Patents Examined by Akelaw Teshale
  • Patent number: 10348896
    Abstract: A facility and method for analyzing and classifying calls without transcription. The facility analyzes individual frames of an audio to identify speech and measure the amount of time spent in speech for each channel (e.g., caller channel, agent channel). Additional telephony metrics such as R-factor or MOS score and other metadata may be factored in as audio analysis inputs. The facility then analyzes the frames together as a whole and formulates a clustered-frame representation of a conversation to further identify dialog patterns and characterize call classification. Based on the data in the clustered-frame representation, the facility is able to make estimations of call classification. The correlation of dialog patterns to call classification may be utilized to develop targeted solutions for call classification issues, target certain advertising channels over others, evaluate advertising placements at scale, score callers, and to identify spammers.
    Type: Grant
    Filed: March 31, 2017
    Date of Patent: July 9, 2019
    Assignee: Marchex, Inc.
    Inventors: Chris Kolbegger, Jason Flaks, Tim Graber, Bryan Rieger, Ziad Ismail, Govindaraj Ramanathan, Darren Spehr, Matthew Berk
  • Patent number: 10341493
    Abstract: Techniques described herein are directed to utilizing an interposing phone number and associated phone tree to direct phone calls intended for a merchant to a customer-facing user interface that facilitates online requests to integrate multiple input channels (e.g., requests made by phone and requests made online) into a single output workflow. An interposing phone number provided by a third-party service can be associated with a merchant profile and an interposing phone tree can be implemented in association with an incoming call directed to the interposing phone number. A path of the interposing phone tree can cause a message including a link to be sent to a mobile device associated with the incoming call. Responsive to receiving an indication of activation of the link, an instruction can be sent to the mobile device causing a customer-facing user interface to be presented to enable a customer to interact with the merchant.
    Type: Grant
    Filed: June 29, 2018
    Date of Patent: July 2, 2019
    Assignee: Square, Inc.
    Inventor: Jeffrey Iacono
  • Patent number: 10334109
    Abstract: A virtual assistant application, system, and service that interacts with a caller over a telephone, cellular, or VoIP network as the called party's representative when the called party is unavailable, providing answers to queries and performing commands that were provisioned by the called party. The application includes a telephony interface, speech recognition and synthesis, a dialog manager, and knowledge domain. The application can also be configured to interact with a sender of SMS, MMS, or IM messages.
    Type: Grant
    Filed: December 14, 2016
    Date of Patent: June 25, 2019
    Assignee: Open Invention Network, LLC
    Inventor: Gerald McCobb
  • Patent number: 10334108
    Abstract: A virtual assistant application, system, and service that interacts with a caller over a telephone, cellular, or VoIP network as the called party's representative when the called party is unavailable, providing answers to queries and performing commands that were provisioned by the called party. The application includes a telephony interface, speech recognition and synthesis, a dialog manager, and knowledge domain. The application can also be configured to interact with a sender of SMS, MMS, or IM messages.
    Type: Grant
    Filed: December 14, 2016
    Date of Patent: June 25, 2019
    Assignee: Open Invention Network, LLC
    Inventor: Gerald McCobb
  • Patent number: 10325614
    Abstract: An example implementation may involve driving an audio output module of a wearable device with a first audio signal and then receiving, via at least one microphone of wearable device, a second audio signal comprising first ambient noise. The device may determine that the first ambient noise is indicative of user speech and responsively duck the first audio signal. While the first audio signal is ducked, the device may detect, in a subsequent portion of the second audio signal, second ambient noise, and determine that the second ambient noise is indicative of ambient speech. Responsive to the determination that the second ambient noise is indicative of ambient speech, the device may continue the ducking of the first audio signal.
