A Visual Analytics Approach to Finding Factors Improving Automatic Speaker Identifications

Abstract : Classification quality criteria such as precision, recall, and F-measure are generally the basis for evaluating contributions in automatic speaker recognition. Specifically, comparisons are carried out mostly via mean values estimated on a set of media. Whilst this approach is relevant to assess improvement w.r.t. the state-of-the-art, or ranking participants in the context of an automatic annotation challenge, it gives little insight to system designers in terms of cues for improving algorithms, hypothesis formulation, and evidence display. This paper presents a design study of a visual and interactive approach to analyze errors made by automatic annotation algorithms. A timeline-based tool emerged from prior steps of this study. A critical review, driven by user interviews, exposes caveats and refines user objectives. The next step of the study is then initiated by sketching designs combining elements of the current prototype to principles newly identified as relevant.
Complete list of metadatas

Contributor : Limsi Publications <>
Submitted on : Thursday, July 12, 2018 - 12:35:19 PM
Last modification on : Friday, July 19, 2019 - 2:44:02 PM


  • HAL Id : hal-01836455, version 1


Pierrick Bruneau, Mickaël Stefas, Hervé Bredin, Johann Poignant, Thomas Tamisier, et al.. A Visual Analytics Approach to Finding Factors Improving Automatic Speaker Identifications. International Conference on Multimodal Interaction, Jan 2015, Seattle, United States. ⟨hal-01836455⟩



Record views