@inproceedings{33847, abstract = {{The scope of speech enhancement has changed from a monolithic view of single, independent tasks, to a joint processing of complex conversational speech recordings. Training and evaluation of these single tasks requires synthetic data with access to intermediate signals that is as close as possible to the evaluation scenario. As such data often is not available, many works instead use specialized databases for the training of each system component, e.g WSJ0-mix for source separation. We present a Multi-purpose Multi-Speaker Mixture Signal Generator (MMS-MSG) for generating a variety of speech mixture signals based on any speech corpus, ranging from classical anechoic mixtures (e.g., WSJ0-mix) over reverberant mixtures (e.g., SMS-WSJ) to meeting-style data. Its highly modular and flexible structure allows for the simulation of diverse environments and dynamic mixing, while simultaneously enabling an easy extension and modification to generate new scenarios and mixture types. These meetings can be used for prototyping, evaluation, or training purposes. We provide example evaluation data and baseline results for meetings based on the WSJ corpus. Further, we demonstrate the usefulness for realistic scenarios by using MMS-MSG to provide training data for the LibriCSS database.}}, author = {{Cord-Landwehr, Tobias and von Neumann, Thilo and Boeddeker, Christoph and Haeb-Umbach, Reinhold}}, booktitle = {{2022 International Workshop on Acoustic Signal Enhancement (IWAENC)}}, location = {{Bamberg}}, title = {{{MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator}}}, year = {{2022}}, } @inproceedings{33807, author = {{Gburrek, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, booktitle = {{ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}}, publisher = {{IEEE}}, title = {{{On Synchronization of Wireless Acoustic Sensor Networks in the Presence of Time-Varying Sampling Rate Offsets and Speaker Changes}}}, doi = {{10.1109/icassp43922.2022.9746284}}, year = {{2022}}, } @article{33451, abstract = {{We present an approach to automatically generate semantic labels for real recordings of automotive range-Doppler (RD) radar spectra. Such labels are required when training a neural network for object recognition from radar data. The automatic labeling approach rests on the simultaneous recording of camera and lidar data in addition to the radar spectrum. By warping radar spectra into the camera image, state-of-the-art object recognition algorithms can be applied to label relevant objects, such as cars, in the camera image. The warping operation is designed to be fully differentiable, which allows backpropagating the gradient computed on the camera image through the warping operation to the neural network operating on the radar data. As the warping operation relies on accurate scene flow estimation, we further propose a novel scene flow estimation algorithm which exploits information from camera, lidar and radar sensors. The proposed scene flow estimation approach is compared against a state-of-the-art scene flow algorithm, and it outperforms it by approximately 30% w.r.t. mean average error. The feasibility of the overall framework for automatic label generation for RD spectra is verified by evaluating the performance of neural networks trained with the proposed framework for Direction-of-Arrival estimation.}}, author = {{Grimm, Christopher and Fei, Tai and Warsitz, Ernst and Farhoud, Ridha and Breddermann, Tobias and Haeb-Umbach, Reinhold}}, journal = {{IEEE Transactions on Vehicular Technology}}, number = {{9}}, pages = {{9435--9449}}, title = {{{Warping of Radar Data Into Camera Image for Cross-Modal Supervision in Automotive Applications}}}, doi = {{10.1109/TVT.2022.3182411}}, volume = {{71}}, year = {{2022}}, } @inproceedings{33696, author = {{Wiechmann, Jana and Glarner, Thomas and Rautenberg, Frederik and Wagner, Petra and Haeb-Umbach, Reinhold}}, booktitle = {{18. Phonetik und Phonologie im deutschsprachigen Raum (P&P)}}, location = {{Bielefeld}}, title = {{{Technically enabled explaining of voice characteristics}}}, year = {{2022}}, } @inproceedings{33857, author = {{Kuhlmann, Michael and Seebauer, Fritz and Ebbers, Janek and Wagner, Petra and Haeb-Umbach, Reinhold}}, booktitle = {{Interspeech 2022}}, publisher = {{ISCA}}, title = {{{Investigation into Target Speaking Rate Adaptation for Voice Conversion}}}, doi = {{10.21437/interspeech.2022-10740}}, year = {{2022}}, } @inproceedings{33808, author = {{Gburrek, Tobias and Schmalenstroeer, Joerg and Heitkaemper, Jens and Haeb-Umbach, Reinhold}}, booktitle = {{2022 International Workshop on Acoustic Signal Enhancement (IWAENC)}}, location = {{ Bamberg, Germany }}, publisher = {{IEEE}}, title = {{{Informed vs. Blind Beamforming in Ad-Hoc Acoustic Sensor Networks for Meeting Transcription}}}, doi = {{10.1109/IWAENC53105.2022.9914772}}, year = {{2022}}, } @inproceedings{34072, abstract = {{Performing an adequate evaluation of sound event detection (SED) systems is far from trivial and is still subject to ongoing research. The recently proposed polyphonic sound detection (PSD)-receiver operating characteristic (ROC) and PSD score (PSDS) make an important step into the direction of an evaluation of SED systems which is independent from a certain decision threshold. This allows to obtain a more complete picture of the overall system behavior which is less biased by threshold tuning. Yet, the PSD-ROC is currently only approximated using a finite set of thresholds. The choice of the thresholds used in approximation, however, can have a severe impact on the resulting PSDS. In this paper we propose a method which allows for computing system performance on an evaluation set for all possible thresholds jointly, enabling accurate computation not only of the PSD-ROC and PSDS but also of other collar-based and intersection-based performance curves. It further allows to select the threshold which best fulfills the requirements of a given application. Source code is publicly available in our SED evaluation package sed_scores_eval.}}, author = {{Ebbers, Janek and Haeb-Umbach, Reinhold and Serizel, Romain}}, booktitle = {{Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}}, title = {{{Threshold Independent Evaluation of Sound Event Detection Scores}}}, year = {{2022}}, } @techreport{49113, abstract = {{In this report we present our system for the Detection and Classification of Acoustic Scenes and Events (DCASE) 2022 Challenge Task 4: Sound Event Detection in Domestic Environments 1 . As in previous editions of the Challenge, we use forward-backward convolutional recurrent neural networks (FBCRNNs) [1, 2] for weakly labeled and semi-supervised sound event detection (SED) and eventually generate strong pseudo labels for weakly labeled and unlabeled data. Then, (tag-conditioned) bidirectional CRNNs (Bi-CRNNs) [1, 2] are trained in a strongly supervised manner as our final SED models. In each of the training stages we use multiple iterations of self-training. Compared to previous editions, we improved our system performance by 1) some tweaks regarding data augmentation, pseudo labeling and inference 2) using weakly labeled AudioSet data [3] for pretraining larger networks and 3) augmenting the DESED data [4] with strongly labeled AudioSet data [5] for finetuning of the networks. Source code is publicly available at https://github.com/fgnt/pb_sed.}}, author = {{Ebbers, Janek and Haeb-Umbach, Reinhold}}, title = {{{Pre-Training And Self-Training For Sound Event Detection In Domestic Environments}}}, year = {{2022}}, } @inproceedings{33848, abstract = {{Impressive progress in neural network-based single-channel speech source separation has been made in recent years. But those improvements have been mostly reported on anechoic data, a situation that is hardly met in practice. Taking the SepFormer as a starting point, which achieves state-of-the-art performance on anechoic mixtures, we gradually modify it to optimize its performance on reverberant mixtures. Although this leads to a word error rate improvement by 7 percentage points compared to the standard SepFormer implementation, the system ends up with only marginally better performance than a PIT-BLSTM separation system, that is optimized with rather straightforward means. This is surprising and at the same time sobering, challenging the practical usefulness of many improvements reported in recent years for monaural source separation on nonreverberant data.