公开(公告)号：US10609479B2

公开(公告)日：2020-03-31

申请号：US16127601

申请日：2018-09-11

Applicant: FUJITSU LIMITED

Inventor： Chisato Shioda ,  Nobuyuki Washio ,  Masanao Suzuki ,  Shunsuke Takeuchi ,  Yoshiteru Tsuchinaga

IPC: G10L25/21 ,  H04R3/00 ,  G10L25/18 ,  H04R1/40 ,  G01S3/80

Abstract: A device for determining a sound source direction determines a direction in which a source of a reached sound exists, based on at least one of a sound pressure difference between a first sound pressure that is a sound pressure of a first frequency component of a first part of the reached sound acquired by a first microphone and a second sound pressure that is a sound pressure of the first frequency component of a second part of the reached sound acquired by a second microphone, and a phase difference between a first phase that is a phase of a second frequency component of the first part of the reached sound and a second phase that is a phase of the second frequency component of the second part of the reached sound.

公开(公告)号：US20180068677A1

公开(公告)日：2018-03-08

申请号：US15643576

申请日：2017-07-07

Applicant: FUJITSU LIMITED

Inventor： Masanao SUZUKI ,  Chisato Shioda ,  Nobuyuki WASHIO

IPC: G10L25/78 ,  G10L19/08

CPC classification number: G10L25/78 ,  G10L19/08 ,  G10L25/84 ,  G10L2025/783 ,  G10L2025/786 ,  G10L2025/906

Abstract: A method for utterance section detection includes: executing pitch gain calculation processing that includes calculating a pitch gain indicating an intensity of periodicity of an audio signal expressing a voice of a speaker for each of frames that are obtained by dividing the audio signal and that each have a predetermined length; and executing utterance section detection processing that includes determining that an utterance section on the audio signal starts when the pitch gain becomes greater than or equal to a first threshold value after a non-utterance section on the audio signal lasts, wherein the utterance section detection processing further includes determining that the utterance section ends when the pitch gain becomes less than a second threshold value lower than the first threshold value after the utterance section lasts.

公开(公告)号：US20150255087A1

公开(公告)日：2015-09-10

申请号：US14627516

申请日：2015-02-20

Applicant: FUJITSU LIMITED

Inventor： Takeshi Otani ,  Taro Togawa ,  Chisato Shioda

IPC: G10L25/48 ,  G10L15/22 ,  G10L15/08

CPC classification number: G10L25/48 ,  G10L25/15 ,  G10L25/63 ,  G10L25/90

Abstract: A voice processing device includes a backchannel-response detector configured to detect, from a first voice signal including a voice of a first speaker, a backchannel-response segment including a voice corresponding to a backchannel response made by the first speaker, using, a start point of a first voice segment detected from the first voice signal, an end point of a second voice segment detected from a second voice signal including a voice of a second speaker uttered before the voice of the first speaker, and the number of vowels detected from the first voice segment of the first voice signal.

Abstract translation: 语音处理装置包括：反向通道响应检测器，被配置为从包括第一扬声器的声音的第一声音信号中检测包括对应于由第一扬声器产生的反向通道响应的声音的反向声道响应段， 从第一语音信号检测到的第一语音段的点，从包括在第一说话者的声音之前发出的第二说话人的声音的第二语音信号检测到的第二语音段的终点以及从第一语音信号检测到的元音的数量 第一语音信号的第一语音段。

公开(公告)号：US10755731B2

公开(公告)日：2020-08-25

申请号：US15643576

申请日：2017-07-07

Applicant: FUJITSU LIMITED

Inventor： Masanao Suzuki ,  Chisato Shioda ,  Nobuyuki Washio

IPC: G10L25/78 ,  G10L25/84 ,  G10L15/04 ,  G10L19/08 ,  G10L25/90

Abstract: A method for utterance section detection includes: executing pitch gain calculation processing that includes calculating a pitch gain indicating an intensity of periodicity of an audio signal expressing a voice of a speaker for each of frames that are obtained by dividing the audio signal and that each have a predetermined length; and executing utterance section detection processing that includes determining that an utterance section on the audio signal starts when the pitch gain becomes greater than or equal to a first threshold value after a non-utterance section on the audio signal lasts, wherein the utterance section detection processing further includes determining that the utterance section ends when the pitch gain becomes less than a second threshold value lower than the first threshold value after the utterance section lasts.

公开(公告)号：US09443537B2

公开(公告)日：2016-09-13

申请号：US14269389

申请日：2014-05-05

Applicant: FUJITSU LIMITED

Inventor： Chisato Shioda ,  Taro Togawa ,  Takeshi Otani

IPC: G10L25/78 ,  G10L21/057 ,  G09B19/06

CPC classification number: G10L25/78 ,  G09B19/06 ,  G10L21/057 ,  G10L2025/783

Abstract: A voice processing device includes a processor; and a memory which stores a plurality of instructions, which when executed by the processor, causing the processor to execute: acquiring an input voice; detecting a sound period included in the input voice and a silent period adjacent to a back end of the sound period; calculating a number of words included in the sound period; and controlling a length of the silent period according to the number of words.