    Type: Grant
    Filed: June 6, 2018
    Date of Patent: June 18, 2019
    Assignee: Google LLC
    Inventors: Anthony Michael Fadell, Simon Robert Prakash, Michael Kai Morishita, Shijing Xian, Chad Seguin
  • Patent number: 10320982
    Abstract: A system for determining the status of an answered telephone during the course of an outbound telephone call includes an automated telephone calling device for placing a telephone call to a location having a telephone number at which a target person is listed, upon the telephone call being answered, initiating a prerecorded greeting which asks for the target person and receiving a spoken response from an answering person and a speech recognition device for performing a speech recognition analysis on the spoken response to determine a status of the spoken response. If the speech recognition device determines that the answering person is the target person, the speech recognition device initiates a speech recognition application with the target person.
    Type: Grant
    Filed: November 17, 2017
    Date of Patent: June 11, 2019
    Assignee: ELIZA CORPORATION
    Inventors: Lucas Merrow, Alexandra Drane, John Krocker, Oleg Boulanov, Nasreen R. Quibria, Michael R. Robinson
  • Patent number: 10320979
    Abstract: A device may receive, from a server device, a request for an initial action associated with an interactive voice response (IVR) service. The request may include a service identifier. The device may obtain a set of code segments for an IVR application that supports the IVR service by using the service identifier to search a data structure. The set of code segments may be associated with logic of the IVR application. The device may provide instructions associated with an initial code segment to the server device to cause the server device to execute the initial action via a communication with a user device. The device may selectively provide, to the server device, instructions associated with another code segment to cause the server device to execute a next action via the communication with the user device.
    Type: Grant
    Filed: September 8, 2017
    Date of Patent: June 11, 2019
    Assignee: Verizon Patent and Licensing Inc.
    Inventors: Michael Brimshan, Robert Paul Pittman, Rakshit Yagnik
  • Patent number: 10310803
    Abstract: A modular speaker system comprises a first speaker module; at least one second speaker module in communication with the first speaker module; and a controller that receives an instruction to selectively activate, reactivate, or inactivate the at least one second speaker module with respect to the first speaker module.
    Type: Grant
    Filed: September 2, 2016
    Date of Patent: June 4, 2019
    Assignee: BOSE CORPORATION
    Inventor: Lino Antony Pucci
  • Patent number: 10305438
    Abstract: A method for generating adaptive notifications include analyzing, at a user device, a spectrum of environmental noise. A portion of the spectrum for adaptive notification enhancement is selected based on the analyzing the spectrum of environmental noise. An adapted notification is generated at the user device by enhancing the selected portion of the spectrum. The adapted notification is transmitted at the user device.
    Type: Grant
    Filed: December 5, 2017
    Date of Patent: May 28, 2019
    Assignee: BlackBerry Limited
    Inventors: John Patrick Grenn, Nazih Almalki, Bradley Ferringo
  • Patent number: 10306061
    Abstract: This disclosure describes techniques for establishing a voice authentication credential for an authenticated user of a mobile device. Techniques in accordance with one or more aspects of the present disclosure may enable use of an interactive voice response (IVR) system for creating a voice authentication credential for a user of a computing device, such as a mobile phone. In one example, a method includes receiving authentication data from a computing device; authenticating a user operating the computing device; storing session data associated with the computing device; outputting instructions for communicating with an interactive voice response (IVR) system; receiving information from the IVR system; determining that the computing device has used the instructions to communicate with the IVR system; and enabling the IVR system to establish a voice authentication credential for the user of the computing device.
    Type: Grant
    Filed: June 16, 2017
    Date of Patent: May 28, 2019
    Assignee: Wells Fargo Bank, N.A.
    Inventors: Daniel S. Sumner, Douglas Innocenti
  • Patent number: 10282160
    Abstract: An apparatus and method for generating audio data and an apparatus and method for playing audio data may be disclosed, in which the apparatus for playing the audio data may extract a descriptor related to a multichannel audio signal from a bitstream generated by the apparatus for generating the audio data, and play the multichannel audio signal, based on the extracted descriptor, and the descriptor may include information on an audio signal included in the multichannel audio signal.