}}, author = {{Cord-Landwehr, Tobias and Boeddeker, Christoph and von Neumann, Thilo and Zorila, Catalin and Doddipatla, Rama and Haeb-Umbach, Reinhold}}, booktitle = {{2022 International Workshop on Acoustic Signal Enhancement (IWAENC)}}, publisher = {{IEEE}}, title = {{{Monaural source separation: From anechoic to reverberant environments}}}, year = {{2022}}, } @inproceedings{33819, author = {{von Neumann, Thilo and Kinoshita, Keisuke and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach, Reinhold}}, booktitle = {{ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}}, publisher = {{IEEE}}, title = {{{SA-SDR: A Novel Loss Function for Separation of Meeting Style Data}}}, doi = {{10.1109/icassp43922.2022.9746757}}, year = {{2022}}, } @misc{33816, author = {{Gburrek, Tobias and Boeddeker, Christoph and von Neumann, Thilo and Cord-Landwehr, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}}, publisher = {{arXiv}}, title = {{{A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network}}}, doi = {{10.48550/ARXIV.2205.00944}}, year = {{2022}}, } @inproceedings{33954, author = {{Boeddeker, Christoph and Cord-Landwehr, Tobias and von Neumann, Thilo and Haeb-Umbach, Reinhold}}, booktitle = {{Interspeech 2022}}, publisher = {{ISCA}}, title = {{{An Initialization Scheme for Meeting Separation with Spatial Mixture Models}}}, doi = {{10.21437/interspeech.2022-10929}}, year = {{2022}}, } @inproceedings{33958, abstract = {{Recent speaker diarization studies showed that integration of end-to-end neural diarization (EEND) and clustering-based diarization is a promising approach for achieving state-of-the-art performance on various tasks. Such an approach first divides an observed signal into fixed-length segments, then performs {\it segment-level} local diarization based on an EEND module, and merges the segment-level results via clustering to form a final global diarization result. The segmentation is done to limit the number of speakers in each segment since the current EEND cannot handle a large number of speakers. In this paper, we argue that such an approach involving the segmentation has several issues; for example, it inevitably faces a dilemma that larger segment sizes increase both the context available for enhancing the performance and the number of speakers for the local EEND module to handle. To resolve such a problem, this paper proposes a novel framework that performs diarization without segmentation. However, it can still handle challenging data containing many speakers and a significant amount of overlapping speech. The proposed method can take an entire meeting for inference and perform {\it utterance-by-utterance} diarization that clusters utterance activities in terms of speakers. To this end, we leverage a neural network training scheme called Graph-PIT proposed recently for neural source separation. Experiments with simulated active-meeting-like data and CALLHOME data show the superiority of the proposed approach over the conventional methods.}}, author = {{Kinoshita, Keisuke and von Neumann, Thilo and Delcroix, Marc and Boeddeker, Christoph and Haeb-Umbach, Reinhold}}, booktitle = {{Proc. Interspeech 2022}}, pages = {{1486--1490}}, publisher = {{ISCA}}, title = {{{Utterance-by-utterance overlap-aware neural diarization with Graph-PIT}}}, doi = {{10.21437/Interspeech.2022-11408}}, year = {{2022}}, } @article{21065, abstract = {{The machine recognition of speech spoken at a distance from the microphones, known as far-field automatic speech recognition (ASR), has received a significant increase of attention in science and industry, which caused or was caused by an equally significant improvement in recognition accuracy. Meanwhile it has entered the consumer market with digital home assistants with a spoken language interface being its most prominent application. Speech recorded at a distance is affected by various acoustic distortions and, consequently, quite different processing pipelines have emerged compared to ASR for close-talk speech. A signal enhancement front-end for dereverberation, source separation and acoustic beamforming is employed to clean up the speech, and the back-end ASR engine is robustified by multi-condition training and adaptation. We will also describe the so-called end-to-end approach to ASR, which is a new promising architecture that has recently been extended to the far-field scenario. This tutorial article gives an account of the algorithms used to enable accurate speech recognition from a distance, and it will be seen that, although deep learning has a significant share in the technological breakthroughs, a clever combination with traditional signal processing can lead to surprisingly effective solutions.