公开(公告)号：US20220335967A1

公开(公告)日：2022-10-20

申请号：US17641928

申请日：2020-09-04

申请人： SONY GROUP CORPORATION

发明人： RYUICHI NAMBA ,  MAKOTO AKUNE ,  YOSHIAKI OIKAWA

IPC分类号： G10L25/93 ,  G01S19/01

摘要： The present technology relates to a signal processing apparatus, a method, and a program that make it possible to obtain a high-quality target sound. The signal processing apparatus includes an interval detection unit configured to detect a time interval containing a sound that is emitted from a mobile body and that is included in a recording signal obtained by collecting sounds around the mobile body in a state where another mobile body is present around the mobile body, the time interval being detected on the basis of the recording signal and a sensor signal output from a sensor attached to the mobile body. The present technology is applicable to a recording system.

公开(公告)号：US20220335939A1

公开(公告)日：2022-10-20

申请号：US17724320

申请日：2022-04-19

申请人： Modality.AI

发明人： Jackson Liscombe ,  Hardik Kothare ,  Doug Habberstad ,  Andrew Cornish ,  Oliver Roesler ,  Michael Neumann ,  David Pautler ,  David Suendermann-Oeft ,  Vikram Ramanarayanan

IPC分类号： G10L15/22 ,  G10L25/93 ,  G10L25/84 ,  G10L25/66

摘要： A computer-generated dialog session is customized for a user having a pathology characterized at least in part by a speech pathology. The user's speech is analyzed for spans of speech in which the starts and ends of the spans satisfy predetermined thresholds of time. Customization occurs by altering at least one of the following configurable parameters: (a) a threshold minimum signal strength of speech (dB) to consider as the start of the span of speech; (b) an adjustment factor by which signal strengths of background noise increases between consecutive spans of speech; (c) a threshold between signal strength during the span of speech and signal strength during the span of non-speech; (d) a start speech time threshold; and (e) an end speech time threshold.

公开(公告)号：US20220301581A1

公开(公告)日：2022-09-22

申请号：US17619606

申请日：2020-06-17

申请人： M.You Cognitive Technologies Ltd

发明人： Itay BARUCHI,

IPC分类号： G10L25/66 ,  G10L25/30 ,  G10L25/93

摘要： Generally, systems and methods for determining a change of a cognitive capability of a user are disclosed. The method may include: receiving at least one sensor signal acquired by at least one sensor (such as an accelerometer, gyro and/or magnetometer) mounted within a mobile phone of the user; determining a voice activity dataset based on the at least one sensor signal; and determining a change of a cognitive capability of the user based on the voice activity dataset. Advantageously, the disclosed systems and methods may enable determining anomalies and trends in the cognition of the user based on the sensor(s) mounted within the mobile phone of the user, without collecting and/or recording the voice of the user.

公开(公告)号：US20220293127A1

公开(公告)日：2022-09-15

申请号：US17828777

申请日：2022-05-31

申请人： GN Hearing A/S

发明人： Rob Anton Jurjen De Vries ,  Tobias Piechowiak

IPC分类号： G10L25/78 ,  G10L25/93 ,  G10L21/0232 ,  H04R3/04

摘要： The present disclosure relates in a first aspect to a method of detecting speech of incoming sound at a portable communication device. A microphone signal is divided into a plurality of separate frequency band signals from which respective power envelope signals are derived. Onsets of voiced speech of a first frequency band signal are determined based on a first stationary noise power signal and a first clean power signal and onsets of unvoiced speech in a second frequency band signal are determined based on a second stationary noise power signal and second clean power signal.

公开(公告)号：US20220277767A1

公开(公告)日：2022-09-01

申请号：US17628467

申请日：2019-07-25

申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION

发明人： Ryo MASUMURA ,  Takanobu OBA ,  Kiyoaki MATSUI

IPC分类号： G10L25/93 ,  G10L25/78 ,  G10L15/02 ,  G06N20/20

摘要： A voice/non-voice determination device robust with respect to an acoustic signal in a high-noise environment is provided. The voice/non-voice determination device includes an acoustic scene classification unit including a first model which receives input of an acoustic signal and outputs acoustic scene information which is information regarding a scene where the acoustic signal is collected, a speech enhancement unit including a second model which receives input of the acoustic signal and outputs speech enhancement information which is information regarding the acoustic signal after enhancement, and a voice/non-voice determination unit including a third model which receives input of the acoustic signal, the acoustic scene information and the speech enhancement information and outputs a voice/non-voice label which is information regarding a label of either a speech section or a non-speech section.

