专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

51. 发明公开

EP1691344A1 SPEECH RECOGNITION DEVICE 有权
标题翻译： SPRACHERKENNUNGSSYSTEM
公开(公告)号：EP1691344A1
公开(公告)日：2006-08-16
申请号：EP04818533.4
申请日：2004-11-12
申请人： HONDA MOTOR CO., Ltd.
发明人： NAKADAI, Kazuhiro , TSUJINO, Hiroshi , OKUNO, Hiroshi 1102, Form Higashi Toin Sanjyo , YAMAMOTO, Shunichi
IPC分类号： G10L15/06
CPC分类号： G10L15/20 , G10L21/028 , G10L2021/02166
摘要： An automatic speech recognition system includes: a sound source localization module for localizing a sound direction of a speaker based on the acoustic signals detected by the plurality of microphones; a sound source separation module for separating a speech signal of the speaker from the acoustic signals according to the sound direction; an acoustic model memory which stores direction-dependent acoustic models that are adjusted to a plurality of directions at intervals; an acoustic model composition module which composes an acoustic model adjusted to the sound direction, which is localized by the sound source localization module, based on the direction-dependent acoustic models, the acoustic model composition module storing the acoustic model in the acoustic model memory; and a speech recognition module which recognizes the features extracted by a feature extractor as character information using the acoustic model composed by the acoustic model composition module.
摘要翻译：一种自动语音识别系统，包括：声源定位模块，用于基于由所述多个麦克风检测到的声信号来定位扬声器的声音方向; 声源分离模块，用于根据声音方向将扬声器的语音信号与声学信号分离; 声学模型存储器，其存储以时间间隔调整到多个方向的方向相关的声学模型; 声学模型合成模块，其基于所述方向相关的声学模型，组合声学模型组合模块，所述声学模型组合模块将声学模型调整到声音方向，所述声学模型由所述声源定位模块定位，所述声学模型组合模块将所述声学模型存储在所述声学模型存储器中; 以及语音识别模块，其使用由声学模型组合模块组成的声学模型识别由特征提取器提取的特征作为字符信息。

52. 发明公开

EP0339891A2 Speech processing apparatus 失效
标题翻译： Einrichtung zur Sprachverarbeitung。
公开(公告)号：EP0339891A2
公开(公告)日：1989-11-02
申请号：EP89304017.0
申请日：1989-04-21
申请人： CANON KABUSHIKI KAISHA
发明人： Miyamae, Koichi , Omata, Satoshi
IPC分类号： G10L3/00
CPC分类号： G10L21/028 , G10L25/18
摘要： A speech processing apparatus of the present invention enables processor elements (403a to 403r) each comprising at least one nonlinear oscillator circuit (621) to be used as band pass filters by using the entrainment taking place in each of the processor elements, whereby the speech of a particular talker in the speech of a plurality of talkers can be recognized.
摘要翻译：本发明的语音处理装置使每个包括至少一个非线性振荡器电路（621）的处理器元件（403a至403r）能够通过使用在每个处理器元件中发生的夹带来用作带通滤波器，由此语音可以识别多个讲话者的讲话中的特定讲话者。

53. 发明授权

EP3109855B1 SOUND SIGNAL PROCESSING DEVICE, SOUND SIGNAL PROCESSING METHOD, AND PROGRAM 有权
公开(公告)号：EP3109855B1
公开(公告)日：2018-11-21
申请号：EP15752747.4
申请日：2015-01-27
申请人： Sony Corporation
发明人： HIROE, Atsuo
IPC分类号： G10L15/04 , G10L25/51 , G10L25/78
CPC分类号： G10L21/028 , G01S3/8006 , G01S3/8083 , G10L15/04 , G10L21/0308 , G10L21/0388 , G10L25/78 , G10L25/93 , G10L2021/02166
摘要： A device and a method for determining a speech segment with a high degree of accuracy from a sound signal in which different sounds coexist are provided. Directional points indicating the direction of arrival of the sound signal are connected in the temporal direction, and a speech segment is detected. In this configuration, pattern classification is performed in accordance with directional characteristics with respect to the direction of arrival, and a directionality pattern and a null beam pattern are generated from the classification results. Also, an average null beam pattern is also generated by calculating the average of the null beam patterns at a time when a non-speech-like signal is input. Further, a threshold that is set at a slightly lower value than the average null beam pattern is calculated as the threshold to be used in detecting the local minimum point corresponding to the direction of arrival from each null beam pattern, and a local minimum point equal to or lower than the threshold is determined to be the point corresponding to the direction of arrival.