}}, author = {{Haeb-Umbach, Reinhold and Heymann, Jahn and Drude, Lukas and Watanabe, Shinji and Delcroix, Marc and Nakatani, Tomohiro}}, journal = {{Proceedings of the IEEE}}, number = {{2}}, pages = {{124--148}}, title = {{{Far-Field Automatic Speech Recognition}}}, doi = {{10.1109/JPROC.2020.3018668}}, volume = {{109}}, year = {{2021}}, } @inproceedings{28256, author = {{Zhang, Wangyou and Boeddeker, Christoph and Watanabe, Shinji and Nakatani, Tomohiro and Delcroix, Marc and Kinoshita, Keisuke and Ochiai, Tsubasa and Kamo, Naoyuki and Haeb-Umbach, Reinhold and Qian, Yanmin}}, booktitle = {{ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}}, title = {{{End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend}}}, doi = {{10.1109/icassp39728.2021.9414464}}, year = {{2021}}, } @inproceedings{28262, author = {{Li, Chenda and Shi, Jing and Zhang, Wangyou and Subramanian, Aswin Shanmugam and Chang, Xuankai and Kamo, Naoyuki and Hira, Moto and Hayashi, Tomoki and Boeddeker, Christoph and Chen, Zhuo and Watanabe, Shinji}}, booktitle = {{2021 IEEE Spoken Language Technology Workshop (SLT)}}, title = {{{ESPnet-SE: End-To-End Speech Enhancement and Separation Toolkit Designed for ASR Integration}}}, doi = {{10.1109/slt48900.2021.9383615}}, year = {{2021}}, } @inproceedings{28261, author = {{Li, Chenda and Luo, Yi and Han, Cong and Li, Jinyu and Yoshioka, Takuya and Zhou, Tianyan and Delcroix, Marc and Kinoshita, Keisuke and Boeddeker, Christoph and Qian, Yanmin and Watanabe, Shinji and Chen, Zhuo}}, booktitle = {{2021 IEEE Spoken Language Technology Workshop (SLT)}}, title = {{{Dual-Path RNN for Long Recording Speech Separation}}}, doi = {{10.1109/slt48900.2021.9383514}}, year = {{2021}}, } @inproceedings{24000, author = {{Heitkaemper, Jens and Schmalenstroeer, Joerg and Ion, Valentin and Haeb-Umbach, Reinhold}}, booktitle = {{Speech Communication; 14th ITG-Symposium}}, pages = {{1--5}}, title = {{{A Database for Research on Detection and Enhancement of Speech Transmitted over HF links}}}, year = {{2021}}, } @inproceedings{44843, abstract = {{Unsupervised blind source separation methods do not require a training phase and thus cannot suffer from a train-test mismatch, which is a common concern in neural network based source separation. The unsupervised techniques can be categorized in two classes, those building upon the sparsity of speech in the Short-Time Fourier transform domain and those exploiting non-Gaussianity or non-stationarity of the source signals. In this contribution, spatial mixture models which fall in the first category and independent vector analysis (IVA) as a representative of the second category are compared w.r.t. their separation performance and the performance of a downstream speech recognizer on a reverberant dataset of reasonable size. Furthermore, we introduce a serial concatenation of the two, where the result of the mixture model serves as initialization of IVA, which achieves significantly better WER performance than each algorithm individually and even approaches the performance of a much more complex neural network based technique.}}, author = {{Boeddeker, Christoph and Rautenberg, Frederik and Haeb-Umbach, Reinhold}}, booktitle = {{ITG Conference on Speech Communication}}, location = {{Kiel}}, title = {{{A Comparison and Combination of Unsupervised Blind Source Separation Techniques}}}, year = {{2021}}, } @inproceedings{28259, author = {{Boeddeker, Christoph and Zhang, Wangyou and Nakatani, Tomohiro and Kinoshita, Keisuke and Ochiai, Tsubasa and Delcroix, Marc and Kamo, Naoyuki and Qian, Yanmin and Haeb-Umbach, Reinhold}}, booktitle = {{ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}}, title = {{{Convolutive Transfer Function Invariant SDR Training Criteria for Multi-Channel Reverberant Speech Separation}}}, doi = {{10.1109/icassp39728.2021.9414661}}, year = {{2021}}, }