Abstract: An acoustic reproduction method includes: obtaining information indicating sounds that reach a listener in a sound reproduction space and direction information indicating a direction in which the head of the listener is oriented; judging whether a first direction in which a first sound reaches the listener and a second direction in which a second sound reaches the listener are in plane symmetry with respect to a predetermined plane that passes through both ears of the listener and is perpendicular to the direction in which the head of the listener is oriented, the first and the second sounds being included in the sounds indicated in the information obtained; performing processing on sound information indicating the second sound when the first and the second directions are judged to be in plane symmetry, the processing being change processing of changing the second direction; and outputting the sound information subjected to the change processing.

Abstract: An information processing method includes: obtaining spatial information indicating a shape of a virtual space including an obstacle and a sound source object that emits a predetermined sound; obtaining position information indicating a position and an orientation of a user in the virtual space; and generating an acoustic virtual environment by determining, based on the position and the orientation of the user and a position of the obstacle in the virtual space, a position of a virtual reflection surface off which the predetermined sound is reflected in the virtual space.

Abstract: An information processing method includes: obtaining a stream including (i) first position and orientation information indicating a position and an orientation of a sound source and (ii) a sound signal indicating a sound that the sound source outputs; obtaining second position and orientation information indicating a position and an orientation of a head of a user; and making a correction to reduce a rate of change at which a speed of the position or the orientation indicated in the second position and orientation information obtained changes relative to the position or the orientation of the sound source indicated in the first position and orientation information, to obtain the second position and orientation information to be used for three-dimensional sound processing to be performed using the first position and orientation information and the second position and orientation information on the sound signal.

Abstract: An information processing method includes: obtaining sound information that includes (i) a first audio signal and (ii) space information that is information for reproducing a virtual space and includes first data relating to a first structure disposed in the virtual space, the virtual space including the first structure and a sound source; generating second data based on the first data, each of the first data and the second data being associated with a position in the virtual space, the second data being data having a smaller amount of data than the first data; calculating a propagation distance of sound from the sound source, the sound being reflected at the position associated with the second data and arriving at a position of a listener; and generating a second audio signal subjected to stereoacoustic processing, using the first audio signal and the propagation distance.

Abstract: An information processing method includes: obtaining a stream including (i) first position and orientation information indicating a position and an orientation of a sound source and (ii) a sound signal indicating a sound that the sound source outputs; obtaining second position and orientation information indicating a position and an orientation of a head of a user; and setting a spatial resolution for three-dimensional audio processing to be performed on the sound signal, according to a positional relationship between the head of the user and the sound source and using the first position and orientation information and the second position and orientation information.

Abstract: An information processing method includes: (i) determining whether a type of a predetermined sound and a type of an external sound match; (ii) determining whether the incoming direction of the predetermined sound and the incoming direction of the external sound overlap by comparing the incoming direction of the predetermined sound with the incoming direction of the external sound analyzed; and performing at least one of the following based on a result of (i) and a result of (ii): (a) adjusting at least one of a sound pressure of the predetermined sound or a sound pressure of the external sound; or (b) adjusting the incoming direction of the predetermined sound.

Abstract: An information processing method includes: calculating an angular amount of change in a predetermined direction in a time domain from sound information including information regarding a predetermined sound and information regarding the predetermined direction; selecting, based on the information regarding the predetermined direction, a 3D sound filter for causing an inputted sound to be perceived as a sound coming from an incoming direction from among 3D sound filter candidates each prepared for a different incoming direction; and generating an output sound signal by inputting the information regarding the predetermined sound to the 3D sound filter selected, in which, when the angular amount of change calculated is less than a threshold, the selecting a 3D sound filter includes determining the 3D sound filter such that the predetermined sound is more strongly emphasized than when the angular amount of change calculated is greater than or equal to the threshold.

Abstract: An information transmission device according to the present disclosure includes: an acoustic feature calculator that calculates an acoustic feature of a spoken voice; a speaker feature calculator that calculates a speaker feature from the acoustic feature using a deep neural network (DNN), the speaker feature being a feature unique to a speaker of the spoken voice; an analyzer that analyzes condition information indicating a condition to be used in calculating the speaker feature, based on the spoken voice; and an information transmitter that transmits the speaker feature and the condition information to an information reception device that performs speaker recognition processing on the spoken voice, as information to be used by the information reception device to recognize the speaker of the spoken voice.

Abstract: In a behavior identification method, surrounding sound is acquired, a feature value that is specified by a spectrum pattern included in spectrum information generated from sound made by a person performing a predetermined behavior is extracted from the sound acquired, the predetermined behavior is identified by the feature value, and information indicating the predetermined behavior identified is output.

Abstract: An unmanned flying object, capable of suppressing an increase in overall size while having a configuration to reduce noise, is provided. The unmanned flying object includes a duct that corresponds to: at least one generator that generates airflow; at least one microphone; and at least one speaker. The duct covers the at least one generator in a direction perpendicular to an airflow direction, passes the airflow in the airflow direction, includes a space between inner and outer peripheral surfaces, and defines an opening at the end of the space in the airflow direction. A shape of the inner peripheral surface is tapered in the airflow direction. The at least one microphone is positioned in the space. The at least one speaker is positioned closer to the at least one generator than the at least one microphone.

