Abstract: Internet Protocol captioned telephone service often utilizing Automated Speech Recognition has the capability of transcribing both sides of a conversation. Text bubbles can grow as the speech continues until a break. Synchronization among various user devices can occur during or after calls amongst devices including with the far end caller for some embodiments. A user can allow a call to go to voicemail and see the text and decide whether or not to pick up with transcription continuing for some embodiments.

Abstract: A mobile communication device that comprises a microphone, a speaker, an input output port and one or more modules; wherein the microphone is configured to receive, during a conference call, (a) an acoustic signal from a first person, and (b) a cross echo from a speaker of another mobile communication device that participates in the conference call, the cross echo is generated as a result of the acoustic signal from the first person; and wherein the one or more modules are configured to cancel the cross echo based, at least in part, of the acoustic signal of the first person.

Abstract: According to an aspect, a method for multi-channel echo cancellation includes receiving a microphone signal and a multi-channel loudspeaker driving signal. The multi-channel loudspeaker driving signal includes a first driving signal that drives a first loudspeaker, and a second driving signal that drives a second loudspeaker. The first driving signal is substantially the same as second driving signal. The microphone signal includes a near-end signal with echo. The method includes determining a unique solution for acoustic transfer functions for a present acoustic scenario based on the microphone signal and the multi-channel loudspeaker driving signal. The acoustic transfer functions include first and second acoustic transfer function. The unique solution is determined based on time-frequency transforms of observations from the present acoustic scenario and at least one previous acoustic scenario.

Abstract: Disclosed is a technique for estimating crosstalk between a first and second electrical transmission lines. The method comprises obtaining measurements of a received near end crosstalk, NEXT, signal, the NEXT signal being received at a first end of the second transmission line over a time period as a result of an electrical signal sent onto the first transmission line from its first end, the obtained measurements being in the time domain. Subsequently, a crosstalk coupling estimate is obtained per transmission line sub-interval by compensating the obtained measurements in the time domain of the received NEXT signal for round-trip attenuation of the sent signal from the first end of the first line to the sub-interval and back to the first end of the second line, and an estimate of a total crosstalk coupling is obtained by adding together at least some of the obtained crosstalk coupling estimates per transmission line sub-interval.

Abstract: Systems and methods are provided for attribute-based client callbacks. A client is prompted to leave a voice message. Attributes are extracted from the voice message and, based on the attributes, tokens created for the selection of an appropriate agent is connected to the client, such as having skills or attributes matching one or more tokens. A callback application server transmits prompts and receives requests for client callbacks. an interaction manager determines agent availability and arranges callback handling, and a session management server initiates callbacks to connect the selected agent with the client.

Abstract: Ringing suppression may be provided. First, a first ringing suppressor in a first branch of an amplifier may cancel interference from a second branch of the amplifier using a transmitted signal from the second branch as a reference. The first ringing suppressor may also cancel echo interference from the first branch of the amplifier using an output of the first ringing suppressor in the first branch as a reference. Furthermore, a second ringing suppressor in the second branch of the amplifier may cancel interference from the first branch of the amplifier using a transmitted signal from the first branch as a reference. Furthermore, the second ringing suppressor may cancel echo interference from the second branch of the amplifier using an output of the second ringing suppressor in the second branch as a reference.

Abstract: An echo is allowed to be effectively removed while a processing load on an arithmetic device is reduced. When a magnitude of a reference signal transmitted to a speaker is equal to or greater than a first threshold, a learning algorithm using nonlinear processing is selected. When the magnitude of the reference signal is smaller than the first threshold, a learning algorithm using linear processing is selected. The echo is learnt using the selected learning algorithm to remove an echo included in an input signal picked up by a microphone based on a learning result.

Abstract: A method to transcribe communications includes obtaining an audio message from a first device during a voice communication session with a second device including a display screen, providing the message to a first speech recognition system to generate a first message transcript, providing the transcript to the second device for presentation on the screen, obtaining an indication that a transcript quality is below a threshold, providing, in response, the message to a second system to generate a second transcript while still providing it to the first system to generate the first transcript and providing the first transcript to the second device for presentation on the display screen, and in response to an event occurring that indicates the second transcript is to be provided to the second device instead of the first transcript, providing the second transcript to the second device for presentation on the screen instead of the first transcript.

Abstract: Operations related to performing gain operations with respect to a receive-path signal of a first device may be performed. The operations may include obtaining the receive-path signal, which includes an echo speech signal and a receive speech signal originating at a second device. In addition, the operations may include identifying a portion of the receive-path signal that includes, at a particular time, a first frequency component that corresponds to the echo speech signal and a second frequency component that corresponds to the receive speech signal in which the first frequency component is different from the second frequency component. Moreover, the operations may include attenuating the first frequency component of the portion while avoiding attenuating the second frequency component of the portion based on the first frequency component corresponding to the echo speech signal and the second frequency component corresponding to the receive speech signal.

