公开(公告)号：US20140161269A1

公开(公告)日：2014-06-12

申请号：US14093798

申请日：2013-12-02

申请人： FUJITSU LIMITED

发明人： Taro TOGAWA ,  Chisato Shioda ,  Yohei KISHI ,  Takeshi OTANI ,  Masanao SUZUKI

IPC分类号： G10K15/00

CPC分类号： G10K15/00 ,  G10K15/12 ,  G10L19/032 ,  G10L19/167 ,  H04S7/305

摘要： An audio signal encoding apparatus includes a processor to quantize an audio signal, to obtain a characteristic of reverberation masking that is exerted on a sound represented by the audio signal by reverberation of the sound generated in a reproduction environment by reproducing the sound, and to control a quantization step size of the audio signal that quantized based on the characteristic of the reverberation masking.

摘要翻译： 音频信号编码装置包括：处理器，用于量化音频信号，以通过再现声音在再现环境中产生的声音的混响来获得施加在由音频信号表示的声音上的混响蒙版的特性，并且控制 基于混响掩蔽的特性量化的音频信号的量化步长。

公开(公告)号：US20130188799A1

公开(公告)日：2013-07-25

申请号：US13707928

申请日：2012-12-07

申请人： Fujitsu Limited

发明人： Takeshi OTANI ,  Taro TOGAWA ,  Masanao SUZUKI

IPC分类号： H04B3/20

CPC分类号： H04R3/002 ,  G10L21/0232 ,  G10L2021/02082 ,  H04B3/20

摘要： An audio processing device includes a reverb property estimating unit that estimates a reverb property at each frequency on the basis of a first audio signal and a second audio signal representing sounds of the first audio signal output by an audio output unit and collected by an audio input unit, a gain calculating unit that determines an attenuating ratio for a component of the first audio signal at each frequency such that the larger the reverb property at the frequency is, the larger the attenuating ratio for the component at the frequency becomes, and a correcting unit that attenuates the first audio signal at the each frequency in accordance with the attenuating ratio determined for each frequency.

公开(公告)号：US20180261238A1

公开(公告)日：2018-09-13

申请号：US15980226

申请日：2018-05-15

申请人： FUJITSU LIMITED

发明人： Taro TOGAWA ,  Sayuri NAKAYAMA ,  Takeshi OTANI

IPC分类号： G10L25/51 ,  H04M3/428 ,  G10L15/22

CPC分类号： G10L25/51 ,  G10L15/22 ,  G10L25/06 ,  G10L25/21 ,  G10L25/63 ,  G10L25/78 ,  G10L25/90 ,  H04M3/4285 ,  H04M3/5175

摘要： A confused state determination device that includes: an audio receiver that receives input of call audio; a memory; and a processor that is connected to the memory and that is configured to detect a questioning utterance in a call-hold duration of the call audio, compute a frequency of the questioning utterance detected in the call-hold duration, and determine a user to be in a confused state in a case in which the computed questioning utterance frequency is a first threshold value or greater.

公开(公告)号：US20140372121A1

公开(公告)日：2014-12-18

申请号：US14260449

申请日：2014-04-24

申请人： FUJITSU LIMITED

发明人： Taro TOGAWA ,  Chisato Shioda ,  Takeshi Otani

IPC分类号： G10L13/027 ,  G10L15/08

CPC分类号： G10L13/027 ,  G10L15/02 ,  G10L15/04 ,  G10L15/08 ,  G10L21/0364 ,  G10L21/057

摘要： A speech 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: obtaining input speech, detecting a vowel segment contained in the input speech, estimating an accent segment contained in the input speech, calculating a first vowel segment length containing the accent segment and a second vowel segment length excluding the accent segment, and controlling at least one of the first vowel segment length and the second vowel segment length.

摘要翻译： 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，检测包含在所述输入语音中的元音段，估计所述输入语音中包含的重音段，计算第一 包含重音段的元音段长度和不包括重音段的第二元音段长度，并且控制第一元音段长度和第二元音段段长度中的至少一个。

公开(公告)号：US20140163979A1

公开(公告)日：2014-06-12

申请号：US14074511

申请日：2013-11-07

申请人： FUJITSU LIMITED

发明人： Masanao SUZUKI ,  Takeshi OTANI ,  Taro TOGAWA

IPC分类号： G10L15/20

CPC分类号： G10L21/04

摘要： 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 a first signal including a plurality of voice segments; controlling such that a non-voice segment with a length equal to or greater than a predetermined first threshold value exists between at least one of the plurality of voice segments; and outputting a second signal including the plurality of voice segments and the controlled non-voice segment.

摘要翻译： 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，接收包括多个语音段的第一信号; 控制使得在所述多个语音段中的至少一个之间存在长度等于或大于预定的第一阈值的非语音段; 以及输出包括所述多个语音段和所述受控非语音段的第二信号。

公开(公告)号：US20140153743A1

公开(公告)日：2014-06-05

申请号：US14080373

申请日：2013-11-14

申请人： FUJITSU LIMITED

发明人： Takeshi OTANI ,  Taro TOGAWA ,  Chisato ISHIKAWA ,  Masanao SUZUKI

IPC分类号： G10K11/16

CPC分类号： H04R3/04 ,  G10L21/0208 ,  H03G5/18 ,  H04R3/007 ,  H04R29/001 ,  H04R2430/01 ,  H04R2430/03 ,  H04R2499/11

摘要： An audio processing device includes a setting section that sets a reproduction sampling frequency Fplay and a recording sampling frequency Frec higher than Fplay, a digital-to-analogue converter that based on Fplay converts a sound source signal that is a digital signal into a reproduction signal that is an analogue signal, an analogue-to-digital converter that based on Frec converts a recording signal that is an analogue signal converter into an input signal that is a digital signal, a signal separator that separates the input signal into a low region signal contained in a band of less than Fplay and a high region signal contained in a band of the Fplay and higher, and a breakup detector that detects whether or not breakup is occurring in the reproduced sound based on power of the high region signal.

