Speech & natural language publications

This paper presents a deep neural network (DNN) to extract articulatory information from the speech signal and explores different ways to use such information in a continuous speech recognition task. 

In this work, we present robust acoustic features motivated by the knowledge gained from human speech perception and production, and demonstrate that these features provide reasonable robustness to reverberation effects…

Our goal is to locate errors in an utterance so that the dialogue manager can pose appropriate clarification questions to the users. 

We propose a novel framework for speaker recognition in which extraction of sufficient statistics for the state-of-the-art i-vector model is driven by a deep neural network (DNN) trained for automatic…

We present a system for detecting lexical stress in English words spoken by English learners.  The system uses both spectral and segmental features to detect three levels of stress for…

We investigate techniques for boosting the accuracy of automatic phonetic segmentation based on HMM acoustic-phonetic models.

This study presents an efficient and effective score calibration technique for keyword detection that is based on the logistic regression calibration approach commonly used in forensic speaker identification. 

This article proposes a new approach for contextualizing features for speaker recognition through the discrete cosine transform (DCT). 

This paper assesses the role of robust acoustic features in spoken term detection (a.k.a keyword spotting—KWS) under heavily degraded channel and noise corrupted conditions. 

We outline a general approach to automated natural-language question answering that uses first-order logic and automated deduction. Our interest is in answering queries over structured data resources

We highlight SRI’s innovations that resulted from the IARPA Biometrics Exploitation Science & Technology (BEST) and the DARPA Robust Automatic Transcription of Speech (RATS) programs, as well as SRI’s approach…

This paper investigates the effect of utterance duration to the calibration of a modern i-vector speaker recognition system with probabilistic linear discriminant analysis (PLDA) modeling.