Abstract: A double talk detection method, a double talk detection apparatus and an echo cancellation system are provided. The double talk detection method comprises: determining, according to an energy ratio between a far-end digital voice signal and a near-end digital voice signal, and a frequency coherence value between the near-end digital voice signal and the far-end digital voice signal, whether a near-end speaker's digital voice signal is present in the near-end digital voice signal. The double talk detection method avoids missing detection and false detection, improves the accuracy of double talk detection, cancels the echo in the near-end voice signal thoroughly when applied in the field of echo cancellation, and improves the communication experience of both talk parties.

Abstract: The following disclosure provides a method and a receiving interface device (200) configured to perform the method for grouping received alarm calls generated by or in connection to the same alarm event, wherein said alarm call being a voice call or/and data/text message. The receiving interface device is a part of an Alarm Receiving Centre (100) for enabling the reception of alarm call alarm calls sent by means of VoIP or SIP, and wherein said receiving interface device comprises said device comprising a processor in a processing circuitry (210) being operative to perform the steps of the method.

Abstract: A method for passive enrollment and identification of one or more speakers in an audio file includes automatically converting audio data to a format suitable for biometric processing, separating different channels present in the converted audio data separating speakers in the converted audio data, generating audio files specific to individual speakers in the converted audio data, iteratively grouping the audio files of individual speakers according to a predetermined matching criteria, creating biometric voice prints from the groups of audio files, and authenticating speakers in the biometric voice prints by comparing the biometric voice prints to entries in a biometric voice print database.

Abstract: A signal processor for performing signal enhancement, the signal processor comprising: an input-terminal, configured to receive an input-signaling; an output-terminal; an interference-cancellation-block configured to receive the input-signaling and to provide an interference-estimate-signaling and an interference-cancelled-signal based on the input-signaling. The signal processor further comprises a feature-block configured to provide a combination-feature-signal based on the interference-cancelled-signal and the interference-estimate-signaling; and a neural-network-block configured to apply model parameters to the combination-feature-signal to provide a neural-network-output-signal to the output-terminal.

Abstract: A method for initialization of a group of customer premises equipment devices (CPEs) during a training that registers capabilities of the CPEs is disclosed, wherein at least one CPE registers late to the training and cannot be registered. The method includes determining capabilities of the CPEs during a joining phase of the training, wherein it is determined whether a CPE device is capable of employing vectoring, and placing in a hold status the at least one CPE that registers late by keeping a line active that is coupled to the at least one CPE. The method further includes providing another joining phase after the joining phase to register the at least one CPE that registers late.

Abstract: Disclosed are an acoustic echo cancelling apparatus and an acoustic echo cancelling method. The acoustic echo cancelling apparatus comprises a first capturer configured to capture a remote audio signal received from a remote machine; a second capturer configured to capture a local audio signal that is input to a local microphone; an acoustic echo canceller (AEC) configured to cancel an acoustic echo of the local audio signal using the remote audio signal and output a local audio signal from which the acoustic echo is cancelled; and a transmitter configured to transmit an output signal of the AEC to the remote machine.

Abstract: A method and a system for allocating vehicles to passengers in a ride-sharing system is provided. A passenger utilizes a passenger device to initiate a first phone call for booking a ride. The first phone call is initiated on a phone number associated with a pick-up location of the passenger. The first phone call is automatically disconnected, and a second phone call is established with the passenger device for providing a set of options selectable by the passenger. Based on an option selected by the passenger, a share-ride fare of the ride is communicated to the passenger during the second phone call. Based on the communicated share-ride fare, the passenger confirms the booking for the ride. In response to the confirmation of the booking for the ride, a vehicle is allocated to the passenger.

Abstract: A system and method for an optimized, self-learning and self-organizing contact center has been developed. This system and method uses principles and tools of information theory, including the latent Dirichlet allocation which reduces information to specific predetermined topics and a distribution of topic related words to infer its hidden, generative underpinnings so to self-organize a contact center, infer its desired electronic versus human make up, and optimally route all customer requests to an electronic resource or a specific human agent best suited to respond to the request for maximal business value per interaction.

Abstract: Techniques for automatically prompting a calling user to send a message to a called user, the calling user using a calling device and the called user using a called device, the method including receiving, at a processor in the calling device, an indication that a call from the calling device to the called device has disconnected, determining, at the processor in the calling device, whether the call connected before receiving the indication that the call has disconnected, and in response to determining that the call did not connect before receiving the indication that the call has disconnected, determining that the call was a missed call.

Abstract: In a voice response unit (VRU) that is one of a plurality of VRU's, a call flow can be selected for an inbound voice call based on an identifier for the inbound voice call. A parameter can then be written to at least one directory server, the parameter specified to replace a default parameter for the selected call flow. The selected call flow can be invoked according to the parameter.

Abstract: A smart voice system is disclosed. The smart voice system includes a data receiving module, a voice message receiving module, a voice response module and a voice message output module. The data receiving module receives a hearing evaluation data of a user, and acquiring a hearing parameter according to the hearing evaluation data. The voice message receiving module receives a voice message inputted by the user. The voice response module acquires a response voice message corresponding to the voice message and the frequency of the response voice message is adjusted according to the hearing parameter. The voice message output module outputs the response voice message.