The article presents the Deep Audio Analyzer, an open-source framework aiming to simplify the research and development process of neural speech processing pipelines. The tool is designed to support several tasks of common interest in the audio forensics field, including the creation of new tasks. Users can visualize audio features, evaluate performances on pre-trained models, and create, export and share new audio analysis workflows. The tool also improves experimental reproducibility by allowing export and sharing of pipelines.
Publication date: 3 Nov 2023
Project Page: Not provided
Paper: https://arxiv.org/pdf/2310.19081
