Abstract: A plurality of talker embedding vectors may be derived that correspond to a plurality of talkers in an input audio stream. Each talker embedding vector may represent respective voice characteristics of a respective talker. The talker embedding vectors may be generated based on, for example, a pre-enrollment process or a cluster-based embedding vector derivation process. A plurality of instances of a personalized noise suppression model may be executed on the input audio stream. Each instance of the personalized noise suppression model may employ a respective talker embedding vector. A plurality of single-talker audio streams may be generated by the plurality of instances of the personalized noise suppression model. A plurality of single-talker transcriptions may be generated based on the plurality of single-talker audio streams. The plurality of single-talker transcriptions may be merged into a multi-talker output transcription.

Abstract: Real-time low-complexity stereo speech enhancement with spatial cue preservation may be performed. A stereo speech enhancement system receives a stereo input signal (e.g., a left and right input signal). The stereo speech enhancement system estimates spatial cues for a target speaker and downmixes the stereo input signal into a monaural signal. A low-complexity model may then process the monaural signal to generate an enhanced monaural signal. The stereo speech enhancement system upmixes the enhanced monaural signal based on the estimated spatial cues for the target speaker, to generate an enhanced stereo output signal.

Abstract: A plasma processing apparatus includes: a detector configured to detect a change in an intensity of light emission from plasma formed inside a processing chamber; and a unit configured to adjust conditions for forming the plasma or processing a wafer arranged inside the processing chamber using an output from the detector, wherein the detector detects a signal of the intensity of light emission at plural time instants before an arbitrary time instant during processing, and wherein the adjusting unit removes the component of a temporal change of a long cycle of the intensity of light emission from this detected signal and detects the component of a short temporal change of the intensity of light emission, and adjusts the conditions for forming the plasma or processing a wafer arranged inside the processing chamber based on the short temporal change of the detected intensity of light emission.

Abstract: A control system includes: a moving object; and a control apparatus. The moving object is configured to: determine a face direction based on whether or not a face image of the human exists; and control the movement apparatus so that the moving object moves in accordance with path information. The control apparatus is configured to: detect a position of the human and the moving object in the area; calculate, based on the position of the human and the moving object, and the face direction, the path information for allowing the moving object to arrive at any one of a position within a predetermined range from the human and in a field of view of the human and a position within the predetermined range from the human and outside the field of view of the human; and transmit the path information to the moving object.

Abstract: Disclosed is a method for synchronizing visual information and auditory information characterized by extracting visual information included in video, recognizing auditory information in a first language that is included in a speech in the first language, associating the visual information with the auditory information in the first language, translating the auditory information in the first language to auditory information in a second language, and editing at least one of the visual information with the auditory information in the second language so as to associate the visual information and the auditory information in the second language with each other.

Abstract: A sound signal processing method and device are provided for separating sounds of the respective sound sources even when sounds are recorded asynchronously by a plurality of devices. Specifically, the present invention comprises the steps of instructing each of the plurality of devices to output a reference signal of a different frequency, receiving each of the reference signals output from the speaker of the plurality of devices according to the instruction, receiving sound signals in which each of the reference signals output from the speaker of the plurality of devices is input into the microphone of the plurality of devices, calculating a time shift amount of each of the devices based on each of the received reference signals output from the speaker and the received sound signals, and separating the plurality of signal signals input into the microphone of the plurality of devices based on the calculated time shift amount.

Abstract: Example implementations described herein are directed to a dialog system with self-learning natural language understanding (NLU), involving a client-server configuration. If the NLU results in the client is not confident, the NLU will be done again in the server. In the dialog system, the human user and the system communicate via speech or text information. The examples of such products include robots, interactive voice response system (IVR) for call centers, voice-enabled personal devices, car navigation system, smart phones, and voice input devices in the work environments where the human operator cannot operate the devices by hands.

Abstract: A control apparatus is configured to execute: acquisition processing of acquiring, from at least one data acquisition apparatus, as data on a second object, time series data on a series of pieces of information on the second object that has been collected since the at least one data acquisition apparatus detected the second object; determination processing of determining whether or not the first and the second object are identical to each other based on information on the first and the second object; and storage processing of storing, when the determination processing results that the first and the second object are/aren't identical to each other, the data on the second object and the data on the first object in association with/without each other, and when the determination processing results in a determination that the first object and the second object are not identical to each other.

Abstract: Example implementations described herein are directed to a dialog system with self-learning natural language understanding (NLU), involving a client-server configuration. If the NLU results in the client is not confident, the NLU will be done again in the server. In the dialog system, the human user and the system communicate via speech or text information. The examples of such products include robots, interactive voice response system (IVR) for call centers, voice-enabled personal devices, car navigation system, smart phones, and voice input devices in the work environments where the human operator cannot operate the devices by hands.

Abstract: A sound signal processing method and device are provided for separating sounds of the respective sound sources even when sounds are recorded asynchronously by a plurality of devices. Specifically, the present invention comprises the steps of instructing each of the plurality of devices to output a reference signal of a different frequency, receiving each of the reference signals output from the speaker of the plurality of devices according to the instruction, receiving sound signals in which each of the reference signals output from the speaker of the plurality of devices is input into the microphone of the plurality of devices, calculating a time shift amount of each of the devices based on each of the received reference signals output from the speaker and the received sound signals, and separating the plurality of signal signals input into the microphone of the plurality of devices based on the calculated time shift amount.

