I
Ignacio Lopez-Moreno
Researcher at Google
Publications - 24
Citations - 1103
Ignacio Lopez-Moreno is an academic researcher from Google. The author has contributed to research in topics: Speaker recognition & Speaker diarisation. The author has an hindex of 10, co-authored 24 publications receiving 922 citations. Previous affiliations of Ignacio Lopez-Moreno include Autonomous University of Madrid.
Papers
More filters
Proceedings ArticleDOI
Automatic language identification using deep neural networks
Ignacio Lopez-Moreno,Javier Gonzalez-Dominguez,Oldrich Plchot,David Martínez,Joaquin Gonzalez-Rodriguez,Pedro J. Moreno +5 more
TL;DR: This work adapts DNNs to the problem of identifying the language of a given spoken utterance from short-term acoustic features and finds relative improvements up to 70%, in Cavg, over the baseline system.
Proceedings ArticleDOI
Improving DNN speaker independence with I-vector inputs
TL;DR: Modifications of the basic algorithm are developed which result in significant reductions in word error rates (WERs), and the algorithms are shown to combine well with speaker adaptation by backpropagation, resulting in a 9% relative WER reduction.
Proceedings ArticleDOI
Automatic Language Identification using Long Short-Term Memory Recurrent Neural Networks
Javier Gonzalez-Dominguez,Ignacio Lopez-Moreno,Hasim Sak,Joaquin Gonzalez-Rodriguez,Pedro J. Moreno +4 more
TL;DR: This work explores the use of Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) for automatic language identification (LID) and shows LSTM RNNs achieve better performance than the best DNN system with an order of magnitude fewer parameters.
Proceedings ArticleDOI
Locally-Connected and Convolutional Neural Networks for Small Footprint Speaker Recognition
Yu-hsin Chen,Ignacio Lopez-Moreno,Tara N. Sainath,Mirko Visontai,Raziel Alvarez,Carolina Parada +5 more
TL;DR: This work compares the performance of deep Locally-Connected Networks (LCN) and Convolutional Neural Networks (CNN) for text-dependent speaker recognition and shows that both a LCN and CNN can reduce the total model footprint to 30% of the original size compared to a baseline fully-connected DNN.
Journal ArticleDOI
On the use of deep feedforward neural networks for automatic language identification
Ignacio Lopez-Moreno,Javier Gonzalez-Dominguez,David Martínez,Oldřich Plchot,Joaquin Gonzalez-Rodriguez,Pedro J. Moreno +5 more
TL;DR: This work presents a comprehensive study on the use of deep neural networks for automatic language identification that includes a detailed performance analysis for different data selection strategies and DNN architectures, and presents a novel approach that combines DNN and i-vector systems by using bottleneck features.