Abstract: A speaker recognition device according to the present disclosure includes: an acoustic feature calculator that calculates, from utterance data indicating a voice of an obtained utterance, acoustic feature of the voice of the utterance; a statistic calculator that calculates an utterance data statistic from the calculated acoustic feature; a speaker feature extractor that extracts speaker feature of a speaker of the utterance data from the calculated utterance data statistic using a deep neural network (DNN); a similarity calculator that calculates a similarity between the extracted speaker feature and pre-stored speaker feature of at least one registered speaker; and a speaker recognizer that recognizes the speaker of the utterance data based on the calculated similarity.

Abstract: An unmanned aerial vehicle capable of employing active noise cancelling without being influenced by wind from a rotor is provided. The unmanned aerial vehicle includes a processor and at least one speaker. The processor acquires operational information regarding each of at least one generator and generates an opposite phase signal having an opposite phase relative to a signal corresponding to the operational information. The at least one generator generates a force to fly the unmanned aerial vehicle. The operational information correlates with noise generated by each of the at least one generator. The at least one speaker outputs sound based on the opposite phase signal.

Abstract: An unmanned air vehicle is provided. The unmanned air vehicle includes one or more generators, each of which generates a force that drives the unmanned air vehicle to fly and also generates an airflow. Each of one or more first microphones is located in an external region that is not included in any of one or more first airflow regions. Each of the one or more first airflow regions corresponds to the airflow generated by one of the one or more generators. Each of one or more second microphones is located in the external region between at least one of the one or more generators and the one or more first microphones. A processor performs processing on one or more first signals output from the one or more first microphones and one or more second signals output from the one or more second microphones.

Abstract: An unmanned air vehicle includes a generator that generates a flying force and also generates an air flow, a structural component, a microphone that outputs a first signal, a speaker, and a processor. The processor generates a second signal according to the first signal. The structural component surrounds a noise source of the generator, and includes a through-hole extending in a direction of the air flow. The through-hole is in a direction opposite to the direction of the air flow. An end, in the opposite direction, of the structural component corresponds to an end, in the opposite direction, of the noise source of the generator. An end, in the direction of the air flow, of the structural component extends, in the direction of the air flow, beyond an end, in the direction of the air flow, of the noise source of the generator.

Abstract: An information processing method includes obtaining an audio signal that represents sound collected by a sound collecting device; calculating, using the audio signal obtained, a volume of the sound collected by the sound collecting device; identifying, using the audio signal obtained, a type of a sound source of the sound collected by the sound collecting device; estimating a distance between the sound collecting device and the sound source of the sound collected by the sound collecting device based on a standard volume and the volume calculated, the standard volume being (i) stored in a database in which the type of the sound source and the standard volume are preassociated with each other, (ii) the volume of the sound from the sound source at a predetermined distance, and (iii) associated with the type of the sound source identified; and outputting an estimation result.

Abstract: A control apparatus, that can expand a range in which noise generated in an unmanned flying object is reduced, is provided. The control apparatus acquires position information of one or more unmanned flying objects and noise information concerning first noises generated by the one or more unmanned flying objects. The control apparatus also acquires output region information indicating an output region of sound output from a speaker. The control apparatus calculates, using the position information, the output region information, and the noise information, second noises that reach the output region. The second noises are caused by the first noises which are generated by the one or more unmanned flying objects. The control apparatus generates opposite phase signals for outputting opposite phase sounds with respect to the calculated second noises, and causes the speaker to output sound on a basis of the generated opposite phase signals.

Abstract: A speaker recognition device according to the present disclosure includes: an acoustic feature calculator that calculates, from utterance data indicating a voice of an obtained utterance, acoustic feature of the voice of the utterance; a statistic calculator that calculates an utterance data statistic from the calculated acoustic feature; a speaker feature extractor that extracts speaker feature of a speaker of the utterance data from the calculated utterance data statistic using a deep neural network (DNN); a similarity calculator that calculates a similarity between the extracted speaker feature and pre-stored speaker feature of at least one registered speaker; and a speaker recognizer that recognizes the speaker of the utterance data based on the calculated similarity.

Abstract: In a behavior identification method, surrounding sound is acquired, a feature value that is specified by a spectrum pattern included in spectrum information generated from sound made by a person performing a predetermined behavior is extracted from the sound acquired, the predetermined behavior is identified by the feature value, and information indicating the predetermined behavior identified is output.

Abstract: An information processing method includes obtaining an audio signal that represents sound collected by a sound collecting device; calculating, using the audio signal obtained, a volume of the sound collected by the sound collecting device; identifying, using the audio signal obtained, a type of a sound source of the sound collected by the sound collecting device; estimating a distance between the sound collecting device and the sound source of the sound collected by the sound collecting device based on a standard volume and the volume calculated, the standard volume being (i) stored in a database in which the type of the sound source and the standard volume are preassociated with each other, (ii) the volume of the sound from the sound source at a predetermined distance, and (iii) associated with the type of the sound source identified; and outputting an estimation result.

Abstract: A control apparatus, that can expand a range in which noise generated in an unmanned flying object is reduced, is provided. The control apparatus acquires position information of one or more unmanned flying objects and noise information concerning first noises generated by the one or more unmanned flying objects. The control apparatus also acquires output region information indicating an output region of sound output from a speaker. The control apparatus calculates, using the position information, the output region information, and the noise information, second noises that reach the output region. The second noises are caused by the first noises which are generated by the one or more unmanned flying objects. The control apparatus generates opposite phase signals for outputting opposite phase sounds with respect to the calculated second noises, and causes the speaker to output sound on a basis of the generated opposite phase signals.