Search

Alistair David Conkie

from San Jose, CA
Age ~66

Alistair Conkie Phones & Addresses

  • 1295 Mokelumne Pl, San Jose, CA 95120
  • Middleton, WI
  • Cupertino, CA
  • Morristown, NJ
  • Watchung, NJ
  • Santa Clara, CA

Publications

Us Patents

Synthesis-Based Pre-Selection Of Suitable Units For Concatenative Speech

View page
US Patent:
6505158, Jan 7, 2003
Filed:
Jul 5, 2000
Appl. No.:
09/609889
Inventors:
Alistair D. Conkie - Morristown NJ
Assignee:
ATT Corp. - New York NY
International Classification:
G10L 1308
US Classification:
704260, 704268
Abstract:
A method and system for providing concatenative speech uses a speech synthesis input to populate a triphone-indexed database that is later used for searching and retrieval to create a phoneme string acceptable for a text-to-speech operation. Prior to initiating the “real time” synthesis, a database is created of all possible triphone contexts by inputting a continuous stream of speech. The speech data is then analyzed to identify all possible triphone sequences in the stream, and the various units chosen for each context. During a later text-to-speech operation, the triphone contexts in the text are identified and the triphone-indexed phonemes in the database are searched to retrieve the best-matched candidates.

Method And System For Preselection Of Suitable Units For Concatenative Speech

View page
US Patent:
6684187, Jan 27, 2004
Filed:
Jun 30, 2000
Appl. No.:
09/607615
Inventors:
Alistair D. Conkie - Morristown NJ
Assignee:
ATT Corp. - New York NY
International Classification:
G10L 1308
US Classification:
704260, 704258, 704266
Abstract:
A system and method for improving the response time of text-to-speech synthesis utilizes “triphone contexts” (i. e. , triplets comprising a central phoneme and its immediate context) as the basic unit, instead of performing phoneme-by-phoneme synthesis. Prior to initiating the “real time” synthesis, a database is created of ail possible triphones (there are approximately 10000 in the English language) and their associated preselection costs. At run time, therefore, only the most likely candidates are selected from the triphone database, significantly reducing the calculations that are required to be performed in real time.

Synthesis-Based Pre-Selection Of Suitable Units For Concatenative Speech

View page
US Patent:
7013278, Mar 14, 2006
Filed:
Sep 5, 2002
Appl. No.:
10/235401
Inventors:
Alistair D. Conkie - Morristown NJ, US
Assignee:
AT&T Corp. - New York NY
International Classification:
G10L 13/08
US Classification:
704260, 704266, 704268
Abstract:
A method for generating concatenative speech uses a speech synthesis input to populate a triphone-indexed database that is later used for searching and retrieval to create a phoneme string acceptable for a text-to-speech operation. Prior to initiating the “real time” synthesis process, a database is created of all possible triphone contexts by inputting a continuous stream of speech. The speech data is then analyzed to identify all possible triphone sequences in the stream, and the various units chosen for each context. During a later text-to-speech operation, the triphone contexts in the text are identified and the triphone-indexed phonemes in the database are searched to retrieve the best-matched candidates.

Method And System For Preselection Of Suitable Units For Concatenative Speech

View page
US Patent:
7124083, Oct 17, 2006
Filed:
Nov 5, 2003
Appl. No.:
10/702154
Inventors:
Alistair D. Conkie - Morristown NJ, US
Assignee:
AT&T Corp. - New York NY
International Classification:
G10L 13/04
US Classification:
704266, 704254
Abstract:
A system and method for improving the response time of text-to-speech synthesis utilizes “triphone contexts” (i. e. , triplets comprising a central phoneme and its immediate context) as the basic unit, instead of performing phoneme-by-phoneme synthesis. The method comprises a method of generating a triphone preselection cost database for use in speech synthesis, the method comprising 1) selecting a triphone sequence u-u-u, 2) calculating a preselection cost for each 5-phoneme sequence u-u-u-u-u, where uis allowed to match any identically labeled phoneme in a database and the units uand uvary over the entire phoneme universe and 3) storing a group of the selected triphone sequences exhibiting the lowest costs in a triphone preselection cost database.

Synthesis-Based Pre-Selection Of Suitable Units For Concatenative Speech

View page
US Patent:
7233901, Jun 19, 2007
Filed:
Dec 30, 2005
Appl. No.:
11/275432
Inventors:
Alistair D. Conkie - Morristown NJ, US
Assignee:
AT&T Corp. - New York NY
International Classification:
G10L 13/06
US Classification:
704260, 704266
Abstract:
A system and computer-readable medium synthesize speech from text using a triphone unit selection database. The instructions on the computer-readable medium control a computing device to perform the steps: receiving input text, selecting a plurality of N phoneme units from the triphone unit selection database as candidate phonemes for synthesized speech based on the input text, applying a cost process to select a set of phonemes from the candidate phonemes and synthesizing speech using the selected set of phonemes.

Automatic Segmentation In Speech Synthesis

View page
US Patent:
7266497, Sep 4, 2007
Filed:
Jan 14, 2003
Appl. No.:
10/341869
Inventors:
Alistair D. Conkie - Morristown NJ, US
Assignee:
AT&T Corp. - New York NY
International Classification:
G10L 13/00
US Classification:
704258, 704256, 704266, 704253
Abstract:
Systems and methods for automatically segmenting speech inventories. A set of Hidden Markov Models (HMMs) are initialized using bootstrap data. The HMMs are next re-estimated and aligned to produce phone labels. The phone boundaries of the phone labels are then corrected using spectral boundary correction. Optionally, this process of using the spectral-boundary-corrected phone labels as input instead of the bootstrap data is performed iteratively in order to further reduce mismatches between manual labels and phone labels assigned by the HMM approach.

Method And System For Preselection Of Suitable Units For Concatenative Speech

View page
US Patent:
7460997, Dec 2, 2008
Filed:
Aug 22, 2006
Appl. No.:
11/466229
Inventors:
Alistair D. Conkie - Morristown NJ, US
Assignee:
AT&T Intellectual Property II, L.P. - New York NY
International Classification:
G10L 13/00
G10L 13/06
US Classification:
704258, 704260, 704266
Abstract:
A system and method for improving the response time of text-to-speech synthesis utilizes “triphone contexts” (i. e. , triplets comprising a central phoneme and its immediate context) as the basic unit, instead of performing phoneme-by-phoneme synthesis. The method comprises a method of generating a triphone preselection cost database for use in speech synthesis, the method comprising 1) selecting a triphone sequence u-u-u, 2) calculating a preselection cost for each 5-phoneme sequence u-u-u-u-u, where uis allowed to match any identically labeled phoneme in a database and the units uand uvary over the entire phoneme universe and 3) storing a group of the selected triphone sequences exhibiting the lowest costs in a triphone preselection cost database.

Synthesis-Based Pre-Selection Of Suitable Units For Concatenative Speech

View page
US Patent:
7565291, Jul 21, 2009
Filed:
May 15, 2007
Appl. No.:
11/748849
Inventors:
Alistair D. Conkie - Morristown NJ, US
Assignee:
AT&T Intellectual Property II, L.P. - New York NY
International Classification:
G10L 13/06
US Classification:
704258
Abstract:
The instructions on the computer-readable medium control a computing device to perform the steps: selecting at least one phoneme from a triphone unit selection database as at least candidate phoneme for use in speech synthesis, selecting a set of phonemes from the at least one candidate phonemes and synthesizing speech using the selected set of phonemes.
Alistair David Conkie from San Jose, CA, age ~66 Get Report