    Type: Grant
    Filed: November 3, 2017
    Date of Patent: May 7, 2019
    Assignees: Electronics and Telecommunications Research Institute, NIPPON HOSO KYOKAI
    Inventors: Jae Hyoun Yoo, Tae Jin Lee, Kyeong Ok Kang, Kaoru Watanabe, Satoshi Oode, Ikuko Sawaya
  • Patent number: 10284934
    Abstract: A loudspeaker system can have first and second loudspeakers selectively operable in a single-channel mode or in a multi-channel mode. In the single-channel mode, the first and the second loudspeakers are configured to simultaneously reproduce a substantially identical signal. In the multi-channel mode, the first loudspeaker reproduces a first-channel signal and the second loudspeaker reproduces a second-channel signal. The first-channel signal and the second-channel signal can constitute respective portions of a multi-channel signal. Such loudspeaker systems can also have a mode selector configured to select one of the single-channel mode and the multi-channel mode. In some embodiments, such selection can occur in response to one or more detected proximities of another loudspeaker system. Multi-zone loudspeaker systems are also disclosed.
    Type: Grant
    Filed: November 14, 2017
    Date of Patent: May 7, 2019
    Assignee: Apple Inc.
    Inventors: Vincenzo Giuliani, David Jeon, Gabriel Sanchez
  • Patent number: 10275209
    Abstract: Ambient sound is converted into an ambient audio stream. A processed ambient audio stream is generated by processing the ambient audio stream in accordance with a selected set of processing parameters selected from the plurality of processing parameter sets stored in the memory. Trigger data is searched and a new set of processing parameters is requested. The trigger data identifies the new set of processing parameters that is available for use in processing the ambient audio stream. A received new set of processing parameters is selected as the selected set of processing parameters. The processed ambient audio stream is converted into processed output sound.
    Type: Grant
    Filed: December 19, 2016
    Date of Patent: April 30, 2019
    Assignee: Dolby Laboratories Licensing Corporation
    Inventors: Gints Klimanis, Noah Kraft, Matthew J. Jaffe, Richard Fritz Lanman, III, Jeffrey Baker
  • Patent number: 10263664
    Abstract: Embodiments of the present invention provide a signal transmission method. The method includes: sequentially rotating phases of to-be-sent signals on a line set 1 by different angles and in relative to phases of to-be-sent signals on a line set 2, and sequentially sending, to a user side, the to-be-sent signals whose phases are rotated. The method also includes receiving a rotation factor that is of a high-quality received signal on the line set 1 and that is fed back by the user side, where the high-quality received signal includes a received signal with a high signal-to-noise ratio or high power. The method also includes using the rotation factor fed back by the user side as a fixed rotation factor, and rotating, according to the fixed rotation factor, a phase of a signal to be subsequently sent on the line set 1.
    Type: Grant
    Filed: April 24, 2017
    Date of Patent: April 16, 2019
    Assignee: Huawei Technologies Co., Ltd.
    Inventors: Fanglin Sun, Bin Zhou, Shicai Chen
  • Patent number: 10264120
    Abstract: A device may generate a call plan for a set of testing calls. The device may initiate a testing call to a communication device associated with a target, of the set of targets, using a user profile of the set of user profiles. The device may initiate monitoring for the testing call to identify information associated with the target during the testing call. The device may generate one or more responses to one or more queries based on the user profile. The device may transmit the one or more responses to the one or more queries based on generating the one or more responses to the one or more queries. The device may process stored data regarding testing calls to generate a recommendation relating to the set of targets for the set of testing calls. The device may communicate with one or more other devices to implement the recommendation.
