Hong S Kim

US Patent:

6665638, Dec 16, 2003

Filed:

Apr 13, 2001

Appl. No.:

09/834391

Inventors:

Hong-Goo Kang - Chatham NJ
Hong Kook Kim - Chatham NJ

Assignee:

ATT Corp. - New York NY

International Classification:

G10L 2100

US Classification:

704224, 704219

Abstract:

Methods and systems for filtering synthesized or reconstructed speech are implemented. A filter based on a set of linear predictive coding (LPC) coefficients is constructed by transforming the LPC coefficients to the pseudo-cepstrum, a domain existing between LPC domain and the line spectral frequency (LSF) domain. The resulting filter can emphasize spectral frequencies associated with various formants, or spectral peaks, of an inverse transfer function relating to the LPC coefficients, and can de-emphasize spectral frequencies associated with various spectral minima, or spectral valleys, of the inverse transfer function relating to the LPC coefficients.

US Patent:

6792405, Sep 14, 2004

Filed:

Dec 5, 2000

Appl. No.:

09/730435

Inventors:

Richard Vandervoort Cox - New Providence NJ
Hong Kook Kim - Chatham NJ

Assignee:

ATT Corp. - New York NY

International Classification:

G10L 1502

US Classification:

704236, 704223, 704214, 704219, 381 36

Abstract:

A feature extraction process for use in a wireless communication system provides automatic speech recognition based on both spectral envelope and voicing information. The shape of the spectral envelope is used to determine the LSPs of the incoming bitstream and the adaptive gain coefficients and fixed gain coefficients are used to generate the âvoicedâ and âunvoicedâ feature parameter information.

US Patent:

7110947, Sep 19, 2006

Filed:

Dec 5, 2000

Appl. No.:

09/730011

Inventors:

Richard Vandervoort Cox - New Providence NJ, US
Hong Kook Kim - Chatham NJ, US

Assignee:

AT&T Corp. - New York NY

International Classification:

G10L 15/08

US Classification:

704236, 704243

Abstract:

A frame erasure concealment technique for a bitstream-based feature extractor in a speech recognition system particularly suited for use in a wireless communication system operates to “delete” each frame in which an erasure is declared. The deletions thus reduce the length of the observation sequence, but have been found to provide for sufficient speech recognition based on both single word and “string” tests of the deletion technique.

US Patent:

7379865, May 27, 2008

Filed:

Oct 26, 2001

Appl. No.:

10/002030

Inventors:

Hong-Goo Kang - Chatham NJ, US
Hong Kook Kim - Chatham NJ, US

Assignee:

AT&T Corp. - New York NY

International Classification:

G10L 19/04

US Classification:

704219, 704228, 704226

Abstract:

A frame erasure concealment device and method that is based on reestimating gain parameters for a code excited linear prediction (CELP) coder is disclosed. During operation, when a frame in a stream of received data is detected as being erased, the coding parameters, especially an adaptive codebook gain gand a fixed codebook gain g, of the erased and subsequent frames can be reestimated by a gain matching procedure. By using this technique with the IS-641 speech coder, it has been found that the present invention improves frame erasure concealment device and method improve the speech quality under various channel conditions, compared with a conventional extrapolation-based concealment algorithm.

US Patent:

7446127, Nov 4, 2008

Filed:

Aug 26, 2004

Appl. No.:

10/926615

Inventors:

Yong Moon Choi - Pine Brook NJ, US
Hunwoo Shin - Livingston NJ, US
Palanichamy Ilankumaran - Pinerbrook NJ, US
Hong Wook Kim - Lincoln Park NJ, US

Assignee:

SK Holdings Co, Ltd. - Seoul

International Classification:

A01N 43/16
C07D 263/30

US Classification:

514458, 548235

Abstract:

There are disclosed derivatives of 3-chromancarboxylic acid represented by formula I.

US Patent:

7630894, Dec 8, 2009

Filed:

Aug 1, 2006

Appl. No.:

11/497009

Inventors:

Richard Vandervoort Cox - New Providence NJ, US
Hong Kook Kim - Chatham NJ, US

Assignee:

AT&T Intellectual Property II, L.P. - Reno NV

International Classification:

G10L 15/08

US Classification:

704236, 704243

Abstract:

A frame erasure concealment technique for a bitstream-based feature extractor in a speech recognition system particularly suited for use in a wireless communication system operates to “delete” each frame in which an erasure is declared. The deletions thus reduce the length of the observation sequence, but have been found to provide for sufficient speech recognition based on both single word and “string” tests of the deletion technique.

US Patent:

7711556, May 4, 2010

Filed:

Aug 1, 2007

Appl. No.:

11/832285

Inventors:

Hong-Goo Kang - Chatham NJ, US
Hong Kook Kim - Chatham NJ, US

Assignee:

AT&T Intellectual Property II, L.P. - New York NY

International Classification:

G10L 19/04
G10L 21/00

US Classification:

704224, 704219

Abstract:

Methods and systems for filtering synthesized or reconstructed speech are implemented. A filter based on a set of linear predictive coding (LPC) coefficients is constructed by transforming the LPC coefficients to the pseudo-cepstrum, a domain existing between LPC domain and the line spectral frequency (LSF) domain. The resulting filter can emphasize spectral frequencies associated with various formants, or spectral peaks, of an inverse transfer function relating to the LPC coefficients, and can de-emphasize spectral frequencies associated with various spectral minima, or spectral valleys, of the inverse transfer function relating to the LPC coefficients.

US Patent:

7979272, Jul 12, 2011

Filed:

Oct 12, 2007

Appl. No.:

11/871699

Inventors:

Hong-Goo Kang - Chatham NJ, US
Hong Kook Kim - Chatham NJ, US

Assignee:

AT&T Intellectual Property II, L.P. - Atlanta GA

International Classification:

G10L 19/04

US Classification:

704219, 704223, 704207, 704230, 704222, 704208

Abstract:

The present invention provides a frame erasure concealment device and method that is based on reestimating gain parameters for a code excited linear prediction (CELP) coder. During operation, when a frame in a stream of received data is detected as being erased, the coding parameters, especially an adaptive codebook gain gand a fixed codebook gain g, of the erased and subsequent frames can be reestimated by a gain matching procedure. By using this technique with the IS-641 speech coder, it has been found that the present invention improves the speech quality under various channel conditions, compared with a conventional extrapolation-based concealment algorithm.