Speech & natural language publications

This  paper  investigates using deep neural networks (DNN) and convolutional neural networks (CNNs) for mapping speech data into its corresponding articulatory space. 

This work investigates robust features, feature-space maximum likelihood linear regression (fMLLR) transform, and deep convolutional nets to address the problem of unseen channel and noise conditions in speech recognition.

This paper gives an in-depth presentation of the multi-microphone speech recognition system we submitted to the 3rd CHiME speech separation and recognition challenge and its extension.

We review research and development activities for in-vehicle dialog systems, examine findings, discuss key challenges, and share our visions for voice-enabled interaction and intelligent assistance for smart vehicles over the…

This article is concerned with the issue of calibration in the context of Deep Neural Network (DNN) based approaches to speaker recognition. We propose a hybrid alignment framework, which stems…

In this paper, we present the SRI system submission to the NIST OpenSAD 2015 speech activity detection (SAD) evaluation. We present results on three different development databases that we created…

In the present study, we focus exclusively on progress in developing speech recognition for the language of interest, Yoloxóchitl Mixtec (YM), an Oto-Manguean language spoken by fewer than 5000 speakers…

This article provides details of the SITW speaker recognition challenge and analysis of evaluation results. We provide an analysis of some of the top performing systems submitted during the evaluation and…

Current state-of-the-art automatic speech recognition systems are sensitive to changing acoustic conditions, which can cause significant performance degradation.

This work investigates learning acoustic units in an unsupervised manner from real-world speech data by using a cascade of an autoencoder and a Kohonen net.

The Speakers in the Wild (SITW) speaker recognition database contains hand-annotated speech samples from open-source media for the purpose of benchmarking text-independent speaker recognition technology.