Development of ABC Systems for the 2021 Edition of NIST Speaker Recognition Evaluation
Jahangir Alam, Radek Beneš, Marián Beszédeš, Lukáš Burget, Mohamed Dahmane, Abderrahim Fathan, Hamed Ghodrati, Ondřej Glembek, Woo Hyun Kang, Pavel Matĕjka, Ladislav Mošner, Oldřich Plchot, Johan Rohdin, Anna Silnova, Themos Stafylakis
Visual Geometry Group Department of Engineering Science University of Oxford Oxford, UK
Omilia Conversational Intelligence Athens, Greece
The goal of this work is to automatically determine whether and when a word of interest is spoken by a talking face, with or without the audio. We propose a zero-shot method suitable for in the wild videos. Our key contributions are: (1) a novel convolutional architecture, KWS-Net, that uses a similarity map intermediate representation to separate the task into (i) sequence matching, and (ii) pattern detection, to decide whether the word is there and when; (2) we demonstrate that if audio is available, visual keyword spotting improves the performance both for a clean and noisy audio signal. Finally, (3) we show that our method generalises to other languages, specifically French and German, and achieves a comparable performance to English with less language specific data, by fine-tuning the network pre-trained on English. The method exceeds the performance of the previous state-of-the-art visual keyword spotting architecture when trained and tested on the same benchmark, and also that of a state-of-the-art lip reading method.