Investigating Reproducibility at Interspeech Conferences: A Longitudinal and Comparative Perspective
This work addresses the problem of low reproducibility in speech and language processing research, particularly for researchers and practitioners relying on open science practices, and is incremental as it builds on existing reproducibility studies.
The study investigated the reproducibility of research at Interspeech conferences by comparing source code availability across seven speech and language processing conferences, finding that Interspeech has up to 40% less source code availability than others.
Reproducibility is a key aspect for scientific advancement across disciplines, and reducing barriers for open science is a focus area for the theme of Interspeech 2023. Availability of source code is one of the indicators that facilitates reproducibility. However, less is known about the rates of reproducibility at Interspeech conferences in comparison to other conferences in the field. In order to fill this gap, we have surveyed 27,717 papers at seven conferences across speech and language processing disciplines. We find that despite having a close number of accepted papers to the other conferences, Interspeech has up to 40% less source code availability. In addition to reporting the difficulties we have encountered during our research, we also provide recommendations and possible directions to increase reproducibility for further studies.