Abstract: Examples of the present disclosure relate to a particle beam dose profile measurement apparatus comprising a particle detector stack comprising a plurality of scintillator layers. Each scintillator layer of the detector stack is disposed along an axis of the apparatus such that the axis projects through each layer. Each scintillator layer is configured to produce scintillation light indicative of an energy deposition, in that scintillator, of a particle beam incident upon the detector stack along said axis. The apparatus comprises readout circuitry configured to measure the scintillation light of each scintillator layer; and dose profile determination circuitry configured to determine a dose profile of said particle beam within the detector stack. Said determining is based on the measured scintillation light of each scintillator layer, and a quenching correction.

Abstract: The redaction system and methods use primary triggers and secondary triggers to initiate redaction capabilities. A primary trigger is initiated when sensitive data is first detected and acts forward in time from the detection event. A secondary trigger is initiated at the end or during the timing of the first trigger and acts both backwards and forwards in time from its initiation. Combining the detection results from these two triggers allows confidence that all sensitive data is removed while avoiding false positives.

Abstract: The disclosed invention provide system and method to ensure resiliency in a network where audio capturing service experiences a failure on one or more active nodes. The network failover system is coupled to a Layer 3 (L3) network and communicates with a network switch through which network packets are transmitted. The failover system performs operations that include receiving network packets that are mirrored via the network switch, monitoring a primary node that captures audio data in the network packets, sending the network packets to a fallback node during an outage of the primary node, examining the network packets to determine which packets are audio-related packets, collecting audio-related packets, and storing the collected audio-related packets in a data storage. The fallback node is in the Layer 3 (L3) network.

Abstract: Examples of the present disclosure relate to a particle beam dose profile measurement apparatus comprising a particle detector stack comprising a plurality of scintillator layers. Each scintillator layer of the detector stack is disposed along an axis of the apparatus such that the axis projects through each layer. Each scintillator layer is configured to produce scintillation light indicative of an energy deposition, in that scintillator, of a particle beam incident upon the detector stack along said axis. The apparatus comprises readout circuitry configured to measure the scintillation light of each scintillator layer; and dose profile determination circuitry configured to determine a dose profile of said particle beam within the detector stack. Said determining is based on the measured scintillation light of each scintillator layer, and a quenching correction.

Abstract: A system, method and non-transitory computer readable medium for providing call quality driven communication management wherein an audio data stream of a communication session having one or more utterances is processed to generate a transcript of the communication session. The generated transcript is analyzed to determine whether a quality of the audio data stream, and one or more quality improvement measures when one or more audio artifacts are determined to be present in the audio data stream.

Abstract: The disclosed invention provides system and method to reconstruct metadata of audio outputs in which portions of metadata are missing. The system and method of the disclosed invention utilizes characteristics of speakers in audio outputs, voiceprints to identify speakers, and transcripts of the audio outputs to further analyze the audio outputs through machine learning process.

Abstract: A system, method and non-transitory computer readable medium for generating a voiceprint for a call participant are disclosed, wherein an audio recording or communication session is received, the quality of the audio recording is analyzed, and if determined to be of sufficient quality, the audio recording is separated into speech for each call participant, which may be further analyzed to generate a voiceprint for each participant. The voiceprint that is generated may be used to identify the participant in other historical recordings or in an active communications session, and upon such an identification, one or more compliance or data protection policies may be applied.

Abstract: A system, method and non-transitory computer readable medium for generating a voiceprint for a call participant are disclosed, wherein an audio recording or communication session is received, the quality of the audio recording is analyzed, and if determined to be of sufficient quality, the audio recording is separated into speech for each call participant, which may be further analyzed to generate a voiceprint for each participant. The voiceprint that is generated may be used to identify the participant in other historical recordings or in an active communications session, and upon such an identification, one or more compliance or data protection policies may be applied.

Abstract: The disclosed invention provide system and method to ensure resiliency in a network where audio capturing service experiences a failure on one or more active nodes. The network failover system is coupled to a Layer 3 (L3) network and communicates with a network switch through which network packets are transmitted. The failover system performs operations that include receiving network packets that are mirrored via the network switch, monitoring a primary node that captures audio data in the network packets, sending the network packets to a fallback node during an outage of the primary node, examining the network packets to determine which packets are audio-related packets, collecting audio-related packets, and storing the collected audio-related packets in a data storage. The fallback node is in the Layer 3 (L3) network.

Abstract: The disclosed invention provides system and method to reconstruct metadata of audio outputs in which portions of metadata are missing. The system and method of the disclosed invention utilizes characteristics of speakers in audio outputs, voiceprints to identify speakers, and transcripts of the audio outputs to further analyze the audio outputs through machine learning process.

Abstract: A system, method and non-transitory computer readable medium for providing call quality driven communication management wherein an audio data stream of a communication session having one or more utterances is processed to generate a transcript of the communication session. The generated transcript is analyzed to determine whether a quality of the audio data stream, and one or more quality improvement measures when one or more audio artifacts are determined to be present in the audio data stream.

Abstract: A packet switching system including a method for determining if a real time channel with inter-packet delay requirements can be admitted into the system is disclosed. A method and means for scheduling channels to send packets based on these inter-packet delay requirement is also presented. Variations to provide selected jitter requirements on packets are also disclosed.