Abstract: The disclosure relates to a method for recognizing at least one naturally emitted sound produced by a real-life sound source in an environment comprising at least one artificial sound source. The method is implemented by an audio recognition device, and it includes simultaneously obtaining a first audio signal from a first microphone located in the environment and a second audio signal from an audio acquisition device associated with the at least one artificial sound source; analyzing the first audio signal, delivering a first list of sound classes corresponding to sounds recognized in the first audio signal; analyzing the second audio signal, delivering a second list of sound classes corresponding to sounds recognized in the second audio signal; and delivering a third list of sound classes, comprising only sound classes included in the first list of sound classes which are not included in the second list of sound classes.

Abstract: A method and device is described and includes: obtaining an input audio signal associated with the voice input, obtaining a transcript resulting from the processing of the input audio signal, converting the transcript into a synthesized audio signal; extracting an acoustic feature of a same type from the input audio signal and synthesized audio signal, delivering a first sequence of features vectors associated with the input audio signal and a second sequence of features vectors associated with the synthesized audio signal converting the acoustic features to corresponding acoustic features associated with a target reference voice, delivering a first sequence and a second sequence of converted features vectors computing a dynamic time warping distance between the first sequence and second sequence of converted features vectors, and delivering data representative of a detection of an audio adversarial attack, as a result of a comparison between the dynamic time warping distance and a predetermined threshold.

Abstract: A method and device for detecting an audio adversarial attack with respect to a voice command processed by an automatic speech recognition system is described.

Abstract: The disclosure relates to a method for recognizing at least one naturally emitted sound produced by a real-life sound source in an environment comprising at least one artificial sound source. The method is implemented by an audio recognition device, and it includes simultaneously obtaining a first audio signal from a first microphone located in the environment and a second audio signal from an audio acquisition device associated with the at least one artificial sound source; analyzing the first audio signal, delivering a first list of sound classes corresponding to sounds recognized in the first audio signal; analyzing the second audio signal, delivering a second list of sound classes corresponding to sounds recognized in the second audio signal; and delivering a third list of sound classes, comprising only sound classes included in the first list of sound classes which are not included in the second list of sound classes.

Abstract: A method for detecting anomalies, the method being performed by a machine learning system configured for learning at least one model from a set of training data, the method including receiving sensor data from a plurality of N sensors, computing an anomaly prediction based on the sensor data and the at least one model, and if the anomaly prediction is an anomaly detection, sending an anomaly event containing said anomaly prediction. The method further includes receiving a user feedback relating to said anomaly event or to an absence of anomaly event, and adapting the at least one model based on the user feedback.

Abstract: The present disclosure proposes a solution to associate a device with a user by capturing a voice of a speaker by a microphone connected to the network device (e.g. a residential or home gateway), monitoring the IP traffic of the network device and detecting the device contributing to this IP traffic in order to establish a link between the speaker and his device(s) and associate the device with the speaker.

Abstract: The disclosure relates to a method for processing at least first and second audiovisual signals in a rendering system. Each of the first and second audiovisual signals include a video content and an audio content. The rendering system having a main display, an auxiliary display and a first audio output. The method includes: displaying the video content of the first audiovisual signal on the main display and the video content of the second audiovisual signal on the auxiliary display and playing the audio content of the first audiovisual signal on the first audio output, detecting an event in the audio content of the second audiovisual signal, and upon detection of the event, playing the audio content of the second audiovisual signal, instead of the audio content of the first audiovisual signal.

Abstract: A sensor including an integrated circuit and a piezoelectric substrate is described. The piezoelectric substrate is adapted as an antenna of an integrated circuit. The antenna may be an RFID antenna and the integrated circuit may be and RFID integrated circuit.

Abstract: The disclosure relates to a method for processing at least first and second audiovisual signals in a rendering system. Each of the first and second audiovisual signals include a video content and an audio content. The rendering system having a main display, an auxiliary display and a first audio output. The method includes: displaying the video content of the first audiovisual signal on the main display and the video content of the second audiovisual signal on the auxiliary display and playing the audio content of the first audiovisual signal on the first audio output, detecting an event in the audio content of the second audiovisual signal, and upon detection of the event, playing the audio content of the second audiovisual signal, instead of the audio content of the first audiovisual signal.

