@inproceedings{49109,
  abstract     = {{We propose a diarization system, that estimates “who spoke when” based on spatial information, to be used as a front-end of a meeting transcription system running on the signals gathered from an acoustic sensor network (ASN). Although the
spatial distribution of the microphones is advantageous, exploiting the spatial diversity for diarization and signal enhancement is challenging, because the microphones’ positions are typically unknown, and the recorded signals are initially unsynchronized in general. Here, we approach these issues by first blindly synchronizing the signals and then estimating time differences of arrival (TDOAs). The TDOA information is exploited to estimate the speakers’ activity, even in the presence of multiple speakers being simultaneously active. This speaker activity information serves as a guide for a spatial mixture model, on which basis the individual speaker’s signals are extracted via beamforming. Finally, the extracted signals are forwarded to a speech recognizer. Additionally, a novel initialization scheme for spatial mixture models based on the TDOA estimates is proposed. Experiments conducted on real recordings from the LibriWASN data set have shown that our proposed system is advantageous compared to a system using a spatial mixture model, which does not make use
of external diarization information.}},
  author       = {{Gburrek, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}},
  booktitle    = {{Proc. Asilomar Conference on Signals, Systems, and Computers}},
  keywords     = {{Diarization, time difference of arrival, ad-hoc acoustic sensor network, meeting transcription}},
  title        = {{{Spatial Diarization for Meeting Transcription with Ad-Hoc Acoustic Sensor Networks}}},
  year         = {{2023}},
}

@inproceedings{48275,
  abstract     = {{MeetEval is an open-source toolkit to evaluate  all kinds of meeting transcription systems.
It provides a unified interface for the computation of commonly used Word Error Rates (WERs), specifically cpWER, ORC WER and MIMO WER along other WER definitions.
We extend the cpWER computation by a temporal constraint to ensure that only words are identified as correct when the temporal alignment is plausible.
This leads to a better quality of the matching of the hypothesis string to the reference string that more closely resembles the actual transcription quality, and a system is penalized if it provides poor time annotations.
Since word-level timing information is often not available, we present a way to approximate exact word-level timings from segment-level timings (e.g., a sentence) and show that the approximation leads to a similar WER as a matching with exact word-level annotations.
At the same time, the time constraint leads to a speedup of the matching algorithm, which outweighs the additional overhead caused by processing the time stamps.}},
  author       = {{von Neumann, Thilo and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach, Reinhold}},
  booktitle    = {{Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments}},
  keywords     = {{Speech Recognition, Word Error Rate, Meeting Transcription}},
  location     = {{Dublin}},
  title        = {{{MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems}}},
  year         = {{2023}},
}