The concept of speaker recognition using i-vectors was recently introduced offering state-of-the-art performance. An i-vector is a compact representation of a speaker’s utteranc...
This paper presents our work on rapid language adaptation of acoustic models based on multilingual cross-language bootstrapping and unsupervised training. We used Automatic Speech...
Deep Neural Networks (DNNs) denote multilayer artificial neural networks with more than one hidden layer and millions of free parameters. We propose a Generalized Discriminant An...
The 2- 1 sparse signal minimization problem can be solved efficiently by gradient projection. In many applications, the signal to be estimated is known to lie in some range of va...
James Hernandez, Zachary T. Harmany, Daniel Thomps...
Two proportionate af ne projection sign algorithms (APSAs) are proposed for system identi cation applications, such as network echo cancellation (NEC), where the impulse response ...