Speech & natural language publications

This paper presents experiments into the resolution of “you” in multi-party dialog, dividing this process into two tasks: distinguishing between generic and referential uses; and then, for referential uses, identifying…

We present a new modeling approach for speaker recognition that uses the maximum-likelihood linear regression (MLLR) adaptation transforms employed by a speech recognition system as features for support vector machine…

This paper introduces a new adaptation approach, fMPE-MAP, which is an extension to the original fMPE (feature minimum phone error) algorithm, with the enhanced ability in porting Gaussian models and…

We evaluate our approach by applying morpheme segmentation to the training data of a statistical machine translation (SMT) system. Experiments show that our approach is less sensitive to the availability…

Most commonly used kernels are invariant to permutations of the feature vector components. We will consider one such case, where the features are spatially related and show a way to…

We describe our continuing efforts to improve the UW-SRI-ICSI Mandarin broadcast speech recognizer.

This paper describes the system developed jointly at SRI and OGI for participation in the 2006 NIST Spoken Term Detection (STD) evaluation.

In this paper, we present our approach for using information extraction annotations to augment document retrieval for distillation. We take advantage of the fact that some of the distillation queries…

We investigate the application of the co-training learning algorithm on the sentence boundary classification problem by using lexical and prosodic information. Co-training is a semisupervised machine learning algorithm that uses…

This paper describes the IraqComm translation system that mediates and translates spontaneous conversations between an English speaker and a speaker of colloquial Iraqi Arabic.

We propose a method to improve speaker recognition lexical model performance using acoustic-prosodic information. More specifically, the lexical model is trained using duration- and pronunciation-conditioned word N-grams, simultaneously modeling lexical…