Suppose someone tells you something. Under what conditions do owe it to her accept she's said? I will call this The Question. Question raises an issue of philosophical significance. For one thing, the appears be at heart #BelieveWomen, that part #MeToo movement focusing on proper way respond allegations sexual harassment. Do we women who tell us they have been assaulted believe them? How should...

Deep speaker embedding has demonstrated state-of-the-art performance in recognition tasks. However, one potential issue with this approach is that the vectors derived from deep models tend to be non-Gaussian for each individual speaker, and non-homogeneous distributions of different speakers. These irregular can seriously impact performance, especially popular PLDA scoring method, which assumes...

This paper proposes a new method for text-dependent speaker recognition. The scheme is based on learning (what we refer to as) speaker-specific compensators for each speaker in the system. The compensator is essentially a speaker to speaker transformation which enables the recognition of the speech of one speaker through a speaker-dependent speech recognition system built for the other. Such a ...