Mark Robert Cromack

US Patent:

6862298, Mar 1, 2005

Filed:

Jul 28, 2000

Appl. No.:

09/627956

Inventors:

Shawn W. Smith - Ventura CA, US
Mark R. Cromack - Santa Ynez CA, US

Assignee:

Crystalvoice Communications, Inc. - Santa Barbara CA

International Classification:

H04J003/06

US Classification:

370516, 370235, 370252, 370253, 370517, 370519, 370508, 370429

Abstract:

In an improved system for receiving digital voice signals from a data network, a jitter buffer manager monitors packet arrival times, determines a time varying transit delay variation parameter and adaptively controls jitter buffer size in response to the variation parameter. A speed control module responds to a control signal from the jitter buffer manager by modifying the rate of data consumption from the jitter buffer, to compensate for changes in buffer size, preferably in a manner which maintains audio output with acceptable, natural human speech characteristics. Preferably, the manager also calculates average packet delay and controls the speed control module to adaptively align the jitter buffer's center with the average packet delay time.

US Patent:

8332212, Dec 11, 2012

Filed:

Jun 17, 2009

Appl. No.:

12/456586

Inventors:

Andreas Wittenstein - Woodacre CA, US
Mark Cromack - Santa Ynez CA, US

Assignee:

Cogi, Inc. - Santa Barbara CA

International Classification:

G10L 19/14
G10L 15/20
G10L 15/00
G10L 13/08
G10L 13/00
G10L 11/00
G10L 21/00

US Classification:

704211, 704233, 704241, 704258, 704260, 704270

Abstract:

A method and system for improving the efficiency of real-time and non-real-time speech transcription by machine speech recognizers, human dictation typists, and human voicewriters using speech recognizers. In particular, the pacing with which recorded speech is presented to transcriptionists is automatically adjusted by monitoring the transcriptionists' output by comparing the output acoustically or phonetically to the presented recorded speech as well as monitoring the resulting transcription, and accordingly adjusting the pacing.

US Patent:

8335689, Dec 18, 2012

Filed:

Oct 14, 2009

Appl. No.:

12/587894

Inventors:

Andreas Wittenstein - Woodacre CA, US
David Brahm - The Woodlands TX, US
Mark Cromack - Santa Ynez CA, US
Robert Dolan - Santa Barbara CA, US

Assignee:

COGI, Inc. - Santa Barbara CA

International Classification:

G10L 15/26

US Classification:

704235, 704231, 704276

Abstract:

A method and system for improving the efficiency of speech transcription by automating the management of a varying pool of human and machine transcribers having diverse qualifications, skills, and reliability for a fluctuating load of speech transcription tasks of diverse requirements such as accuracy, promptness, privacy, and security, from sources of diverse characteristics such as language, dialect, accent, speech style, voice type, vocabulary, audio quality, and duration.

US Patent:

8407049, Mar 26, 2013

Filed:

Apr 22, 2009

Appl. No.:

12/386854

Inventors:

Mark Cromack - Santa Ynez CA, US
Robert Dolan - Santa Barbara CA, US
Andreas Wittenstein - Woodacre CA, US
David Brahm - The Woodlands TX, US

Assignee:

COGI, Inc. - Santa Barbara CA

International Classification:

G10L 15/26

US Classification:

704235, 704270, 704 7

Abstract:

This invention description details systems and methods for improving human conversations by enhancing conversation participants' ability to: —Distill out and record core ideas of conversations. —Classify and prioritize these key concepts. —Recollect commitments and issues and take appropriate action. —Analyze and uncover new insight from the linkage of these ideas with those from other conversations.