    Type: Grant
    Filed: December 30, 2016
    Date of Patent: April 16, 2019
    Assignee: Accenture Global Solutions Limited
    Inventors: Avigail Goldgraber, Andrew H. Scott, Lora Leigh Nunnelley, Eric Citron
  • Patent number: 10264333
    Abstract: A dual-tone multi-frequency (DTMF) decoder may decode DTMF symbols received in an audio input and transfer the symbols to a buffer. A volume accumulator may determine whether the audio input includes audio with volume above a predetermined threshold. The buffer may receive instructions from the timer or volume accumulator to transfer stored DTMF symbols to a filter, which may identify a characteristic of information conveyed by the DTMF symbols and send the identified characteristic information to an output device. The timer may determine a time associated with when each DTMF symbol was received and transfer each associated time to the buffer, which may transfer each associated time to a group boundary detector that may determine a predetermined number of longest time durations in between the DTMF symbols. The presence of a predetermined number of longest time durations in between the DTMF symbols may indicate a telephone number format.
    Type: Grant
    Filed: November 17, 2017
    Date of Patent: April 16, 2019
    Inventor: Steven Eric Presser
  • Patent number: 10235364
    Abstract: An interpretation distributing device includes: an interpreted voice acquiring unit that acquires at least one piece of interpreted voice data of two or more pieces of interpreted voice data which are voice data obtained by interpreting voice in a first language into voice in two or more different languages; and an interpreted voice transmitting unit that transmits at least one piece of the interpreted voice data acquired by the interpreted voice acquiring unit to one or more terminal devices.
    Type: Grant
    Filed: April 11, 2016
    Date of Patent: March 19, 2019
    Assignee: SHIN TRADING CO., LTD.
    Inventor: Jungbum Shin
  • Patent number: 10237387
    Abstract: Incoming call recording method and device for a multi-channel terminal are provided. The method includes: receiving a service request associated with a current subscriber identity card, and the service request comprises a called service request to a current subscriber which is identified by the current subscriber identity card; and in response to the service request, setting up a first service channel for making a call and starting recording based on an instruction of the current subscriber, and the first service channel is set up based on the current subscriber identity card. Service data transmitted by a remote terminal of the service request may be recorded based on the first service channel, so that a subscriber can know a missed incoming call when the subscriber is inconvenient to listen to the incoming call, which may greatly improve user experience.
    Type: Grant
    Filed: November 13, 2017
    Date of Patent: March 19, 2019
    Assignee: SPREADTRUM COMMUNICATIONS (SHANGHAI) CO., LTD.
    Inventors: Xichun Gao, Xianliang Chen, Yi He, Jinjin Ni, Yiguo Zhao
  • Patent number: 10219070
    Abstract: Invention relates to the field of acoustic systems used to convert electrical signal into sound, and the design of the housing where the electroacoustic loudspeaker is mounted and may be used in household and industrial applications as an acoustic system. The acoustic transducer has a housing, made from coconut endocarp, containing at least one opening for mounting a loudspeaker, and can have additional openings for wires and/or connectors to the signal source, sound-absorbing or dampening materials, mounting elements, for example, hooks for mounting with use of a flexible cord or any other similar fastening elements, connectors, phase inverter, electronics unit, protective decorative mesh or cloth. The proposed acoustic system provides improved sound quality by reducing the level of parasitic acoustic resonances, excited by the loudspeaker in the housing during sound generation by the loudspeaker's membrane.
    Type: Grant
    Filed: November 14, 2016
    Date of Patent: February 26, 2019
    Inventor: Maksim Viktorovich Chyzhov
  • Patent number: 10210869
    Abstract: A system, device and method for validating a 911 caller is provided. A recording is received that includes a voice sample of a caller, the recording associated with an incident. A voiceprint for the caller is generated from the voice sample. A communication device of a responder responding to the incident is identified. An indication of the voiceprint for the caller is transmitted to the communication device, to cause: a comparison of the voiceprint with sound received at the communication device; and, in response to the comparison, an initiation of an action.
    Type: Grant
    Filed: December 21, 2017
    Date of Patent: February 19, 2019
    Assignee: MOTOROLA SOLUTIONS, INC.
    Inventors: Melanie A. King, Scott M. Alazraki