Publication

Exploiting Phoneme Similarities in Hybrid HMM-ANN Keyword Spotting

Related publications (47)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Design considerations for implantable and wearable antennas

Anja Skrivervik

This contribution gives a review of our results characterizing the propagation in lossy biological tissues. These results were mainly obtained using a simplified spherical model allowing a description in spherical wave decomposition. This model is of cours ...

IEEE2017

Word Sequence Modeling using Deep Learning

Joël Yvon Roland Legrand

For a long time, natural language processing (NLP) has relied on generative models with task specific and manually engineered features. Recently, there has been a resurgence of interest for neural networks in the machine learning community, obtaining state ...

EPFL2016

Phonological Vocoding Using Artificial Neural Networks

Philip Neil Garner, Milos Cernak

We investigate a vocoder based on artificial neural networks using a phonological speech representation. Speech decomposition is based on the phonological encoders, realised as neural network classifiers, that are trained for a particular language. The spe ...

IEEE2015

Phonological vocoding using artificial neural networks

Philip Neil Garner, Milos Cernak

Idiap2015

DNN-based Speech Synthesis: Importance of input features and training data

Philip Neil Garner

Deep neural networks (DNNs) have been recently introduced in speech synthesis. In this paper, an investigation on the importance of input features and training data on speaker dependent (SD) DNN-based speech synthesis is presented. Various aspects of the t ...

Springer Berlin Heidelberg2015

Multilingual Deep Neural Network based Acoustic Modeling For Rapid Language Adaptation

Hervé Bourlard, Petr Motlicek, David Imseng

This paper presents a study on multilingual deep neural network (DNN) based acoustic modeling and its application to new languages. We investigate the effect of phone merging on multilingual DNN in context of rapid language adaptation. Moreover, the combin ...

2014

Ising Interfaces and Free Boundary Conditions

Clément Hongler

The authors generalize the result of D. Chelkak et al. [C. R., Math., Acad. Sci. Paris 352, No. 2, 157{161 (2014; Zbl 06265643)] to the case when free boundary conditions enter the picture. The proof is related to the rigorous computation of a (dual) bound ...

2013

KL-HMM and Probabilistic Lexical Modeling

Ramya Rasipuram

Kullback-Leibler divergence based hidden Markov model (KL-HMM) is an approach where a posteriori probabilities of phonemes estimated by artificial neural networks (ANN) are modeled directly as feature observation. In this paper, we show the relation betwee ...

Idiap2013

Exploiting Phoneme Similarities in Hybrid HMM-ANN Keyword Spotting

Hynek Hermansky, Joel Praveen Pinto

We propose a technique for generating alternative models for keywords in a hybrid hidden Markov model - artificial neural network (HMM-ANN) keyword spotting paradigm. Given a base pronunciation for a keyword from the lookup dictionary, our algorithm genera ...

IDIAP2007

Semi-supervised Meeting Event Recognition with Adapted HMMs

Daniel Gatica-Perez, Samy Bengio, Dong Zhang

This paper investigates the use of unlabeled data to help labeled data for audio-visual event recognition in meetings. To deal with situations in which it is difficult to collect enough labeled data to capture event characteristics, but collecting a large ...

2005