@inproceedings{48281,
  abstract     = {{	We propose a general framework to compute the word error rate (WER) of ASR systems that process recordings containing multiple speakers at their input and that produce multiple output word sequences (MIMO).
	Such ASR systems are typically required, e.g., for meeting transcription.
	We provide an efficient implementation based on a dynamic programming search in a multi-dimensional Levenshtein distance tensor under the constraint that a reference utterance must be matched consistently with one hypothesis output. 
	This also results in an efficient implementation of the ORC WER which previously suffered from exponential complexity.
	We give an overview of commonly used WER definitions for multi-speaker scenarios and show that they are specializations of the above MIMO WER tuned to particular application scenarios. 
	We conclude with a  discussion of the pros and cons of the various WER definitions and a recommendation when to use which.}},
  author       = {{von Neumann, Thilo and Boeddeker, Christoph and Kinoshita, Keisuke and Delcroix, Marc and Haeb-Umbach, Reinhold}},
  booktitle    = {{ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}},
  keywords     = {{Word Error Rate, Meeting Recognition, Levenshtein Distance}},
  publisher    = {{IEEE}},
  title        = {{{On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems}}},
  doi          = {{10.1109/icassp49357.2023.10094784}},
  year         = {{2023}},
}