Abstract translation: 语音处理装置包括处理器; 以及存储器，其存储多个指令，所述指令在由所述处理器执行时使所述处理器执行：获取输入语音; 检测包括在输入声音中的声音周期和与声音周期的后端相邻的静音期间; 计算包含在声音周期中的字数; 以及根据单词数量来控制静音期间的长度。

公开(公告)号：US20150371662A1

公开(公告)日：2015-12-24

申请号：US14723907

申请日：2015-05-28

Applicant: FUJITSU LIMITED

Inventor： TARO TOGAWA ,  Chisato Shioda ,  Takeshi OTANI

IPC: G10L25/18 ,  G10L15/04

CPC classification number: G10L25/48 ,  G10L21/0216 ,  G10L25/06 ,  G10L25/93

Abstract: A voice processing device includes a memory; and a processor configured to execute a plurality of instructions stored in the memory, the instructions includes acquiring a transmitted voice; first detecting a first utterance segment of the transmitted voice; second detecting a response segment from the first utterance segment; determining a frequency of the response segment included in the transmitted voice; and estimating an utterance time period of a received voice on a basis of the frequency.

Abstract translation: 语音处理装置包括存储器; 以及处理器，被配置为执行存储在所述存储器中的多个指令，所述指令包括获取发送的语音; 首先检测所发送的声音的第一话音段; 第二检测来自第一话音段的响应段; 确定包括在所发送的语音中的响应段的频率; 以及基于所述频率来估计所接收的语音的发声时间段。

公开(公告)号：US20150340048A1

公开(公告)日：2015-11-26

申请号：US14711284

申请日：2015-05-13

Applicant: FUJITSU LIMITED

Inventor： Chisato Shioda ,  Taro Togawa ,  Takeshi Otani

IPC: G10L21/02

CPC classification number: G10L21/02 ,  G10L21/0308 ,  G10L2021/02082

Abstract: A voice processing device, includes, a processor; and a memory which stores a plurality of instructions, which when executed by the processor, cause the processor to execute: receiving, through a communication network, a first voice of a first user and a second voice of a second user inputted to a first microphone positioned nearer to the first user than the second user, and a third voice of the first user and a fourth voice of the second user inputted to a second microphone positioned nearer to the second user than the first user; calculating a first phase difference between the received first voice and the received second voice and a second phase difference between the received third voice and the received fourth voice; and performing at least one of: controlling transmission of the received second voice or the received fourth voice to a first speaker.

Abstract translation: 一种语音处理装置，包括：处理器; 以及存储器，其存储多个指令，所述指令在由所述处理器执行时使所述处理器执行：通过通信网络接收第一用户的第一语音和输入到第一麦克风的第二用户的第二语音 定位成比第二用户更靠近第一用户，并且第一用户的第三声音和第二用户的第四声音输入到比第一用户更​​靠近第二用户的第二麦克风; 计算所接收的第一语音和所接收的第二语音之间的第一相位差和所接收的第三语音与所接收的第四语音之间的第二相位差; 以及执行以下中的至少一个：控制所接收的第二语音或所接收的第四语音的传输到第一说话者。

公开(公告)号：US11295755B2

公开(公告)日：2022-04-05

申请号：US16532188

申请日：2019-08-05

Applicant: FUJITSU LIMITED

Inventor： Nobuyuki Washio ,  Masanao Suzuki ,  Chisato Shioda

IPC: G10L25/51 ,  H04R3/00 ,  H04R5/04 ,  G06F40/263

Abstract: A non-transitory computer-readable storage medium storing a program that causes a processor included in a computer mounted on a sound source direction estimation device to execute a process, the process includes calculating a sound pressure difference between a first voice data acquired from a first microphone and a second voice data acquired from a second microphone and estimating a sound source direction of the first voice data and the second voice data based on the sound pressure difference, outputting an instruction to execute a voice recognition on the first voice data or the second voice data in a language corresponding to the estimated sound source direction, and controlling a reference for estimating a sound source direction based on the sound pressure difference, based on a time length of the voice data used for the voice recognition based on the instruction and a voice recognition time length.

公开(公告)号：US11205416B2

公开(公告)日：2021-12-21

申请号：US16668009

申请日：2019-10-30

Applicant: FUJITSU LIMITED

Inventor： Nobuyuki Washio ,  Chisato Shioda ,  Masanao Suzuki

IPC: G10L15/00 ,  G10L21/0308 ,  G10L21/0216 ,  G06F40/58

Abstract: An utterance detection apparatus includes a processor configured to: detect an utterance start based on a first sound pressure based on first audio data acquired from a first microphone and a second sound pressure based on second audio data acquired from a second microphone; suppress an utterance start direction sound pressure when the utterance start direction sound pressure, which is one of the first sound pressure and the second sound pressure being larger at a time point of detecting the utterance start, falls below a non-utterance start direction sound pressure, which is the other one of the first sound pressure and the second sound pressure being smaller at the time point of detecting the utterance start; and detect an utterance end based on the suppressed utterance start direction sound pressure.

公开(公告)号：US20200051584A1

公开(公告)日：2020-02-13

申请号：US16532188

申请日：2019-08-05

Applicant: FUJITSU LIMITED

Inventor： Nobuyuki WASHIO ,  Masanao SUZUKI ,  Chisato Shioda

IPC: G10L25/51 ,  H04R5/04 ,  H04R3/00 ,  G06F17/27

Abstract: A non-transitory computer-readable storage medium storing a program that causes a processor included in a computer mounted on a sound source direction estimation device to execute a process, the process includes calculating a sound pressure difference between a first voice data acquired from a first microphone and a second voice data acquired from a second microphone and estimating a sound source direction of the first voice data and the second voice data based on the sound pressure difference, outputting an instruction to execute a voice recognition on the first voice data or the second voice data in a language corresponding to the estimated sound source direction, and controlling a reference for estimating a sound source direction based on the sound pressure difference, based on a time length of the voice data used for the voice recognition based on the instruction and a voice recognition time length.