公开(公告)号：US11270707B2

公开(公告)日：2022-03-08

申请号：US16156263

申请日：2018-10-10

申请人： Cirrus Logic International Semiconductor Ltd.

发明人： John Paul Lesso

IPC分类号： G10L17/22 ,  G10L17/02 ,  G10L25/84 ,  G10L17/06 ,  G10L25/51 ,  G10L17/00 ,  G10L25/48 ,  G10L25/30 ,  G10L25/18 ,  G10L25/93

摘要： A method of analysis of an audio signal comprises: receiving an audio signal representing speech; extracting first and second components of the audio signal representing first and second acoustic classes of the speech respectively; analysing the first and second components of the audio signal with models of the first and second acoustic classes of the speech of an enrolled user. Based on the analysing, information is obtained information about at least one of a channel and noise affecting the audio signal.

公开(公告)号：US11134354B1

公开(公告)日：2021-09-28

申请号：US16901073

申请日：2020-06-15

申请人： Cirrus Logic International Semiconductor Ltd.

发明人： John P. Lesso

IPC分类号： H04R29/00 ,  H04R1/10 ,  G10L25/06 ,  G10L25/93

摘要： A method is used of detecting whether a device is being worn, when the device comprises a first transducer and a second transducer. It is determined when a signal detected by at least one of the first and second transducers represents speech. It is then determined when said speech contains speech of a first acoustic class and speech of a second acoustic class. A first correlation signal is generated, representing a correlation between signals generated by the first and second transducers during at least one period when said speech contains speech of the first acoustic class. A second correlation signal is generated, representing a correlation between signals generated by the first and second transducers during at least one period when said speech contains speech of the second acoustic class. It is then determined from the first correlation signal and the second correlation signal whether the device is being worn.

公开(公告)号：US11081100B2

公开(公告)日：2021-08-03

申请号：US16321295

申请日：2017-08-03

申请人： SONY CORPORATION

发明人： Hiro Iwase ,  Mari Saito ,  Shinichi Kawano

IPC分类号： H04S7/00 ,  G10L13/033 ,  H04R3/00 ,  G10L13/02 ,  G10L13/00 ,  G10L25/27 ,  G10L25/93 ,  G11B27/34

摘要： The present technology relates to a sound processing device and a method that can present progress of sound reproduction. The sound processing device includes a control unit for controlling a sound output that aurally expresses progress of sound reproduction with respect to an entirety of the sound reproduction according to the reproduction of a sound. The present technology can be applied to a sound speech progress presentation UI system.

公开(公告)号：US10742531B2

公开(公告)日：2020-08-11

申请号：US15302945

申请日：2015-04-09

申请人： DOLBY LABORATORIES LICENSING CORPORATION

发明人： Kai Li ,  Xuejing Sun ,  Gary Spittle

IPC分类号： H04L12/26 ,  H04L29/06 ,  H04J3/06 ,  G10L15/08 ,  G10L25/93 ,  G10L25/48 ,  G10L25/78

摘要： Some implementations involve analyzing audio packets received during a time interval that corresponds with a conversation analysis segment to determine network jitter dynamics data and conversational interactivity data. The network jitter dynamics data may provide an indication of jitter in a network that relays the audio data packets. The conversational interactivity data may provide an indication of interactivity between participants of a conversation represented by the audio data. A jitter buffer size may be controlled according to the network jitter dynamics data and the conversational interactivity data. The time interval may include a plurality of talkspurts.

公开(公告)号：US10719551B2

公开(公告)日：2020-07-21

申请号：US16102478

申请日：2018-08-13

申请人： Tencent Technology (Shenzhen) Company Limited

发明人： Weifeng Zhao

IPC分类号： G06F16/78 ,  G06F16/683 ,  G06F16/632 ,  G06F16/783 ,  G10L25/54 ,  G10L25/18 ,  H04N21/8352 ,  H04N21/439 ,  G10L25/93

摘要： A song determining method and device are provided. According to the embodiment of the present disclosure, by extracting the audio file in the video and acquiring the candidate song identification of the candidate song, to which the segment belongs, in the audio file, the candidate song identification set is obtained; then by acquiring the candidate song file corresponding to the candidate song identification and acquiring a matched audio frame, in which the candidate song file is matched with the audio file, the matched audio frame unit is obtained, wherein the matched audio frame unit includes multiple continuous matched audio frames; the target song identification of the target song, to which the segment belongs, is acquired from the candidate song identification set according to the matched audio frame unit corresponding to the candidate song identification, and the target song, to which the segment belongs, is determined according to the target song identification.