Publications Search | Page 7 | SRI International

Toggle Menu

Publications Search

By Elizabeth Shriberg

Current speech-input systems typically use a nonspeech threshold for end-of-utterance detection. While usually sufficient for short utterances, the approach can cut speakers off during pauses in more complex utterances. We elicit personal-assistant speech (reminders, calendar entries, messaging,...

May, 2014
In Proceedings
420
By Vikramjit Mitra, Wen Wang, Andreas Kathol

Reverberation in speech degrades the performance of speech recognition systems, leading to higher word error rates.

May, 2014
In Proceedings
420
By Vikramjit Mitra

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.

May, 2014
In Proceedings
420
By Vikramjit Mitra, Wen Wang

Accurate phone-level segmentation of speech remains an important task for many subfields of speech research. We investigate techniques for boosting the accuracy of automatic phonetic segmentation based on HMM acoustic-phonetic models.

May, 2014
In Proceedings
420
By Mitchell McLaren, Nicolas Scheffer, Luciana Ferrer, Yun Lei

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

May, 2014
In Proceedings
420
By Julien van Hout, Dimitra Vergyri, Vikramjit Mitra

State-of-the-art calibration and fusion approaches for spoken term detection (STD) systems currently rely on a multi-pass approach where the scores are calibrated, then fused, and finally re-calibrated to obtain a single decision threshold across keywords.

May, 2014
In Proceedings
420
By Elizabeth Shriberg

Recent studies have shown the importance of using online videos along with textual material in educational instruction, especially for better content retention and improved concept understanding. A key question is how to select videos to maximize student engagement, particularly when there are...

May, 2014
In Proceedings
420

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.

May, 2014
In Proceedings
420

Though sparse features have produced significant gains over traditional dense features in statistical machine translation, careful feature selection and feature engineering are necessary to avoid overfitting in optimizations.

May, 2014
In Proceedings
420
By Wen Wang, Vikramjit Mitra

Accurate phone-level segmentation of speech remains an important task for many subfields of speech research.

May, 2014
In Proceedings
420

Pages