Abstract: Disclosed is a method for synchronizing visual information and auditory information characterized by extracting visual information included in video, recognizing auditory information in a first language that is included in a speech in the first language, associating the visual information with the auditory information in the first language, translating the auditory information in the first language to auditory information in a second language, and editing at least one of the visual information with the auditory information in the second language so as to associate the visual information and the auditory information in the second language with each other.

Abstract: A control system includes: a moving object; and a control apparatus. The moving object is configured to: determine a face direction based on whether or not a face image of the human exists; and control the movement apparatus so that the moving object moves in accordance with path information. The control apparatus is configured to: detect a position of the human and the moving object in the area; calculate, based on the position of the human and the moving object, and the face direction, the path information for allowing the moving object to arrive at any one of a position within a predetermined range from the human and in a field of view of the human and a position within the predetermined range from the human and outside the field of view of the human; and transmit the path information to the moving object.

Abstract: A plasma processing device performing etching processing to a sample disposed in a processing chamber disposed in a vacuum vessel by using plasma formed in the processing chamber includes a light detector, a component detector, and a determination unit. The light detector detects light intensity of a plurality of wavelengths from the inside of the processing chamber at a plurality of times during the sample processing. The component detector detects, by using a result of a principal component analysis of time-series data, a highly correlated component between the time-series data of a plurality of the wavelengths at a certain time in a plurality of the times obtained from output of the light detector. The determination unit determines an amount or an end point of the etching processing based on a change in light intensity of at least one of a plurality of the wavelengths detected by using the time-series data from which the highly correlated component is removed.

Abstract: A control apparatus is configured to execute: acquisition processing of acquiring, from at least one data acquisition apparatus, as data on a second object, time series data on a series of pieces of information on the second object that has been collected since the at least one data acquisition apparatus detected the second object; determination processing of determining whether or not the first and the second object are identical to each other based on information on the first and the second object; and storage processing of storing, when the determination processing results that the first and the second object are/aren't identical to each other, the data on the second object and the data on the first object in association with/without each other, and when the determination processing results in a determination that the first object and the second object are not identical to each other.

Abstract: A plasma processing apparatus includes: a detector configured to detect a change in an intensity of light emission from plasma formed inside a processing chamber; and a unit configured to adjust conditions for forming the plasma or processing a wafer arranged inside the processing chamber using an output from the detector, wherein the detector detects a signal of the intensity of light emission at plural time instants before an arbitrary time instant during processing, and wherein the adjusting unit removes the component of a temporal change of a long cycle of the intensity of light emission from this detected signal and detects the component of a short temporal change of the intensity of light emission, and adjusts the conditions for forming the plasma or processing a wafer arranged inside the processing chamber based on the short temporal change of the detected intensity of light emission.

Abstract: A plasma processing apparatus includes: a detector configured to detect a change in an intensity of light emission from plasma formed inside a processing chamber; and a unit configured to adjust conditions for forming the plasma or processing a wafer arranged inside the processing chamber using an output from the detector, wherein the detector detects a signal of the intensity of light emission at plural time instants before an arbitrary time instant during processing, and wherein the adjusting unit removes the component of a temporal change of a long cycle of the intensity of light emission from this detected signal and detects the component of a short temporal change of the intensity of light emission, and adjusts the conditions for forming the plasma or processing a wafer arranged inside the processing chamber based on the short temporal change of the detected intensity of light emission.

Abstract: A plasma processing device performing etching processing to a sample disposed in a processing chamber disposed in a vacuum vessel by using plasma formed in the processing chamber includes a light detector, a component detector, and a determination unit. The light detector detects light intensity of a plurality of wavelengths from the inside of the processing chamber at a plurality of times during the sample processing. The component detector detects, by using a result of a principal component analysis of time-series data, a highly correlated component between the time-series data of a plurality of the wavelengths at a certain time in a plurality of the times obtained from output of the light detector. The determination unit determines an amount or an end point of the etching processing based on a change in light intensity of at least one of a plurality of the wavelengths detected by using the time-series data from which the highly correlated component is removed.

Abstract: In a conventional dereverberation system, when there is a fluctuating reverberation component, it has been difficult to determine, with high accuracy, a linear dereverberation filter for removing a non-fluctuating reverberation component. An algorithm integrating a dereverberation system using a linear filter and a dereverberation system using a non-linear filter includes the function of measuring the amount of fluctuation in transfer function in a latter-stage non-linear filter over time, and controls the strength of the non-linear filter over time based on the function. In this configuration, a strong non-linear process is implemented only when the fluctuation in transfer function is large, whereby distortion in speech components can be minimized.

Abstract: There is a tendency of the intensity and the shape of a spectrum to be measured transitioning with the passage of measured time, depending on the volatility and the reactivity of a component. A mass spectrometric system includes: a mass spectrometric unit that measures a specimen and outputs a mass spectrum; and an estimator that has an estimation rule on content information, the estimation rule being assigned to each component and each measurement time. The estimator estimates, based on a mass spectrum output from the mass spectrometric unit, content information on each component of a plurality of components that may be contained in the specimen in accordance with the estimation rule.

Abstract: A plasma processing apparatus includes: a detector configured to detect a change in an intensity of light emission from plasma formed inside a processing chamber; and a unit configured to adjust conditions for forming the plasma or processing a wafer arranged inside the processing chamber using an output from the detector, wherein the detector detects a signal of the intensity of light emission at plural time instants before an arbitrary time instant during processing, and wherein the adjusting unit removes the component of a temporal change of a long cycle of the intensity of light emission from this detected signal and detects the component of a short temporal change of the intensity of light emission, and adjusts the conditions for forming the plasma or processing a wafer arranged inside the processing chamber based on the short temporal change of the detected intensity of light emission.