Search Results - "Bellegarda, J.R."

Exploiting latent semantic information in statistical language modeling by Bellegarda, J.R.

“…Statistical language models used in large-vocabulary speech recognition must properly encapsulate the various constraints, both local and global, present in…”
Get full text

A global, boundary-centric framework for unit selection text-to-speech synthesis by Bellegarda, J.R.

“…The level of quality that can be achieved by modern concatenative text-to-speech synthesis heavily depends on the optimization criteria used in the unit…”
Get full text

Unit-Centric Feature Mapping for Inventory Pruning in Unit Selection Text-to-Speech Synthesis by Bellegarda, J.R.

“…The level of quality that can be attained in concatenative text-to-speech (TTS) synthesis is primarily governed by the inventory of units used in unit…”
Get full text

Large vocabulary speech recognition with multispan statistical language models by Bellegarda, J.R.

“…Multispan language modeling refers to the integration of various constraints, both local and global, present in the language. It was recently proposed to…”
Get full text

Statistical prosodic modeling: from corpus design to parameter estimation by Bellegarda, J.R., Silverman, K.E.A., Lenzo, K., Anderson, V.

“…The increasing availability of carefully designed and collected speech corpora opens up new possibilities for the statistical estimation of formal multivariate…”
Get full text

Natural language spoken interface control using data-driven semantic inference by Bellegarda, J.R., Silverman, K.E.A.

“…Spoken interaction tasks are typically approached using a formal grammar as language model. While ensuring good system performance, this imposes a rigid…”
Get full text

Further analysis of LSM-based unit pruning forunit selection TTS by Bellegarda, J.R.

“…The level of quality that can be achieved in concatenative text-to-speech synthesis is primarily governed by the inventory of units used in unit selection…”
Get full text

The hit array: an analysis formalism for multiple access frequency hop coding by Bellegarda, J.R., Titlebaum, E.L.

“…A formalism is presented for the analysis of general frequency hop waveforms, such as those suitable for use in coherent active radar and sonar echolocation…”
Get full text

Lsm-Based Boundary Training for Concatenative Speech Synthesis by Bellegarda, J.R.

“…The level of quality that can be achieved in concatenative text-to-speech synthesis depends, among other things, on a judicious chiseling of the inventory used…”
Get full text

A novel approach to part-of-speech tagging based on latent analogy by Bellegarda, J.R.

“…Part-of-speech tagging is a necessary pre-processing step for many natural language tasks. Recent statistical approaches, such as conditional random fields,…”
Get full text

Globally Optimal Training of Unit Boundaries in Unit Selection Text-to-Speech Synthesis by Bellegarda, J.R.

“…The level of quality that can be achieved by modern concatenative text-to-speech synthesis heavily depends on a judicious composition of the unit inventory…”
Get full text

Unsupervised, language-independent grapheme-to-phoneme conversion by latent analogy by Bellegarda, J.R.

“…Automatic, data-driven grapheme-to-phoneme conversion is a challenging but often necessary task. The top-down strategy implicitly followed by traditional…”
Get full text

Latent semantic mapping [information retrieval] by Bellegarda, J.R.

“…This article has described LSM, a data-driven framework for modeling globally meaningful relationships implicit in large volumes of data. LSM generalizes a…”
Get full text

Speech recognition experiments using multi-span statistical language models by Bellegarda, J.R.

“…A multi-span framework was proposed to integrate the various constraints, both local and global, that are present in the language. In this approach, local…”
Get full text

Language-independent, short-enrollment voice verification over a far-field microphone by Bellegarda, J.R., Naik, D., Neeracher, M., Silverman, K.E.A.

“…An approach is presented for the dual verification of speaker identity and verbal content in a text-dependent voice authentication system. The application…”
Get full text

Exploiting both local and global constraints for multi-span statistical language modeling by Bellegarda, J.R.

“…A new framework is proposed to integrate the various constraints, both local and global, that are present in the language. Local constraints are captured via…”
Get full text

Using a sigmoid transformation for improved modeling of phoneme duration by Silverman, K.E.A., Bellegarda, J.R.

“…The "sums-of-products" approach has emerged as one of the most promising avenues to model contextual influences on phoneme duration. The associated regression…”
Get full text

Congruential frequency hop signals for multi-user environments: a comparative analysis by Bellegarda, J.R.

“…Frequency-hop pulse train signals used in applications such as coherent multiuser of multibeam echolocation must be selected on the basis of good…”
Get full text

Time-frequency properties of extended quadratic congruential frequency hop signals by Bellegarda, J.R.

“…Frequency-hop pulse train signals, used in applications such as coherent multiuser or multibeam echo location, must be selected on the basis of good…”
Get full text

A fast statistical mixture algorithm for on-line handwriting recognition by Bellegarda, E.J., Bellegarda, J.R., Nahamoo, D., Nathan, K.S.

“…The automatic recognition of online handwriting is considered from an information theoretic viewpoint. Emphasis is placed on the recognition of unconstrained…”
Get full text