@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{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}},
}

@inproceedings{23998,
  author       = {{Schmalenstroeer, Joerg and Heitkaemper, Jens and Ullmann, Joerg and Haeb-Umbach, Reinhold}},
  booktitle    = {{29th European Signal Processing Conference (EUSIPCO)}},
  pages        = {{1--5}},
  title        = {{{Open Range Pitch Tracking for Carrier Frequency Difference Estimation from HF Transmitted Speech}}},
  year         = {{2021}},
}

@article{22528,
  abstract     = {{Due to the ad hoc nature of wireless acoustic sensor networks, the position of the sensor nodes is typically unknown. This contribution proposes a technique to estimate the position and orientation of the sensor nodes from the recorded speech signals. The method assumes that a node comprises a microphone array with synchronously sampled microphones rather than a single microphone, but does not require the sampling clocks of the nodes to be synchronized. From the observed audio signals, the distances between the acoustic sources and arrays, as well as the directions of arrival, are estimated. They serve as input to a non-linear least squares problem, from which both the sensor nodes’ positions and orientations, as well as the source positions, are alternatingly estimated in an iterative process. Given one set of unknowns, i.e., either the source positions or the sensor nodes’ geometry, the other set of unknowns can be computed in closed-form. The proposed approach is computationally efficient and the first one, which employs both distance and directional information for geometry calibration in a common cost function. Since both distance and direction of arrival measurements suffer from outliers, e.g., caused by strong reflections of the sound waves on the surfaces of the room, we introduce measures to deemphasize or remove unreliable measurements. Additionally, we discuss modifications of our previously proposed deep neural network-based acoustic distance estimator, to account not only for omnidirectional sources but also for directional sources. Simulation results show good positioning accuracy and compare very favorably with alternative approaches from the literature.}},
  author       = {{Gburrek, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}},
  issn         = {{1687-4722}},
  journal      = {{EURASIP Journal on Audio, Speech, and Music Processing}},
  title        = {{{Geometry calibration in wireless acoustic sensor networks utilizing DoA and distance information}}},
  doi          = {{10.1186/s13636-021-00210-x}},
  year         = {{2021}},
}

@inproceedings{23994,
  author       = {{Gburrek, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}},
  booktitle    = {{ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}},
  title        = {{{Iterative Geometry Calibration from Distance Estimates for Wireless Acoustic Sensor Networks}}},
  doi          = {{10.1109/icassp39728.2021.9413831}},
  year         = {{2021}},
}

@inproceedings{23999,
  author       = {{Gburrek, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}},
  booktitle    = {{Speech Communication; 14th ITG-Symposium}},
  pages        = {{1--5}},
  title        = {{{On Source-Microphone Distance Estimation Using Convolutional Recurrent Neural Networks}}},
  year         = {{2021}},
}

@inproceedings{29304,
  abstract     = {{In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder and a style encoder. To foster disentanglement, we propose adversarial contrastive predictive coding. This new disentanglement method does neither need parallel data nor any supervision. We show that the proposed technique is capable of separating speaker and content traits into the two different representations and show competitive speaker-content disentanglement performance compared to other unsupervised approaches. We further demonstrate an increased robustness of the content representation against a train-test mismatch compared to spectral features, when used for phone recognition.}},
  author       = {{Ebbers, Janek and Kuhlmann, Michael and Cord-Landwehr, Tobias and Haeb-Umbach, Reinhold}},
  booktitle    = {{Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}},
  pages        = {{3860–3864}},
  title        = {{{Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations}}},
  year         = {{2021}},
}

@inproceedings{26770,
  abstract     = {{Automatic transcription of meetings requires handling of overlapped speech, which calls for continuous speech separation (CSS) systems. The uPIT criterion was proposed for utterance-level separation with neural networks and introduces the constraint that the total number of speakers must not exceed the number of output channels. When processing meeting-like data in a segment-wise manner, i.e., by separating overlapping segments independently and stitching adjacent segments to continuous output streams, this constraint has to be fulfilled for any segment. In this contribution, we show that this constraint can be significantly relaxed. We propose a novel graph-based PIT criterion, which casts the assignment of utterances to output channels in a graph coloring problem. It only requires that the number of concurrently active speakers must not exceed the number of output channels. As a consequence, the system can process an arbitrary number of speakers and arbitrarily long segments and thus can handle more diverse scenarios.
Further, the stitching algorithm for obtaining a consistent output order in neighboring segments is of less importance and can even be eliminated completely, not the least reducing the computational effort. Experiments on meeting-style WSJ data show improvements in recognition performance over using the uPIT criterion. }},
  author       = {{von Neumann, Thilo and Kinoshita, Keisuke and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach, Reinhold}},
  booktitle    = {{Interspeech 2021}},
  keywords     = {{Continuous speech separation, automatic speech recognition, overlapped speech, permutation invariant training}},
  title        = {{{Graph-PIT: Generalized Permutation Invariant Training for Continuous Separation of Arbitrary Numbers of Speakers}}},
  doi          = {{10.21437/interspeech.2021-1177}},
  year         = {{2021}},
}