Speech & natural language publications

We address the problem of retrieving spoken information from noisy and heterogeneous audio archives using a rich system combination with a diverse set of noise-robust modules and audio characterization.

We present a neural network model to estimate articulatory trajectories from speech signals where the model was trained using synthetic speech signals generated by Haskins Laboratories’ task-dynamic model of speech…

We propose a novel approach for noise-robust speaker recognition, where the model of distortions caused by additive and convolutive noises is integrated into the i-vector extraction framework.

We explored the use of neural probabilistic language models and a TF-IDF weighted variant of Explicit Semantic Analysis.

This paper demonstrates that the proposed iterative approach is superior to conventional acoustically-referenced dynamic timing-warping procedures and provides reliable gestural annotation for speech datasets.

This presentation describes the findings of the VERUS project in using virtual world language usage behavior to identify real world demographic attributes.

This paper focuses on the identification of seven speaker trait categories from the Interspeech Speaker Trait Challenge: likeability, intelligibility, openness, conscientiousness, extraversion, agreeableness, and neuroticism.

This work proposes the use of discriminative training to construct a phoneme confusion model, which expands the phonemic index of a KWS system by adding phonemic variation to handle the…

This study examines a large corpus of online gaming chat and avatar names to explore gender differences in virtual world (VW) language use.

Knowledge of the nuisance characteristics present in the signal can be used to improve performance of the system. In some cases, the nature of these nuisance characteristics is known a…

We evaluate the effect that improved audio quality has for speaker verification performance, using a recently released full-bandwidth version of microphone data from the SRE2010 evaluation.

In this work, we extend our approach with the use of model adaptation and discriminative modeling techniques, inspired on methods that have been effective in the area of speaker identification.