espnet/diar_ami_eend

End-to-end Neural Diarization (EEND) trained on AMI-headset dataset. This example could be found at egs2/ami/diar1.

Configurations:

• Use ESPNet's default frontend to extract features. The sampling rate is 8000 Hz, with a frame length of 25 ms and a frame shift of 10 ms. The frontend extracts 23 log-scaled Mel-filterbanks.
• Follow the frame concatenation and subsampling strategy described in paper [[2]]. Each frame is concatenated with the preceding and following 7 frames, followed by subsampling with a factor of 10. As a result, a 345-dimensional acoustic feature (23 × 15) is extracted for each 100 ms.
• Training and testing are performed exclusively on data with 4 speakers.
• Use 4 layer stacked Transformer encoder, each outputs 256-dimensional frame-wise embeddings.
• The training process spans 500 epochs.
• Detailed configurations are defined in exp/diar/train_diar_diar_raw/config.yaml.

RESULTS

Environments

• date: Thu Dec 19 22:03:53 EST 2024
• python version: 3.11.10 (main, Oct 3 2024, 07:29:13) [GCC 11.2.0]
• espnet version: espnet 202409
• pytorch version: pytorch 2.4.0
• Git hash: c12b3d59ca4fd8847edf274e56a1716474d2a30e
  • Commit date: Thu Dec 19 21:58:26 2024 -0500

diar_train_diar_raw

DER

diarized_test

threshold_median_collar	DER
result_th0.3_med11_collar0.0	71.73
result_th0.3_med1_collar0.0	74.62
result_th0.4_med11_collar0.0	70.10
result_th0.4_med1_collar0.0	71.98
result_th0.5_med11_collar0.0	70.57
result_th0.5_med1_collar0.0	72.44
result_th0.6_med11_collar0.0	72.64
result_th0.6_med1_collar0.0	74.63
result_th0.7_med11_collar0.0	76.52
result_th0.7_med1_collar0.0	78.41

diar_train_diar_raw

DER

diarized_dev

threshold_median_collar	DER
result_th0.3_med11_collar0.0	75.88
result_th0.3_med1_collar0.0	78.21
result_th0.4_med11_collar0.0	71.45
result_th0.4_med1_collar0.0	73.32
result_th0.5_med11_collar0.0	70.53
result_th0.5_med1_collar0.0	72.34
result_th0.6_med11_collar0.0	72.03
result_th0.6_med1_collar0.0	73.96
result_th0.7_med11_collar0.0	76.66
result_th0.7_med1_collar0.0	78.33