Day: 16 September 2019
Speech group took the first place in the VoxCeleb Speaker Recognition Challenge
Speech@FIT research group scored again in a world competition. Group members Shuai Wang and Hossein Zeinali took the first place in the VoxCeleb Speaker Recognition Challenge (VoxSRC) in Graz. The goal of this challenge is to probe how well current methods can recognize speakers in different environments in the audio-track recordings. The VoxCeleb database includes videos of several thousand celebrities and hundreds of thousands of videos - from both professionally edited and red carpet interviews as well as more casual conversational audio in which background noise, laughter, and other artefacts are observed in a range of recording environments. The results can be found HERE and HERE.