US Patent:

51630508, Nov 10, 1992

Filed:

Jan 23, 1991

Appl. No.:

7/644934

Inventors:

Mark R. Cromack - Santa Ynez CA

Assignee:

Digital Sound Corporation - Carpinteria CA

International Classification:

H04J 312

US Classification:

3701103

Abstract:

In a digital messaging system (10), an apparatus (37) and method for determining whether a DTMF (Dual Tone Multi Frequency) digit is present on an input signal (11,12). A heuristics engine (37) performs a series of tests on the input signal (11,12) using a set of parameters that are stored in a RAM (38). There is one parameter for each of a set of input signal (11,12) characteristics and for each of a set of operating modes of the digital messaging system (10). All of the parameters are configurable. The configurability allows for the use of non-standard telephone equipment (13,14) and minimizes deleterious effects such as talkoff. The tests are from the set of sets comprising an absolute magnitude test, a frequency deviation test, a twist test, an echo test, a consistency test, and a temporal test.

US Patent:

54003946, Mar 21, 1995

Filed:

Jun 23, 1994

Appl. No.:

8/265697

Inventors:

Vijay R. Raman - Santa Barbara CA
Mark R. Cromack - Santa Ynez CA

Assignee:

Digital Sound Corporation - Carpenteria CA

International Classification:

H04J 1500
H04M 174

US Classification:

379 88

Abstract:

An apparatus and method for echo cancellation in voice-messaging and voice-response systems, to enhance recognition of received DTMF and voice signals, comprising an efficient software echo canceller using adaptive digital filtering techniques. The voice messaging system includes analog telephone line interface modules which provide digitized voice data to a digital signal processor (DSP) chip. A transmit data line and a receive data line are each coupled to a cancel module with a cancel filter and an adapt/window module with an adaptive digital filter. The cancel filter causes echo cancellation on the receive data line; the adapt/window module monitors buffered transmit data in non-real time, without directly causing cancellation to occur, and selectively transfers an adjacent window of filter coefficients to the cancel filter under control of an adaptation control coupled to the adapt/window module. The control identifies a plurality of frames meeting a power criterion and passes the frames to the adaptive filter, which adapts on taps in frame segments during all available DSP real time, using a "cycle steal" approach for testing whether additional DSP processor cycles are available to use for echo cancellation. A masked white noise burst may be used to initialize adaptation.

US Patent:

52673227, Nov 30, 1993

Filed:

Dec 13, 1991

Appl. No.:

7/806763

Inventors:

Shawn W. Smith - Santa Barbara CA
Mark Cromack - Santa Ynez CA

Assignee:

Digital Sound Corporation - Carpinteria CA

International Classification:

H03G 300

US Classification:

381107

Abstract:

An automatic gain controller for a digitized audio signal, comprising a buffer with a plurality of subframes. Each subframe contains digitized data samples of the signal, the subframes including at least one future subframe and a current subframe. Signal processing means (such as a DSP) is coupled to the memory for controlling gain of the audio signal represented by the current subframe in the buffer. The signal processing means includes means to control gain of the data samples using a stored program for computing a plurality of mean signal level values from the plurality of subframes, each mean signal level value in the plurality corresponding to one of the subframes. The program includes means for causing decay of gain on the signal represented by the current subframe when a first set of the mean values are each below a low threshold signal level. The program also has means for causing gain attack on the audio signal represented by the current subframe when a second set of the mean values are each above a high threshold signal level. The program also comprises means for shifting the data samples in one subframe in the future group into the current subframe for controlling gain of the audio signal after causing gain attack or decay.

US Patent:

20190156826, May 23, 2019

Filed:

Nov 14, 2018

Appl. No.:

16/191151

Inventors:

- Santa Barbara CA, US
Mark Robert Cromack - Santa Ynez CA, US

International Classification:

G10L 15/22
G06F 17/27
G06F 17/21
G06F 16/483
G06F 16/33

Abstract:

A content extraction and display process which process may include various functionality for segmenting content into analyzable portions, ranking relevance of content within such segments, and displaying highly ranked extractions in graphical cloud form. The graphical cloud in some embodiments will dynamically and synchronously update as the content is played back or acquired. Extracted elements maybe in the form of words, phrases, audio sequences, non-verbal visual segments or icons as well as a host of other information communicating data objects expressible by graphical display.