structure, which is concisely designed and computationally cheap. Moreover, this data-driven method customizes the HMM structure for each phone precisely without external assumptions concerning the number of states or transition patterns. Experimental results on both TIMIT and TEDliumv2 corpora indicate that the proposed HMM structure improves both the monophone system and the triphone system substantially. Besides, its adoption further improves state-of-the-art speech recognition systems with remarkably reduced parameters.

22 September 2021
Verified
Book Chapter
Closed access
PDF file
TWTobias Watzel
Tobias Watzel
LKLudwig Kürzinger
Ludwig Kürzinger
LLLujun Li
Lujun Li
GRGerhard Rigoll
Gerhard Rigoll