摘要翻译： 音频处理装置包括设置部分，其设置再现采样频率Fplay和高于Fplay的记录采样频率Frec，基于Fplay的数模转换器将作为数字信号的声源信号转换为再现信号 这是模拟信号，基于Frec的模数转换器将作为模拟信号转换器的记录信号转换为作为数字信号的输入信号，信号分离器将输入信号分离成低区域信号 包含在Fplay和Fplay的频带中包含的低于Fplay的频带和高区域信号，以及分解检测器，其基于高区域信号的功率来检测再现声音中是否发生分解。

公开(公告)号：US20140142943A1

公开(公告)日：2014-05-22

申请号：US14054266

申请日：2013-10-15

申请人： FUJITSU LIMITED

发明人： Chisato Ishikawa ,  Taro TOGAWA ,  Takeshi OTANI ,  Masanao SUZUKI

IPC分类号： G10L17/00

CPC分类号： G10L17/26 ,  G10L21/04 ,  G10L25/51 ,  G10L25/66 ,  G10L25/78

摘要： A signal 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 speech of a speaker as a first signal; detecting an expiration period included in the first signal; extracting a number of phonemes included in the expiration period; and controlling, a second signal, which is an output to the speaker, on the basis of the number of phonemes and a length of the expiration period.

摘要翻译： 信号处理装置包括处理器; 以及存储器，其存储多个指令，当由所述处理器执行时，使所述处理器执行，接收说话者的语音作为第一信号; 检测包括在第一信号中的期满期; 提取期满中包含的一些音素; 并根据音素的数量和有效期的长度来控制作为扬声器的输出的第二信号。

公开(公告)号：US20240193671A1

公开(公告)日：2024-06-13

申请号：US18451773

申请日：2023-08-17

申请人： Fujitsu Limited

发明人： Arisu ENDO ,  Taro TOGAWA ,  Shun KOHATA

IPC分类号： G06Q30/0601 ,  G06V10/70 ,  G06V20/40 ,  G06V20/52 ,  G06V40/20

CPC分类号： G06Q30/0639 ,  G06V10/70 ,  G06V20/41 ,  G06V20/52 ,  G06V40/20

摘要： A computer-readable recording medium has stored therein an information processing program that causes a computer to execute a process including obtaining a video in which inside of a store is captured analyzing the obtained video identifying, based on a result of the analyzing, a first-type region that covers a product placed inside the store captured in the video, a second-type region that covers a person targeted for selling the product inside the store captured in the video, and a relationship that recognizes interaction between the first-type region and the second-type region and associating the identified relationship to the product covered in the first-type region.

公开(公告)号：US20180061434A1

公开(公告)日：2018-03-01

申请号：US15666722

申请日：2017-08-02

申请人： FUJITSU LIMITED

发明人： Takeshi OTANI ,  Taro TOGAWA ,  Sayuri NAKAYAMA

IPC分类号： G10L21/0232 ,  G10K11/178

CPC分类号： G10L21/0232 ,  G10K11/178 ,  G10K2210/30232 ,  G10K2210/3045 ,  G10L21/0208 ,  G10L21/0272 ,  G10L21/0316 ,  G10L2021/02087 ,  G10L2021/02161 ,  H03G3/32 ,  H03G5/165 ,  H04R3/005 ,  H04R2430/03

摘要： A sound processing device includes a processor configured to generate a first frequency spectrum of a first sound signal corresponding to a first sound received at a first input device and a second frequency spectrum of a second sound signal corresponding to the first sound received at a second input device, calculate a transfer characteristic based on a first difference between an intensity of the first frequency spectrum and an intensity of the second frequency spectrum, generate a third frequency spectrum of a third sound signal transmitted from the first input device and a fourth frequency spectrum of a fourth sound signal transmitted from the second input device, specify a suppression level of an intensity of the fourth frequency spectrum based on a second difference between an intensity of the third frequency spectrum and an intensity of the fourth frequency spectrum.

公开(公告)号：US20150350781A1

公开(公告)日：2015-12-03

申请号：US14822119

申请日：2015-08-10

申请人： FUJITSU LIMITED

发明人： Takeshi OTANI ,  Taro TOGAWA ,  Masanao SUZUKI

IPC分类号： H04R3/00

CPC分类号： H04R3/002 ,  G10L21/0232 ,  G10L2021/02082 ,  H04B3/20

摘要： An audio processing device includes a reverb property estimating unit that estimates a reverb property at each frequency on the basis of a first audio signal and a second audio signal representing sounds of the first audio signal output by an audio output unit and collected by an audio input unit, a gain calculating unit that determines an attenuating ratio for a component of the first audio signal at each frequency such that the larger the reverb property at the frequency is, the larger the attenuating ratio for the component at the frequency becomes, and a correcting unit that attenuates the first audio signal at the each frequency in accordance with the attenuating ratio determined for each frequency.

摘要翻译： 音频处理装置包括混响属性估计单元，其基于第一音频信号和表示由音频输出单元输出的第一音频信号的声音并由音频输入收集的第二音频信号来估计每个频率的混响特性 单元，增益计算单元，其确定每个频率处的第一音频信号的分量的衰减比，使得频率处的混响特性越大，频率处的分量的衰减比越大，并且校正 单元，其根据针对每个频率确定的衰减比，在每个频率处衰减第一音频信号。