Sonos doesn’t make computer speakers. And despite how closely some of its speakers look the part (specifically the Era 100, as well as the older Play:1, One and One SL), that’s not how they were ...

Recently, deep neural networks that map utterances to fixed-dimensional embeddings have emerged as the state-of-the-art in speaker recognition. Our prior work introduced x-vectors, an embedding that ...

Deep learning is progressively gaining popularity as a viable alternative to i-vectors for speaker recognition. Promising results have been recently obtained with Convolutional Neural Networks (CNNs) ...