LIUM SPKDIARIZATION: AN OPEN SOURCE TOOLKIT FOR DIARIZATION
By Sylvain Meignier, Téva Merlin. 2010
199 citations recorded by the source corpus.
Subfields: Speech & Audio, ML Systems & Hardware
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Speech & Audio
- Shinji Watanabe
- Sanjeev Khudanpur
- Daniel Povey
- Yusuke Fujita
- Vimal Manohar
- Shota Horiguchi
- Kenji Nagamatsu
- Naoyuki Kanda
In ML Systems & Hardware
- Paul Deléglise
- Yannick Estève
- Anthony Rousseau
- Sanjeev Khudanpur
- Daniel Povey
- Vimal Manohar
- Guoguo Chen
- Vassil Panayotov
Citations in the corpus
- Librispeech: An ASR corpus based on public domain audio books (2015, methodology): “As an extra precaution, in the final post-processi ng tep of the alignment processing the recordings are processed wi th the LIUM speaker diarization toolkit [20] to automatically det ect multispeaker chapters.”
- TED-LIUM: an Automatic Speech Recognition dedicated corpus (2012, methodology): “We started by generating an automatic segmentation of the audio data using our in-house speaker segmentation and clustering tool ( LIUM_SpkDiarization ), presented in (Meignier and Merlin, 2010).”
- JHU Kaldi system for Arabic MGB-3 ASR challenge using diarization, audio-transcript alignment and transfer learning (2017, methodology): “We follow this up with a linear clustering step that merges adjacent segments based on full-covariance gaussian Bayesian information criterion (∆BIC) [16].”
- End-to-End Neural Speaker Diarization with Permutation-Free Objectives (2019, methodology): “Various clustering algorithms have been adopted, such as Gaussian mixture models [11, 12], agglomerative hierarchical clustering [11, 13, 16, 17], mean shift [14], k-means [15, 18], Links [18, 22], and spectral clustering [18].”
- Enhancing the TED-LIUM Corpus with Selected Data for Language Modeling and More TED Talks (2014, methodology): “This acoustic data has been automatically segmented using our in-house tool (Meignier and Merlin, 2010) to produce 61699 speech segments.”
- An open-source state-of-the-art toolbox for broadcast news diarization (2013, methodology): “This system is widely described in [6].”
- The INTERSPEECH 2013 computational paralinguistics challenge: social signals, conflict, emotion, autism (2013, methodology): “[24] S. Meignier and T. Merlin, “LIUM SpkDiarization: An open source toolkit for diarization,” in Proc.”