ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models
This toolkit addresses the need for accessible and reproducible speaker recognition tools for researchers, though it is incremental as it builds on existing methods.
The paper introduces ESPnet-SPK, a toolkit for training speaker embedding extractors, providing an open-source platform with models like x-vector and SKA-TDNN, and demonstrates its versatility by achieving a 0.39% equal error rate on the Vox1-O evaluation protocol using WavLM-Large with ECAPA-TDNN.
This paper introduces ESPnet-SPK, a toolkit designed with several objectives for training speaker embedding extractors. First, we provide an open-source platform for researchers in the speaker recognition community to effortlessly build models. We provide several models, ranging from x-vector to recent SKA-TDNN. Through the modularized architecture design, variants can be developed easily. We also aspire to bridge developed models with other domains, facilitating the broad research community to effortlessly incorporate state-of-the-art embedding extractors. Pre-trained embedding extractors can be accessed in an off-the-shelf manner and we demonstrate the toolkit's versatility by showcasing its integration with two tasks. Another goal is to integrate with diverse self-supervised learning features. We release a reproducible recipe that achieves an equal error rate of 0.39% on the Vox1-O evaluation protocol using WavLM-Large with ECAPA-TDNN.