The Statistical Phrase/Accent Model for Intonation Modeling: Difference between revisions
From HLT@INESC-ID
No edit summary |
No edit summary |
||
| Line 1: | Line 1: | ||
__NOTOC__ | __NOTOC__ | ||
{{ | {{speakerLargeBio| | ||
| | |name=Gopala Krishna Anumanchipalli | ||
| | |image=Gopala.Anumanchipalli.jpg | ||
| | |email= gopalakr@cs.cmu.edu | ||
| | |www=http://www.cs.cmu.edu/~gopalakr/ | ||
|bio=Gopala is a PhD student in the LTI, CMU and INESC-ID Lisboa, IST. He is advised by Dr. Alan W Black and Dr. Luis Oliveira. He is currently at INESC-ID. He is interested broadly in everything to do with language, but specifically works on building models and transformation approaches for prosody in Speech synthesis. He is working in the PT-Star project aiming to do Speech-to-Speech machine translation of video lectures. | |||
}} | }} | ||
== Date == | == Date == | ||
* | * 15:00, Friday, September 3<sup>rd</sup>, 2010 | ||
* Room 336 | * Room 336 | ||
== Speaker == | == Speaker == | ||
* [[Gopala Krishna Anumanchipalli]] | * [[Gopala Krishna Anumanchipalli]], Carnegie Mellon University, USA and INESC-ID Lisboa, IST | ||
== Abstract == | == Abstract == | ||
Revision as of 11:10, 6 June 2011
| Gopala Krishna Anumanchipalli |
 |
| Addresses: www mail |
Date
- 15:00, Friday, September 3rd, 2010
- Room 336
Speaker
- Gopala Krishna Anumanchipalli, Carnegie Mellon University, USA and INESC-ID Lisboa, IST
Abstract
In this talk I will describe the newly developed statistical phrase accent model for generation of natural and expressive intonation contours in speech synthesis. I will briefly mention the conventional approaches and drawbacks of existing intonation models for speech synthesis. I will introduce the proposed statistical model, an associated training algorithm and performance on some tasks.
This is joint work with Dr. Alan Black and Dr. Luis Oliveira.
Note: This seminar will be held in English.