Gerald E Corrigan

US Patent:

20040088161, May 6, 2004

Filed:

Oct 30, 2002

Appl. No.:

10/283640

Inventors:

Gerald Corrigan - Chicago IL, US
Steven Albrecht - Glenview IL, US

International Classification:

G10L019/14

US Classification:

704/211000

Abstract:

To address the need for a method and apparatus for preventing speech dropout in a low-latency text-to-speech system, a method and apparatus for preventing such speech dropout is described herein. In accordance with the preferred embodiment of the present invention the rate of speech is allowed to vary based on an amount of data existing within the buffer. More particularly, as the buffer empties, the rate of speech slows, reducing the chances that the output buffer will empty.

US Patent:

20050060156, Mar 17, 2005

Filed:

Aug 9, 2004

Appl. No.:

10/914583

Inventors:

Gerald Corrigan - Chicago IL, US
Steven Albrecht - Glenview IL, US

International Classification:

G10L021/00
G10L013/00

US Classification:

704270100, 704258000

Abstract:

In a speech synthesis technique used in a network (), a set of text words is accepted by a speech engine software function () in a client device (). From the set of text words, an invalid subset of text words is determined for which the text words are not in a word synthesis dictionary of the client device. The invalid subset of text words is transmitted over the network to a server device (), which generates a set of word pronunciations including at least a portion of the text words of the invalid subset of text words and pronunciations associated with each of the text words. The client device uses the pronunciations for speech synthesis and may store them in a local word synthesis dictionary () stored in a memory () of the client device.

US Patent:

59131942, Jun 15, 1999

Filed:

Jul 14, 1997

Appl. No.:

8/892295

Inventors:

Orhan Karaali - Rolling Meadows IL
Noel Massey - Schaumburg IL
Gerald Corrigan - Chicago IL

Assignee:

Motorola, Inc. - Schaumburg IL

International Classification:

G10L 502

US Classification:

704259

Abstract:

A method (400), device and system (300) provide, in response to linguistic information, efficient generation of a parametric representation of speech using a neural network. The method provides, in response to linguistic information efficient generation of a refined parametric representation of speech, comprising the steps of: A) using a data selection module to retrieve representative parameter vectors for each segment description according to the phonetic segment type and the phonetic segment types included in adjacent segment descriptions; B) interpolating between the representative parameter vectors according to the segment descriptions and duration to provide interpolated statistical parameters; C) converting the interpolated statistical parameters and linguistic information to neural network input parameters; D) utilizing a statistically enhanced neural network/neural network with post-processor to provide neural network output parameters that correspond to a parametric representation of speech; and converting the neural network output parameters to a refined parametric representation of speech.

US Patent:

61784028, Jan 23, 2001

Filed:

Apr 29, 1999

Appl. No.:

9/301711

Inventors:

Gerald E. Corrigan - Chicago IL

Assignee:

Motorola, Inc. - Schaumburg IL

International Classification:

G10L 1300

US Classification:

704259

Abstract:

The present invention provides a method, device and system to generate acoustic parameters in a text-to-speech system utilizing a neural network to generate a representation of a trajectory in an acoustic parameter space across a phonetic segment.

US Patent:

51289474, Jul 7, 1992

Filed:

Jun 30, 1989

Appl. No.:

7/373963

Inventors:

Gerald Corrigan - Chicago IL

Assignee:

Motorola, Inc. - Schaumburg IL

International Classification:

G06F 1100

US Classification:

371 63

Abstract:

A totally self-checking memory cell array apparatus (30) has an array (31) of memory cells (32) selectively addressed by row and column decoders (33, 35) which receive unidirectional error detecting code signals as address inputs (34, 36). Data, as a multiple bit data word (A, B, C. sub. 1, C. sub. 2), is stored in the array (31) in unidirectional error detecting code form. Cells in each row (1-8) of the array have two separate row select connection lines (45 and 45a) for coupling the cell to data and data complement (46, 46*) connections. Error detection circuits (44, 47) are provided which determine errors by comparing the data and data complement lines for each data bit read out of the array and for detecting when multiple bit data words read out of the array are not coded in a unidirectional error detecting code format. The above apparatus provides error indications in case of any unidirectional errors in the row or column input address signals or the row or column decoders, or any unidirectional error corruption of the data stored in the memory cell array. This is achieved without completely duplicating each memory cell in the array and all row and column decoder circuitry.

US Patent:

48037265, Feb 7, 1989

Filed:

Dec 31, 1986

Appl. No.:

6/948199

Inventors:

Stephen N. Levine - Itasca IL
Larry C. Puhl - Sleepy Hollow IL
Harry M. Bliss - Chicago IL
Gerald E. Corrigan - Chicago IL

Assignee:

Motorola, Inc. - Schaumburg IL

International Classification:

H04K 102
H04L 700

US Classification:

380 48

Abstract:

A method and means for maintaining continuous bit synchronization of data transmitted from a remote unit through a base unit to a landline unit is disclosed. An input data stream at a first bit rate, such as digitized or encrypted speech, is interleaved with a plurality of signalling words, and transmitted over an RF channel at a second bit rate. The base site recovers the clock of the received data, strips off the signalling word, modifies the bit rate of the received data, and adjusts the recovered clock rate to provide an output data stream which is in bit synchronization with the input data stream and within a predetermined modem specification. The encrypted data is then sent over landlines to a decryption unit which requires bit synchronization.

US Patent:

59501626, Sep 7, 1999

Filed:

Oct 30, 1996

Appl. No.:

8/739975

Inventors:

Gerald Corrigan - Chicago IL
Orhan Karaali - Rolling Meadows IL
Noel Massey - Hoffman Estates IL

Assignee:

Motorola, Inc. - Schaumburg IL

International Classification:

G10L 506
G10L 900

US Classification:

704260

Abstract:

The present invention teaches a method (400), device and system (300) utilizing at least one of: mapping a sequence of phones to a sequence of articulatory features and utilizing prominence and boundary information, in addition to a predetermined set of rules for type, phonetic context, syntactic and prosodic context for phones to provide provide a system that generates segment durations efficiently with a small training set.

US Patent:

56689268, Sep 16, 1997

Filed:

Mar 22, 1996

Appl. No.:

8/622237

Inventors:

Orhan Karaali - Rolling Meadows IL
Gerald Edward Corrigan - Chicago IL
Ira Alan Gerson - Schaumburg IL

Assignee:

Motorola, Inc. - Schaumburg IL

International Classification:

G10L 506

US Classification:

704232

Abstract:

Text may be converted to audible signals, such as speech, by first training a neural network 106 using recorded audio messages 204. To begin the training, the recorded audio messages are converted into a series of audio frames 205 having a fixed duration 213. Then, each audio frame is assigned a phonetic representation 203 and a target acoustic representation 208, where the phonetic representation 203 is a binary word that represents the phone and articulation characteristics of the audio frame, while the target acoustic representation 208 is a vector of audio information such as pitch and energy. After training, the neural network 106 is used in conversion of text into speech. First, text that is to be convened is translated to a series of phonetic frames 401 of the same form as the phonetic representations 208 and having the fixed duration 213. Then the neural network produces acoustic representations in response to context descriptions 207 that include some of the phonetic frames 401. The acoustic representations are then converted into a speech wave form by a synthesizer 107.