54. 发明公开

EP3400596A1 ACOUSTIC MAP COMMAND CONTEXTUALIZATION AND DEVICE CONTROL 审中-公开
公开(公告)号：EP3400596A1
公开(公告)日：2018-11-14
申请号：EP16790773.2
申请日：2016-10-04
申请人： General Electric Company
发明人： VANDROUX, Stéphane , HADDAD, Mireille , RIOU, Patrice
IPC分类号： G10L15/22 , G10L17/00
CPC分类号： G10L17/22 , G10L15/005 , G10L15/1822 , G10L15/22 , G10L17/00 , G10L21/028 , G10L25/93 , G10L2015/223 , H04R3/005
摘要： Provided is a system where users performing a coordinated process are localized in a complex environment based upon audio input. Audio commands are detected and executed based on system user vocalization. Available commands are limited by user status, location, process type and process progress. Command execution is limited by the presence and locations of system users, non-users, or extraneous equipment.

55. 发明公开

EP3387648A1 LOCALIZATION ALGORITHM FOR SOUND SOURCES WITH KNOWN STATISTICS 有权
公开(公告)号：EP3387648A1
公开(公告)日：2018-10-17
申请号：EP15817848.3
申请日：2015-12-22
申请人： Huawei Technologies Duesseldorf GmbH
发明人： HELWANI, Karim , CHEN, Kainan , GEIGER, Jürgen
IPC分类号： G10L21/028 , G10L21/0272 , G01S3/80 , G01S3/808 , H04S7/00
CPC分类号： G01S3/8006 , G01S3/8083 , G01S3/8086 , G10L17/02 , G10L21/028 , G10L25/18 , G10L2025/783 , H04R1/406 , H04R3/005
摘要： The proposed method for localizing a target sound source from a plurality of sound sources, wherein a multi-channel recording signal of the plurality of sound sources comprises a plurality of microphone channel signals, comprises converting each microphone channel signal into a respective channel spectrogram in a time-frequency domain, blindly separating the channel spectrograms to obtain a plurality of separated source signals, identifying, among the plurality of separated source signals, the separated source signal that best matches a target source model, estimating, based on the identified separated source signal, a binary mask reflecting where the target sound source is active in the channel spectrograms in terms of time and frequency, applying the binary mask on the channel spectrograms to obtain masked channel spectrograms, and localizing the target sound source from the plurality of sound sources based on the masked channel spectrograms.

56. 发明公开

EP3337187A1 VERFAHREN ZUM BETRIEB EINES HÖRGERÄTES 审中-公开
公开(公告)号：EP3337187A1
公开(公告)日：2018-06-20
申请号：EP17199797.6
申请日：2017-11-02
申请人： Sivantos Pte. Ltd.
发明人： KAMKAR-PARSI, Homayoun , LUGGER, Marko
IPC分类号： H04R25/00 , G10L21/028 , G10L17/22
CPC分类号： H04R25/505 , G10L17/00 , G10L21/028 , H04R25/405 , H04R25/407 , H04R25/552 , H04R2225/41 , H04R2225/43
摘要： Die Erfindung nennt ein Verfahren (1) zum Betrieb eines Hörgerätes (2), welches wenigstens einen ersten Eingangswandler (10) und einen zweiten Eingangswandler (12) umfasst, wobei der erste Eingangswandler (10) aus einem Schallsignal (14) der Umgebung ein erstes Eingangssignal (16) generiert und der zweite Eingangswandler (12) aus dem Schallsignal (14) ein zweites Eingangssignal (18) generiert, wobei einer ersten Signalquelle (22) eine erste Richtung (26) zugeordnet wird, wobei anhand des ersten Eingangssignals (16) und des zweiten Eingangssignals (18) ein in der ersten Richtung (26) ausgerichtetes erstes Richtsignal (30) gebildet wird, und wobei wenigstens Signalanteile (34) des ersten Richtsignals (30) auf das Vorhandensein eines Nutzsignals von einer hinsichtlich der Art vorgegebenen Nutzsignalquelle (6) untersucht werden.

57. 发明公开

EP3170172A4 WIND NOISE REDUCTION FOR AUDIO RECEPTION 审中-公开
公开(公告)号：EP3170172A4
公开(公告)日：2018-01-17
申请号：EP15821863
申请日：2015-05-19
申请人： INTEL IP CORP
发明人： CHATLANI NAVIN , PLANTE FABRICE , SAPLAKOGLU GURHAN
IPC分类号： G10L21/0208 , G10L21/0232 , G10L25/18
CPC分类号： G10L21/0232 , G10L21/028 , G10L25/18 , H04M9/082
摘要： Wind noise reduction is described for audio signals received in a device. In one embodiment, an audio signal is decomposed into a plurality of sub-bands, the audio signal including wind noise, a first sub-band of the plurality of sub-bands low-pass filtered, wind noise is removed from the first sub band and the first sub-band is combined with the other sub-bands after removing wind noise.