Abstract: A device and method for monitoring a first device proximity to a second device is disclosed. The first device is for example a smartphone and the second device is for example a wearable device. Proximity between both devices is monitored in conjunction with an electronic calendar so as to trigger an alert in case proximity between both devices is going to be lost while an event of the calendar is imminent.

Abstract: The present disclosure proposes a solution to associate a device with a user by capturing a voice of a speaker by a microphone connected to the network device (e.g. a residential or home gateway), monitoring the IP traffic of the network device and detecting the device contributing to this IP traffic in order to establish a link between the speaker and his device(s) and associate the device with the speaker.

Abstract: A method and apparatus for recognizing an activity of a monitored individual in an environment are described including receiving a first acoustic signal, performing audio feature extraction on the first acoustic signal in a first temporal window, classifying the first acoustic signal by determining a location of the monitored individual in the environment based on the extracted features of the first acoustic signal in the first temporal window, receiving a second audio signal, performing audio feature extraction of the second acoustic signal in a second temporal window and classifying the second acoustic signal by determining an activity of the monitored individual in the location in the environment based on the extracted features of the second acoustic signal in the second temporal window.

Abstract: A device and method for walker identification. An audio input interface obtains a sampled acoustic signal, possibly from a microphone, a vibration input interface obtains a sampled vibration signal, possibly from a geophone and at least one hardware processor fuses the sampled acoustic signal and the sampled vibration signal into a fused signal, extracts features from the fused signal and identifies a walker based on extracted features.

Abstract: An electronic apparatus includes a communication unit that communicates with a tag located within a target region when the communication unit is active within the target region, and a processor configured to monitor an activity within the target region based on status information from the tag received by the communication unit, wherein the activity comprises at least one of opening and closing of a member arranged within the target region

Abstract: A method of decoding an audio/video content transmitted over a broadband network. The method being based on the quick decoding of the first frames of a group of pictures without rendering them if the group of pictures arrives too late to be rendered synchronously with another audio/video content received through a broadcast network. The method allowing the synchronized rendering of contents respectively received over broadcast and broadband networks as soon as possible for the viewer.

Abstract: A radio frequency identification (RFID) reader identifies in which room among several rooms the RFID reader is more likely to be located. The RFID reader includes a transmitter for transmitting an interrogating radio frequency (RF) signal. It includes a receiver for receiving RF signals generated in corresponding pairs of RFID tags. The RFID tag pairs are attached to corresponding regions of each of the rooms. Each of said RFID tag pair including a first RFID tag and a second RFID tag that are spaced from each other by a distance that is larger or equal to ?/4 and smaller than or equal to ?/2 with respect to a frequency of a responding RF signal originated in the pair of RFID tags. A processor selects a larger RSSI of the RSSI's of the signal pair. The processor determines a corresponding sum of the RSSI's selected from each signal pair associated with each room. The processor evaluates in accordance with determined sums, the location in which said RFID reader is more likely to be located.

Abstract: An electronic apparatus includes a communication unit that communicates with a tag located within a target region when the communication unit is active within the target region, and a processor configured to monitor an activity within the target region based on status information from the tag received by the communication unit, wherein the activity comprises at least one of opening and closing of a member arranged within the target region.

Abstract: The invention relates to a storage device management method allowing to manage the storage space, on a storage device, by proposing to an end user to store a new content he was going to consume if its storage determined size is lower than an already stored content size.

Abstract: The invention discloses a method for reception of an audio-visual program transmitted via portions over a network, the method using a real-time transport protocol and a real-time control protocol between a server and a receiver, the audio-visual program being available on the server in a plurality of versions corresponding to the program coded in different resolutions and enabling its transmission at different bitrates according to requests of the receiver. The method comprising a regular measurement of the bandwidth of the network by the receiver in order to adjust the transmission bitrate according to the state of the network.

Abstract: A device and a method for controlling lighting conditions of a room. The room has at least one adjustable element that impacts the lighting conditions of the room. A multidirectional light sensor including a plurality of light sensors is arranged to capture the light intensity from a plurality of directions. The device obtains measurements from the multidirectional light sensor and adjusts the lighting conditions of the room. When the light in direction of the screen is higher than a first threshold, the device decreases the lighting conditions by sending a command to the adjustable element located in opposite direction to the screen. When the average value of light is lower than a second threshold, the device increases the lighting conditions by sending a command to at least one adjustable element of the room.