Publications

In this paper we present an approach to close the gap between text-dependent and text-independent speaker verification performance. Text-constrained GMM-UBM systems are created using word segmentations produced by a LVCSR system on conversational speech allowing the system to focus on speaker differences over a constrained set of acoustic units. Results...

As ever greater numbers of telephone transactions are being conducted solely between a caller and an automated answering system, the need increases for software which can automatically identify and authenticate these callers without the need for an onerous speaker enrollment process. In this paper we introduce and investigate a novel...

In this paper, an adaptive approach to the enhancement of speech signals is developed based on auditory spectral change. The algorithm is motivated by sensitivity of aural biologic systems to signal dynamics, by evidence that noise is aurally masked by rapid changes in a signal, and by analogies to these...

This report describes a study effort on the state-of-the-art and lessons learned in automated, two- way, speech-to-speech translation and its potential application to military problems. The study includes and comments upon an extensive set of references on prior and current work in speech translation. The study includes recommendations on future...

This paper describes improvement to an innovative high-performance speaker recognition system. Recent experiments showed that with sufficient training data phone strings from multiple languages are exceptional features for speaker recognition. The prototype phonetic speaker recognition system used phone sequences from six languages to produce an equal error rate of 11.5%...

Phone tokenization followed by n-gram language modeling has consistently provided good results for the task of language identification. In this paper, this technique is generalized by using Gaussian mixture models as the basis for tokenizing. Performance results are presented for a system employing a GMM tokenizer in conjunction with multiple...

Development of a robust two-way real-time speech translation system exposes researchers and system developers to various challenges of machine translation (MT) and spoken language dialogues. The need for communicating in at least two different languages poses problems not present for a monolingual spoken language dialogue system, where no MT engine...

We investigate the effect of speech coding on automatic speaker recognition when training and testing conditions are matched and mismatched. Experiments used standard speech coding algorithms (GSM, G.729, G.723, MELP) and a speaker recognition system based on Gaussian mixture models adapted from a universal background model. There is little loss...

This paper presents a novel information retrieval system that includes 1) the addition of concepts to facilitate the identification of the correct word sense, 2) a natural language query interface, 3) the inclusion of weights and penalties for proper nouns that build upon the Okapi weighting scheme, and 4) a...

The NATO N4 corpus contains speech collected at naval training schools within several NATO countries. The speech utterances comprising the corpus are short, tactical transmissions typical of NATO naval communications. In this paper, we report the results of some preliminary speaker recognition experiments on the N4 corpus. We compare the...