Search Results - "Lennig, M."

The hemodynamic effects of protamine in pediatric patients undergoing pulmonary artery reconstruction and unifocalization surgery: A Pilot Study by Li, Xi, Fang, Zhe Amy, Lennig, M Michael Andrew, Klein, Alexandra, Char, Danton, Giustini, Andrew James, Boltz, Madalane G, Quiñónez, Zoel A

Get full text

Putting speech recognition to work in the telephone network by Lennig, M.

“…The use of speaker-independent speech recognition in the development of Northern Telecom's automated alternate billing service (AABS) for collect calls,…”
Get full text

Phonemic hidden Markov models with continuous mixture output densities for large vocabulary word recognition by Deng, L., Kenny, P., Lennig, M., Gupta, V., Seitz, F., Mermelstein, P.

“…The authors demonstrate the effectiveness of phonemic hidden Markov models with Gaussian mixture output densities (mixture HMMs) for speaker-dependent…”
Get full text

Modeling microsegments of stop consonants in a hidden markov model based word recognizer by DENG, L, LENNIG, M, MERMELSTEIN, P

“…The motivation of this study is the poor performance of speech recognizers on the stop consonants. To overcome this weakness, word initial and word final stop…”
Get full text

Modeling acoustic transitions in speech by state-interpolation hidden Markov models by Deng, L., Kenny, P., Lennig, M., Mermelstein, P.

“…The authors present a new type of hidden Markov model (HMM) for vowel-to-consonant (VC) and consonant-to-vowel (CV) transitions based on the locus theory of…”
Get full text

Use of vowel duration information in a large vocabulary word recognizer by DENG, L, LENNIG, M, MERMELSTEIN, P

“…In this paper, a method is developed to employ vowel duration properties in a hidden Markov model (HMM)-based large vocabulary speaker trained recognition…”
Get full text

Fast search strategy in a large vocabulary word recognizer by GUPTA, V. N, LENNIG, M, MERMELSTEIN, P

“…In this article, a fast search algorithm is presented for generating word hypotheses for a 75 000-word vocabulary, speaker-trained, isolated word recognizer…”
Get full text

Speaker adaptation in a large-vocabulary Gaussian HMM recognizer by Kenny, P., Lennig, M., Mermelstein, P.

“…The problem of using a small amount of speech data to adapt a set of Gaussian HMMs (hidden Markov models) that have been trained on one speaker to recognize…”
Get full text

A new fast match for very large vocabulary continuous speech recognition by Kenny, P., Labute, P., Li, Z., Hollan, R., Lennig, M., O'Shaughnessy, D.

“…A novel fast match for very large vocabulary continuous speech recognition in which phonetic transcriptions are scored at a cost of one floating-point…”
Get full text

A linear predictive HMM for vector-valued observations with applications to speech recognition by Kenny, P., Lennig, M., Mermelstein, P.

“…The authors describe a new type of Markov model developed to account for the correlations between successive frames of a speech signal. The idea is to treat…”
Get full text

Hybrid segmental-LVQ/HMM for large vocabulary speech recognition by Cheng, Y.M., O'Shaughnessy, D., Gupta, V., Kenny, P., Lennig, M., Mermelstein, P., Parthasarathy, S.

“…The authors have assessed the possibility of modeling phone trajectories to accomplish speech recognition. This approach has been considered as one of the ways…”
Get full text

Using phoneme duration and energy contour information to improve large vocabulary isolated-word recognition by Gupta, V.N., Lennig, M., Mermelstein, P., Kenny, P., Seitz, F., O'Shaughnessy, D.

“…Minimum duration constraints and energy thresholds for phonemes were used to increase the recognition accuracy of an 86000-word speaker-trained isolated word…”
Get full text

A-admissible heuristics for rapid lexical access by Kenny, P., Hollan, R., Gupta, V.N., Lennig, M., Mermelstein, P., O'Shaughnessy, D.

“…A new class of A* algorithms for Viterbi phonetic decoding subject to lexical constraints is presented. This type of algorithm can be made to run substantially…”
Get full text

Automation of alternate billed calls using speech recognition by Murphy, M., Bielby, G., Roe, B., Read, K., O'Gorman, A., Lennig, M.

“…Alternate billed calls (collect, calling-card, bill-to-third-party), which represent close to 50% of the toll and assist traffic in North America, requiring…”
Get full text

Directory assistance automation in Bell Canada: Trial results by Lennig, Matthew, Bielby, Greg, Massicotte, Julie

“…Speech recognition was used to automate directory assistance in a 6-month trial with Bell Canada's public customers. The bilingual application gave the caller…”
Get full text

Experiments on speaker-independent recognition of hand-segmented French vowels by Lennig, M.

“…This paper addresses the problem of recognizing hand-segmented vowel phonemes in isolated words pronounced by different speakers. Overcoming variation in the…”
Get full text

Language modeling for very-large-vocabulary speech recognition by O'Shaughnessy, D., Gupta, V., Lennig, M., Seitz, F., Mermelstein, P.

“…Virtually all recognition systems, both research and commercial, place severe limits on the vocabulary and syntactic structures a speaker may use. This…”
Get full text

Intonation in text-to-speech synthesis: evaluation of algorithms by AKERS, G, LENNIG, M

“…Two algorithms, termed schematic and naturalistic, for generating intonation contours in an English text-to-speech system are compared by eliciting preference…”
Get full text

Acoustic recognition component of an 86000-word speech recognizer by Deng, L., Gupta, V., Lennig, M., Kenny, P., Mermelstein, P.

“…Recent results obtained with a hidden Markov model (HMM)-based acoustic recognizer using a virtually unlimited vocabulary (86000 words) to perform…”
Get full text

A locus model of coarticulation in an HMM speech recognizer by Deng, L., Kenny, P., Lennig, M., Gupta, V., Mermelstein, P.

“…A novel type of hidden Markov model (HMM) has been developed to account explicitly for the context-dependent vowel acoustic transitions in consonant-vowel and…”
Get full text