-
公开(公告)号：US11425517B2
公开(公告)日：2022-08-23
申请号：US17264174
申请日：2019-07-29
IPC分类号： H04R27/00 , B60N2/90 , G06F3/16 , G10L21/0232 , H04R1/40 , H04R3/00 , H04R3/12 , G10L21/0208 , G10L21/0216
摘要： A conversation support system supports conversation of passengers in an automobile. Seats of at least two or more rows are placed in the automobile, and the conversation support system includes a speech switching control part configured to designate a desired sound pickup and reproduce area based on designation by a first passenger sitting in a first seat, a first target speech emphasizing part configured to output a signal obtained by emphasizing speech emitted from the designated sound pickup and reproduce area to a loud speaker corresponding to the first seat, and a second target speech emphasizing part configured to output the signal obtained by emphasizing speech, which is collected with a microphone corresponding to the first seat and which is emitted from the first seat, to a loud speaker corresponding to the sound pickup and reproduce area.
-
公开(公告)号：US12112749B2
公开(公告)日：2024-10-08
申请号：US17603263
申请日：2020-04-03
发明人： Kazunori Kobayashi , Shoichiro Saito , Hiroaki Ito
CPC分类号： G10L15/22 , G10L15/05 , G10L25/87 , G10L2015/223
摘要： A command analysis device capable of shortening the time until a command is executed is provided. The command analysis device includes a speech recognition unit that performs, every time when a predetermined unit of a speech signal is input, speech recognition on the speech signal and acquires a partial speech recognition result which is an intermediate result, and a command analysis unit that verifies an intermediate result in light of a predetermined intermediate result recognition rule, and outputs an analysis result during the input of the speech signal when a command execution target and a command execution content are successfully analyzed are provided.
-
公开(公告)号：US11678114B2
公开(公告)日：2023-06-13
申请号：US17259857
申请日：2019-07-01
CPC分类号： H04R3/00 , H04R1/08 , H04R1/323 , G10K11/16 , H04R2499/13
摘要： Provided is a sound collection loudspeaker apparatus that makes it possible to intuitively distinguish which talker is talking, and improve the comfort of conversations, when performing in-vehicle conversation and conversations with people outside of a vehicle. The sound collection loudspeaker apparatus is installed in a vehicle. Two or more sound collection and amplification positions are assumed to be present inside the vehicle. The apparatus includes: a transfer function multiplying unit that, from a transfer function for transfer from a desired sound source position where a sound image of an enhanced signal is localized to both ears of a target person located at the sound collection and amplification position, and a transfer function for transfer from one or more speakers installed for playing back sound at the sound collection and amplification position to the ears, applies a filter for localizing a sound image at the sound source position to an enhanced signal, and outputs the enhanced signal that has been filtered to the speaker. The enhanced signal is a signal in which a target sound emitted from the sound collection and amplification position has been enhanced from a signal collected by the one or more microphones.
-
公开(公告)号：US11482234B2
公开(公告)日：2022-10-25
申请号：US17264197
申请日：2019-07-29
IPC分类号： G10L21/0208 , H04R1/02
摘要： A first noise level, which is an estimated value of a magnitude of a noise component included in a first sound collection signal obtained from a first microphone which collects sound emitted from a first sound collection and amplification position is obtained, a second noise level, which is an estimated value of a magnitude of a noise component included in a second sound collection signal obtained from a second microphone which collects sound emitted from a second sound collection and amplification position is obtained, a ratio of a reproduced noisy sound level, which is an estimated value of a magnitude of noise at a position of a passenger at the second sound collection and amplification position in a case where the first noise level is reproduced from a second speaker placed at the second sound collection and amplification position, with respect to a second noisy sound level, which is an estimated value of a magnitude of noise corresponding to the second noise level at the position of the passenger at the second sound collection and amplification position is obtained, and a noise suppression amount is obtained so that a product of this ratio and the noise suppression amount becomes a constant set in advance.
