Karl Daniel Gierach - Irvine CA, Michael V. Shmalko - Newport Beach CA,
Assignee:
Applied Voice and Speech Technologies, Inc. - Foothill Ranch CA
International Classification:
H04M 9/08
US Classification:
37940601, 37940603, 37940606
Abstract:
Apparatus, methods, and machine-readable articles of manufacture enable a telephone system to distinguish between actual events and echoes. Events may include conferees' voice and DTMF commands. In selected embodiments, the system categorizes an event received on one channel as a real event if the energy of the event's waveform is greater than concurrent energy of every other channel of the same conference. Otherwise, the event is stored. When the system receives a new event of the same type on a channel of the same conference during a predetermined period, it compares the energies of the new and stored events. If the energy of the new event exceeds that of the stored event, the new event becomes the stored event, and the old stored event is ignored. At the end of the period, the stored event is categorized as a real event and forwarded to appropriate application code.
Apparatus And Method For Performing Hosted And Secure Identity Authentication Using Biometric Voice Verification Over A Digital Network Medium
Apparatus, methods, and machine-readable articles of manufacture enable a means of performing vocal tract based authentication and vocal tract based enrollment via the Internet or similar computing network as a communication medium. A protocol and process is outlined which enables Internet or similar network based authentication among three parties; a party wishing to prove a claimed identity, a party requesting to authenticate the claimed identity, and a party performing the authentication or enrollment process. Further, the party requesting authentication is a separate entity from the party performing authentication or enrollment. In such an arrangement, the party performing the authentication or enrollment is termed “hosted” or “software as a service”. The protocol and process is suitable for execution by distinct software components installed and running on computers located at the location of each of the three parties.
Apparatus And Method For Notification Of A Party In A Telephone Conference
Systems, methods, and machine-readable articles of manufacture enable private notification of a participant in a telephone conference. In representative embodiments, a system receives a telephone call intended for a first conference participant, generates an informative announcement containing information regarding the call, mixes the informative announcement with the conference audio, and privately plays the mixed audio to the first participant. In other representative embodiments, the system concurrently generates a non-informative announcement, mixes the non-informative announcement with the conference audio, and plays the second mixed audio to the other conference participant or participants. In this way, the first participant is notified of the incoming call while simultaneously listening to the conference audio, and the information regarding the call is not shared with the other conference participant or participants.
Karl Daniel Gierach - Irvine CA, Michael V. Shmalko - Newport Beach CA,
Assignee:
Applied Voice & Speech Technologies, Inc. - Foothill Ranch CA
International Classification:
H04M 9/08
US Classification:
37940601, 37940603, 37940606
Abstract:
Apparatus, methods, and machine-readable articles of manufacture enable a telephone system to distinguish between actual events and echoes. Events may include conferees' voice and DTMF commands. In selected embodiments, the system categorizes an event received on one channel as a real event if the energy of the event's waveform is greater than concurrent energy of every other channel of the same conference. Otherwise, the event is stored. When the system receives a new event of the same type on a channel of the same conference during a predetermined period, it compares the energies of the new and stored events. If the energy of the new event exceeds that of the stored event, the new event becomes the stored event, and the old stored event is ignored. At the end of the period, the stored event is categorized as a real event and forwarded to appropriate application code.
Detection Of Voice Inactivity Within A Sound Stream
Applied Voice & Speech Technologies, Inc. - Foothill Ranch CA
International Classification:
G10L 17/00
US Classification:
704248, 704208, 704231, 704246, 704251, 704254
Abstract:
A method for identifying end of voiced speech within an audio stream of a noisy environment employs a speech discriminator. The discriminator analyzes each window of the audio stream, producing an output corresponding to the window. The output is used to classify the window in one of several classes, for example, (1) speech, (2) silence, or (3) noise. A state machine processes the window classifications, incrementing counters as each window is classified: speech counter for speech windows, silence counter for silence, and noise counter for noise. If the speech counter indicates a predefined number of windows, the state machine clears all counters. Otherwise, the state machine appropriately weights the values in the silence and noise counters, adds the weighted values, and compares the sum to a limit imposed on the number of non-voice windows. When the non-voice limit is reached, the state machine terminates processing of the audio stream.
Detection Of Voice Inactivity Within A Sound Stream
Applied Voice & Speech Technologies, Inc. - Foothill Ranch CA
International Classification:
G10L011/06
US Classification:
704208000
Abstract:
A method for identifying end of voiced speech within an audio stream of a noisy environment employs a speech discriminator. The discriminator analyzes each window of the audio stream, producing an output corresponding to the window. The output is used to classify the window in one of several classes, for example, (1) speech, (2) silence, or (3) noise. A state machine processes the window classifications, incrementing counters as each window is classified: speech counter for speech windows, silence counter for silence, and noise counter for noise. If the speech counter indicates a predefined number of windows, the state machine clears all counters. Otherwise, the state machine appropriately weights the values in the silence and noise counters, adds the weighted values, and compares the sum to a limit imposed on the number of non-voice windows. When the non-voice limit is reached, the state machine terminates processing of the audio stream.
Apparatus And Methods For Notification Of A Party In A Telephone Conference
Karl Daniel Gierach - Irvine CA, Michael V. Shmalko - Newport Beach CA,
International Classification:
H04M 11/00 H04M 3/42
US Classification:
379 9301, 37920201
Abstract:
Systems, methods, and machine-readable articles of manufacture enable private notification of a participant in a telephone conference. In representative embodiments, a system receives a telephone call intended for a first conference participant, generates an informative announcement containing information regarding the call, mixes the informative announcement with the conference audio, and privately plays the mixed audio to the first participant. In other representative embodiments, the system concurrently generates a non-informative announcement, mixes the non-informative announcement with the conference audio, and plays the second mixed audio to the other conference participant or participants. In this way, the first participant is notified of the incoming call while simultaneously listening to the conference audio, and the information regarding the call is not shared with the other conference participant or participants.
Michael Fox - San Diego CA, Faisal Mushtaq - San Jose CA, Karl Gierach - Irvine CA,
Assignee:
ORTIVA WIRELESS, INC. - La Jolla CA
International Classification:
G06F 15/16
US Classification:
709219, 709228
Abstract:
An intermediate device receives a content data message addressed to a receiving device for a communication session between a source device and the receiving device. The intermediate device substitutes adapted content data for content data of the content data message and then sends the adapted content data to the receiving device such that it appears to the receiving device that the adapted content data originated from the source device. The communication from the source device to the receiving device is intercepted by the intermediate device in a manner that is transparent to the source device and receiving device.
Googleplus
Karl Gierach
Lived:
Irvine, CA
Work:
Voice Identity, Inc. - CEO
Education:
University of Illinois at Chicago
Youtube
video 2012 04 26 18 48 15
Karl Gierach of Voice Identity pitches at a TCVN Forum on April 26, 20...