@inproceedings{57085,
  abstract     = {{We propose an approach for simultaneous diarization and separation of meeting data. It consists of a complex Angular Central Gaussian Mixture Model (cACGMM) for speech source separation, and a von-Mises-Fisher Mixture Model (VMFMM) for diarization in a joint statistical framework. Through the integration, both spatial and spectral information are exploited for diarization and separation. We also develop a method for counting the number of active speakers in a segment of a meeting to support block-wise processing. While the total number of speakers in a meeting may be known, it is usually not known on a per-segment level. With the proposed speaker counting, joint diarization and source separation can be done segment-by-segment, and the permutation problem across segments is solved, thus allowing for block-online processing in the future. Experimental results on the LibriCSS meeting corpus show that the integrated approach outperforms a cascaded approach of diarization and speech enhancement in terms of WER, both on a per-segment and on a per-meeting level.}},
  author       = {{Cord-Landwehr, Tobias and Boeddeker, Christoph and Haeb-Umbach, Reinhold}},
  booktitle    = {{ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}},
  keywords     = {{diarization, source separation, mixture model, meeting}},
  location     = {{Hyderabad, India}},
  title        = {{{Simultaneous Diarization and Separation of Meetings through the Integration of Statistical Mixture Models}}},
  doi          = {{10.1109/ICASSP49660.2025.10888445}},
  year         = {{2024}},
}

@article{35602,
  abstract     = {{Continuous Speech Separation (CSS) has been proposed to address speech overlaps during the analysis of realistic meeting-like conversations by eliminating any overlaps before further processing.
CSS separates a recording of arbitrarily many speakers into a small number of overlap-free output channels, where each output channel may contain speech of multiple speakers.
This is often done by applying a conventional separation model trained with Utterance-level Permutation Invariant Training (uPIT), which exclusively maps a speaker to an output channel, in sliding window approach called stitching.
Recently, we introduced an alternative training scheme called Graph-PIT that teaches the separation network to directly produce output streams in the required format without stitching.
It can handle an arbitrary number of speakers as long as never more of them overlap at the same time than the separator has output channels.
In this contribution, we further investigate the Graph-PIT training scheme.
We show in extended experiments that models trained with Graph-PIT also work in challenging reverberant conditions.
Models trained in this way are able to perform segment-less CSS, i.e., without stitching, and achieve comparable and often better separation quality than the conventional CSS with uPIT and stitching.
We simplify the training schedule for Graph-PIT with the recently proposed Source Aggregated Signal-to-Distortion Ratio (SA-SDR) loss.
It eliminates unfavorable properties of the previously used A-SDR loss and thus enables training with Graph-PIT from scratch.
Graph-PIT training relaxes the constraints w.r.t. the allowed numbers of speakers and speaking patterns which allows using a larger variety of training data.
Furthermore, we introduce novel signal-level evaluation metrics for meeting scenarios, namely the source-aggregated scale- and convolution-invariant Signal-to-Distortion Ratio (SA-SI-SDR and SA-CI-SDR), which are generalizations of the commonly used SDR-based metrics for the CSS case.}},
  author       = {{von Neumann, Thilo and Kinoshita, Keisuke and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach, Reinhold}},
  issn         = {{2329-9290}},
  journal      = {{IEEE/ACM Transactions on Audio, Speech, and Language Processing}},
  keywords     = {{Continuous Speech Separation, Source Separation, Graph-PIT, Dynamic Programming, Permutation Invariant Training}},
  pages        = {{576--589}},
  publisher    = {{Institute of Electrical and Electronics Engineers (IEEE)}},
  title        = {{{Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation Criteria}}},
  doi          = {{10.1109/taslp.2022.3228629}},
  volume       = {{31}},
  year         = {{2023}},
}

@inproceedings{11753,
  abstract     = {{This contribution describes a step-wise source counting algorithm to determine the number of speakers in an offline scenario. Each speaker is identified by a variational expectation maximization (VEM) algorithm for complex Watson mixture models and therefore directly yields beamforming vectors for a subsequent speech separation process. An observation selection criterion is proposed which improves the robustness of the source counting in noise. The algorithm is compared to an alternative VEM approach with Gaussian mixture models based on directions of arrival and shown to deliver improved source counting accuracy. The article concludes by extending the offline algorithm towards a low-latency online estimation of the number of active sources from the streaming input data.}},
  author       = {{Drude, Lukas and Chinaev, Aleksej and Tran Vu, Dang Hai and Haeb-Umbach, Reinhold}},
  booktitle    = {{14th International Workshop on Acoustic Signal Enhancement (IWAENC 2014)}},
  keywords     = {{Accuracy, Acoustics, Estimation, Mathematical model, Soruce separation, Speech, Vectors, Bayes methods, Blind source separation, Directional statistics, Number of speakers, Speaker diarization}},
  pages        = {{213--217}},
  title        = {{{Towards Online Source Counting in Speech Mixtures Applying a Variational EM for Complex Watson Mixture Models}}},
  year         = {{2014}},
}

@inproceedings{11913,
  abstract     = {{In this paper we propose to employ directional statistics in a complex vector space to approach the problem of blind speech separation in the presence of spatially correlated noise. We interpret the values of the short time Fourier transform of the microphone signals to be draws from a mixture of complex Watson distributions, a probabilistic model which naturally accounts for spatial aliasing. The parameters of the density are related to the a priori source probabilities, the power of the sources and the transfer function ratios from sources to sensors. Estimation formulas are derived for these parameters by employing the Expectation Maximization (EM) algorithm. The E-step corresponds to the estimation of the source presence probabilities for each time-frequency bin, while the M-step leads to a maximum signal-to-noise ratio (MaxSNR) beamformer in the presence of uncertainty about the source activity. Experimental results are reported for an implementation in a generalized sidelobe canceller (GSC) like spatial beamforming configuration for 3 speech sources with significant coherent noise in reverberant environments, demonstrating the usefulness of the novel modeling framework.}},
  author       = {{Tran Vu, Dang Hai and Haeb-Umbach, Reinhold}},
  booktitle    = {{IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2010)}},
  keywords     = {{array signal processing, blind source separation, blind speech separation, complex vector space, complex Watson distribution, directional statistics, expectation-maximisation algorithm, expectation maximization algorithm, Fourier transform, Fourier transforms, generalized sidelobe canceller, interference suppression, maximum signal-to-noise ratio beamformer, microphone signal, probabilistic model, spatial aliasing, spatial beamforming configuration, speech enhancement, statistical distributions}},
  pages        = {{241--244}},
  title        = {{{Blind speech separation employing directional statistics in an Expectation Maximization framework}}},
  doi          = {{10.1109/ICASSP.2010.5495994}},
  year         = {{2010}},
}