The 2020 personalized voice trigger challenge: Open datasets, evaluation metrics, baseline system and results
The 2020 Personalized Voice Trigger Challenge (PVTC2020) addresses two different research problems in a unified setup: joint wake-up word detection with speaker verification on closetalking single microphone data and far-field multi-channel microphone array data. Specially, the second task poses an additional cross-channel matching challenge on top of the far-field condition. To simulate the real-life application scenario, the enrollment utterances are recorded from close-talking cell-phone only, while the test utterances are recorded from both the closetalking cell-phone and the far-field microphone arrays. This paper introduces our challenge setup and the released database as well as the evaluation metrics. In addition, we present a sequential two stage end-to-end neural network baseline system trained with the proposed database for speaker-dependent wake-up word detection. Results show that state-of-the-art personalized voice trigger methods are still based on the two stage design, however, this benchmark database could also be used to evaluate multi-task joint learning methods. The official website1, the open-source baseline system2 and results3 of submitted systems have been released.
