Christopher Liberatore

Christopher Liberatore
Texas A&M University | TAMU · Department of Computer Science and Engineering

Bachelor of Science, Computer Science

About

9
Publications
750
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
45
Citations
Introduction
I am currently working on a technique, based in simulation optimization, which will allow us to estimate a speaker's anatomical and articulatory features from acoustic samples only. We could use this optimization technique on a detailed physical model of the vocal tract to synthesize phonemes with a target speaker's voice quality, even if that speaker never uttered those phonemes. This synthesis could then be applied to accent conversion algorithms.
Additional affiliations
May 2016 - August 2016
Wright-Patterson Air Force Base
Position
  • Research Internship
May 2015 - August 2015
Wright-Patterson Air Force Base
Position
  • Research Internship
May 2014 - September 2014
Texas A&M University
Position
  • Research Assistant
Education
August 2013 - May 2018
Texas A&M University
Field of study
  • Computer Science
August 2009 - May 2013
California State University, Sacramento
Field of study
  • Computer Science

Publications

Publications (9)
Article
The type of voice model used in Computer Assisted Pronunciation Instruction is a crucial factor in the quality of practice and the amount of uptake by language learners. As an example, prior research indicates that second-language learners are more likely to succeed when they imitate a speaker with a voice similar to their own, a so-called “golden...
Conference Paper
In previous work we presented a Sparse, Anchor-Based Representation of speech (SABR) that uses phonemic “anchors” to represent an utterance with a set of sparse non-negative weights. SABR is speaker-independent: combining weights from a source speaker with anchors from a target speaker can be used for voice conversion. Here, we present an extension...
Conference Paper
Full-text available
We present SABR (Sparse, Anchor-Based Representation), an analysis technique to decompose the speech signal into speaker-dependent and speaker-independent components. Given a collection of utterances for a particular speaker, SABR uses the centroid for each phoneme as an acoustic " anchor, " then applies Lasso regularization to represent each speec...
Conference Paper
Full-text available
We describe a method for adapting a physical vocal tract model's anatomical and gestural parameters using acoustic information to match a target speaker. Physical vocal tract models are hard to adjust to match a speaker, as doing so requires information which is difficult to capture, such as X-Ray or MRI information. We propose an analysis-by-synth...

Network

Cited By