Achronferry / Overlapping_speaker_segmentation_using_multiple_hypothesis_tracking_of_fundamental_frequency

Code for 'Overlapping speaker segmentation using multiple hypothesis tracking of fundamental frequency'

A. Hogg, C. Evers, A. Moore and P. Naylor: Overlapping Speaker Segmentation using Multiple Hypothesis Tracking of Fundamental Frequency. In: Proc. IEEE/ACM Transactions on Audio Speech and Language Processing, 2021.

Results

Please find a full table of results for 24 meetings on the AMI corpus here: Results Table

Citation

Please use the following citation: https://ieeexplore.ieee.org/document/9381673

@ARTICLE{Hogg2021,
  author={A. O. T. {Hogg} and C. {Evers} and A. H. {Moore} and P. A. {Naylor}},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, 
  title={Overlapping speaker segmentation using multiple hypothesis tracking of fundamental frequency}, 
  year={2021},
  volume={},
  number={},
  pages={1-1},
  doi={10.1109/TASLP.2021.3067161}}

Please also consider citing the following papers whose code this project utilises:

[1] C. Kim, F. Li, A. Ciptadi, and J. M. Rehg, “Multiple hypothesis tracking revisited,” in IEEE Intl. Conf. on Computer Vision (ICCV), Washington, DC, USA, 2015, pp. 4696–4704. https://github.com/jonperdomo/openmht

[2] D. M. Brookes, “VOICEBOX: A speech processing toolbox for MATLAB,” 1997. [Online]. Available: http://www.ee.ic.ac.uk/hp/staff/dmb/voicebox/voicebox.html