Home

Awesome

EEND (End-to-End Neural Diarization)

EEND (End-to-End Neural Diarization) is a neural-network-based speaker diarization method.

The EEND extension for various number of speakers is also provided in this repository.

Install tools

Requirements

Install kaldi and python environment

cd tools
make

Test recipe (mini_librispeech)

Configuration

Data preparation

cd egs/mini_librispeech/v1
./run_prepare_shared.sh

Run training, inference, and scoring

./run.sh

CALLHOME two-speaker experiment

Configuraition

Data preparation

cd egs/callhome/v1
./run_prepare_shared.sh
# If you want to conduct 1-4 speaker experiments, run below.
# You also have to set paths to your corpora properly.
./run_prepare_shared_eda.sh

Self-attention-based model using 2-speaker mixtures

./run.sh

BLSTM-based model using 2-speaker mixtures

local/run_blstm.sh

Self-attention-based model with EDA using 1-4-speaker mixtures

./run_eda.sh

References

[1] Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi, Kenji Nagamatsu, Shinji Watanabe, " End-to-End Neural Speaker Diarization with Permutation-free Objectives," Proc. Interspeech, pp. 4300-4304, 2019

[2] Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi, Yawen Xue, Kenji Nagamatsu, Shinji Watanabe, " End-to-End Neural Speaker Diarization with Self-attention," Proc. ASRU, pp. 296-303, 2019

[3] Shota Horiguchi, Yusuke Fujita, Shinji Watanabe, Yawen Xue, Kenji Nagamatsu, " End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors," Proc. INTERSPEECH, 2020

Citation

@inproceedings{Fujita2019Interspeech,
 author={Yusuke Fujita and Naoyuki Kanda and Shota Horiguchi and Kenji Nagamatsu and Shinji Watanabe},
 title={{End-to-End Neural Speaker Diarization with Permutation-free Objectives}},
 booktitle={Interspeech},
 pages={4300--4304}
 year=2019
}