58. 发明公开

EP3226244A1 NOISE SUPPRESSING APPARATUS, SPEECH RECOGNITION APPARATUS, AND NOISE SUPPRESSING METHOD 审中-公开
标题翻译：噪音抑制装置，语音识别装置和噪音抑制方法
公开(公告)号：EP3226244A1
公开(公告)日：2017-10-04
申请号：EP17163024.7
申请日：2017-03-27
申请人： FUJITSU LIMITED
发明人： Matsumoto, Chikako
IPC分类号： G10L21/0232 , G10L15/20 , G10L25/78 , G10L21/0216
CPC分类号： G10L21/0232 , G10L15/20 , G10L21/028 , G10L25/78 , G10L25/87 , G10L2021/02165 , G10L2021/02166 , H04R3/005 , H04R2201/403 , H04R2430/03 , H04R2430/20 , H04R2499/13
摘要： A noise suppressing apparatus calculates a phase difference on the basis of a first and second sound signal obtained by a microphone array; calculates a first sound arrival rate on the basis of a first phase difference area and the phase difference and a second sound arrival rate on the basis of a second phase difference area and the phase difference; calculates a dissimilarity that represents a level of difference between the first sound arrival rate and the second sound arrival rate; determines whether the pickup target sound is included in the first sound signal on the basis of the dissimilarity; and determines a suppression coefficient to be applied to the frequency spectrum of the first sound signal, on the basis of a result of the determination of whether the pickup target sound is included and on the basis of the phase difference.
摘要翻译：噪声抑制装置基于由麦克风阵列获得的第一和第二声音信号来计算相位差; 基于第一相差区域和相位差以及第二声音到达率，基于第二相差区域和相位差来计算第一声音到达率; 计算表示所述第一声音到达率与所述第二声音到达率之差的等级的相异度; 基于不相似性来确定拾取目标声音是否被包括在第一声音信号中; 并且基于确定是否包括拾取目标声音的结果并且基于相位差来确定要应用于第一声音信号的频谱的抑制系数。

59. 发明授权

EP2843659B1 METHOD AND APPARATUS FOR DETECTING CORRECTNESS OF PITCH PERIOD 有权
标题翻译：方法和装置检测正确性成瘾期作者：
公开(公告)号：EP2843659B1
公开(公告)日：2017-04-05
申请号：EP12876916.3
申请日：2012-12-26
申请人： Huawei Technologies Co., Ltd.
发明人： QI, Fengyan , MIAO, Lei
IPC分类号： G10L25/90
CPC分类号： G10L21/013 , G10L19/00 , G10L21/028 , G10L25/00 , G10L25/90

60. 发明公开

EP3111445A1 SYSTEMS AND METHODS FOR SPEAKER DICTIONARY BASED SPEECH MODELING 有权
标题翻译： SPURCHERWÖRTERBUCHBASIERTENSPRACHMODELLIERUNG系统
公开(公告)号：EP3111445A1
公开(公告)日：2017-01-04
申请号：EP15710339.1
申请日：2015-02-24
申请人： Qualcomm Incorporated
发明人： GUO, Yinyi , NAM, Juhan , VISSER, Erik , ZHANG, Shuhua , KIM, Lae-Hoon
IPC分类号： G10L21/0208 , G10L21/028
CPC分类号： G10L15/20 , G10L15/06 , G10L21/0208 , G10L21/028
摘要： A method for speech modeling by an electronic device is described. The method includes obtaining a real-time noise reference based on a noisy speech signal. The method also includes obtaining a real-time noise dictionary based on the real-time noise reference. The method further includes obtaining a first speech dictionary and a second speech dictionary. The method additionally includes reducing residual noise based on the real-time noise dictionary and the first speech dictionary to produce a residual noise-suppressed speech signal at a first modeling stage. The method also includes generating a reconstructed speech signal based on the residual noise-suppressed speech signal and the second speech dictionary at a second modeling stage.
摘要翻译：描述了一种通过电子设备进行语音建模的方法。该方法包括基于噪声语音信号获得实时噪声参考。该方法还包括基于实时噪声参考获得实时噪声字典。该方法还包括获得第一语音词典和第二语音词典。该方法还包括基于实时噪声字典和第一语音字典减少残留噪声，以在第一建模阶段产生残留噪声抑制语音信号。该方法还包括在第二建模阶段基于剩余噪声抑制语音信号和第二语音词典生成重构语音信号。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式