-
公开(公告)号：US11835430B2
公开(公告)日：2023-12-05
申请号：US17630112
申请日：2019-07-30
发明人： Yuma Koizumi , Shoichiro Saito
CPC分类号： G01M99/005
摘要： Erroneous detection of erroneously determining a normal sound to be anomalous is suppressed. A registered normal sound detection apparatus 2 calculates anomaly score of an observed signal. A feature extraction unit 24 extracts a feature amount with a fixed-length from a time-series acoustic signal with an arbitrary length. An anomaly score calculation unit 25 corrects the anomaly score calculated from the observed signal so that the higher similarity score between the observed signal and a registered normal sound is, the smaller a value of the anomaly score is. The anomaly score calculation unit 25 calculates the similarity score by a similarity score function learned by using the feature amount extracted from the time-series acoustic signal including at least a normal sound by the feature extraction unit 24.
-
公开(公告)号：US11609115B2
公开(公告)日：2023-03-21
申请号：US16485334
申请日：2017-09-14
发明人： Yuma Koizumi , Shoichiro Saito , Hisashi Uematsu
摘要： To provide an anomalous sound detection training technique by which a feature amount extraction function for detecting anomalous sound can be generated irrespective of whether training data for anomalous signals is available or not. An anomalous sound detection training apparatus includes: a first function updating unit 3 that updates a feature amount extraction function and an feature amount inverse transformation function, which are input, based on an optimization index of a variational autoencoder; an acoustic feature extraction unit 4 that extracts an acoustic feature of normal sound based on training data for normal sound; a normal sound model updating unit 5 that updates a normal sound model by using the acoustic feature that is extracted; a threshold updating unit 6 that obtains a threshold φρ corresponding to a false positive rate ρ, which has a predetermined value, by using the training data for normal sound and the feature amount extraction function that is input; and a second function updating unit 8 that updates the feature amount extraction function that is updated, based on a Neyman-Pearson-type optimization index defined by the threshold φρ that is obtained, and repeatedly performs processing of each of the above-mentioned units.
-
公开(公告)号：US11510000B2
公开(公告)日：2022-11-22
申请号：US17265673
申请日：2019-07-25
摘要： A sound collection apparatus includes a substantially spherical base on which at least a predetermined number of recess portions are provided in a surface thereof with a predetermined interval therebetween; and a predetermined number of microphones. The predetermined number is an integer of 2 or greater. The microphones are installed on an inner bottom surface side of the recess portions one by one. Intervals between sound collecting portions of adjacent microphones are substantially equal to each other.
-
公开(公告)号：US11479184B2
公开(公告)日：2022-10-25
申请号：US17263867
申请日：2019-07-10
摘要： An object is to provide a sound collection apparatus capable of collecting a sound with a higher SN rate than before through use of a reflected sound. The sound collection apparatus is installed in a vehicle. The vehicle includes a seat for a passenger to sit on, and a reflective structure that reflects a sound emitted by a passenger sitting in the seat. The sound collection apparatus includes a first microphone arranged at a position where a direct sound that is a sound emitted by the passenger is readily collected, and a second microphone arranged at a position where a reflected sound that is a sound emitted by the passenger and reflected by the reflective structure is readily collected.
-
公开(公告)号：US20220013102A1
公开(公告)日：2022-01-13
申请号：US17293808
申请日：2019-11-07
摘要： There is provided a sound-emitting device that is easily installable and can output sound having directivity without performing signal processing. An on-vehicle sound-emitting device 10 installed in a vehicle includes a speaker 1 and a reflection unit 2 disposed at a position facing the speaker 1. The reflection unit 2 reflects sound output from the speaker 1 to direct the sound in a desired direction.
-
10.发明授权公开(公告)号：US11996120B2
公开(公告)日：2024-05-28
申请号：US17425672
申请日：2020-01-16
发明人： Yuma Koizumi , Shin Murata , Noboru Harada , Shoichiro Saito
摘要： The accuracy of unsupervised anomalous sound detection is improved. An anomalous sound generation unit 12 generates a pseudo-anomalous sound by associating a sound obtained from a predetermined device with a probability distribution followed by a sound obtained from a desired device group. A threshold value setting unit 13 sets a threshold value so that all anomaly scores calculated from the pseudo-anomalous sound are determined to be anomalous. A parameter update unit 14 uses an obtained normal sound and an obtained anomalous sound, or a threshold value and a value based on the obtained anomalous sound, to update a parameter so to reliably determine an anomalous sound as anomalous and minimize the probability of determining a normal sound as anomalous.
-
-
-
-
-
-
-
-
-
搜索结果
20 条记录 (耗时 0.02 秒)
