license: cc-by-4.0
language:
- es
base_model:
- pyannote/segmentation-3.0
library_name: pyannote-audio
pyannote-segmentation-3.0-RTVE-primary
Model Details
This system is a collection of three fine-tuned models monitoring False Alarm, Missed Detection, and Speaker Confusion, to be fused with DOVER-Lap.
Each model is a fine-tuned version of pyannote/segmentation-3.0 on the RTVE database used for Albayzin Evaluations of IberSPEECH 2024.
On the RTVE2024 test set it achives the following results (two-decimal rounding):
- Diarization Error Rate (DER): 14.98%
- False Alarm: 2.64%
- Missed Detection: 4.54%
- Speaker Confusion: 7.80%
Uses
This system is intented to be used for speaker diarization of TV shows.
Usage
The instructions to obtain the RTTM output of each model can be found here, using this configuration file
Once obtained, this script can be modified to obtain the fusion of each model's output.
Training Details
Training Data
The train.lst file includes the URIs of the training data.
Training Hyperparameters
Model:
- duration: 10.0
- max_speakers_per_chunk: 3
- max_speakers_per_frame: 2
- train_batch_size: 32
- powerset_max_classes: 2
Adam Optimizer:
- lr: 0.0001
Early Stopping:
- direction: 'min'
- max_epochs: 20
Development Data
The development.lst file includes the URIs of the development data.
Evaluation
- Forgiveness collar: 250ms
- Skip overlap: False
Testing Data & Metrics
Testing Data
The test.lst file includes the URIs of the testing data.
Metrics
Diarization Error Rate, False Alarm, Missed Detection, Speaker Confusion.
Citation
If you use these models, please cite:
BibTeX:
@inproceedings{souganidis24_iberspeech,
title = {HiTZ-Aholab Speaker Diarization System for Albayzin Evaluations of IberSPEECH 2024},
author = {Christoforos Souganidis and Gemma Meseguer and Asier Herranz and Inma {Hernáez Rioja} and Eva Navas and Ibon Saratxaga},
year = {2024},
booktitle = {IberSPEECH 2024},
pages = {327--330},
doi = {10.21437/IberSPEECH.2024-68},
}