专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US07546241B2 Speech synthesis method and apparatus, and dictionary generation method and apparatus 失效
标题翻译：语音合成方法和装置，以及字典生成方法和装置
公开(公告)号：US07546241B2
公开(公告)日：2009-06-09
申请号：US10449072
申请日：2003-06-02
申请人： Masayuki Yamada , Yasuhiro Komori , Toshiaki Fukada
发明人： Masayuki Yamada , Yasuhiro Komori , Toshiaki Fukada
IPC分类号： G10L13/08
CPC分类号： G10L13/06 , G10L13/04
摘要： In a speech synthesis process, micro-segments are cut from acquired waveform data and a window function. The obtained micro-segments are re-arranged to implement a desired prosody, and superposed data is generated by superposing the re-arranged micro-segments, so as to obtain synthetic speech waveform data. A spectrum correction filter is formed based on the acquired waveform data. At least one of the waveform data, micro-segments, and superposed data is corrected using the spectrum correction filter. In this way, “blur” of a speech spectrum due to the window function applied to obtain micro-segments is reduced, and speech synthesis with high sound quality is realized.
摘要翻译：在语音合成过程中，从获取的波形数据和窗口函数中切割微片段。所获得的微片段被重新布置以实现期望的韵律，并且通过叠加重新布置的微片段来产生叠加数据，以便获得合成语音波形数据。基于获取的波形数据形成频谱校正滤波器。使用光谱校正滤波器来校正波形数据，微片段和叠加数据中的至少一个。以这种方式，由于应用于获得微片段的窗口函数而导致的语音频谱的“模糊”减少，并且实现了高音质的语音合成。

2. 发明授权

US07603278B2 Segment set creating method and apparatus 失效
标题翻译：段集创建方法和装置
公开(公告)号：US07603278B2
公开(公告)日：2009-10-13
申请号：US11225178
申请日：2005-09-14
申请人： Toshiaki Fukada , Masayuki Yamada , Yasuhiro Komori
发明人： Toshiaki Fukada , Masayuki Yamada , Yasuhiro Komori
IPC分类号： G10L13/08 , G10L13/06
CPC分类号： G10L13/06
摘要： A segment set before updating is read, and clustering considering a phoneme environment is performed to it. For each cluster obtained by the clustering, a representative segment of a segment set belonging to the cluster is generated. For each cluster, a segment belonging to the cluster is replaced with the representative segment so as to update the segment set.
摘要翻译：读取更新前设置的段，并执行考虑音素环境的聚类。对于通过聚类获得的每个聚类，生成属于聚类的段集合的代表性段。对于每个集群，属于集群的段被替换为代表段，以便更新段集。

3. 发明申请

US20060069566A1 Segment set creating method and apparatus 失效
公开(公告)号：US20060069566A1
公开(公告)日：2006-03-30
申请号：US11225178
申请日：2005-09-14
申请人： Toshiaki Fukada , Masayuki Yamada , Yasuhiro Komori
发明人： Toshiaki Fukada , Masayuki Yamada , Yasuhiro Komori
IPC分类号： G10L13/08
CPC分类号： G10L13/06
摘要： A segment set before updating is read, and clustering considering a phoneme environment is performed to it. For each cluster obtained by the clustering, a representative segment of a segment set belonging to the cluster is generated. For each cluster, a segment belonging to the cluster is replaced with the representative segment so as to update the segment set.

4. 发明授权

US07451090B2 Information processing device and information processing method 有权
标题翻译：信息处理装置及信息处理方法
公开(公告)号：US07451090B2
公开(公告)日：2008-11-11
申请号：US11135083
申请日：2005-05-23
申请人： Kenichiro Nakagawa , Makoto Hirota , Hiromi Ikeda , Tsuyoshi Yagisawa , Hiroki Yamamoto , Toshiaki Fukada , Yasuhiro Komori
发明人： Kenichiro Nakagawa , Makoto Hirota , Hiromi Ikeda , Tsuyoshi Yagisawa , Hiroki Yamamoto , Toshiaki Fukada , Yasuhiro Komori
IPC分类号： G10L21/00
CPC分类号： G06F17/30265
摘要： In a system implementing image retrieval by performing speech recognition on voice information added to an image, the speech recognition is triggered by an event, such as an image upload event, that is not an explicit speech-recognition order event. The system obtains voice information added to an image, detects an event, and performs speech recognition on the obtained voice information in response to a specific event, even if the detected event is not an explicit speech-recognition order event.
摘要翻译：在通过对添加到图像的语音信息执行语音识别来实现图像检索的系统中，语音识别由诸如图像上传事件的事件触发，该事件不是明确的语音识别顺序事件。即使检测到的事件不是明确的语音识别顺序事件，系统获得添加到图像的语音信息，检测事件，并且响应于特定事件对所获得的语音信息执行语音识别。

5. 发明申请

US20050131689A1 Apparatus and method for detecting signal 失效
标题翻译：用于检测信号的装置和方法
公开(公告)号：US20050131689A1
公开(公告)日：2005-06-16
申请号：US11007245
申请日：2004-12-09
申请人： Philip Garner , Toshiaki Fukada , Yasuhiro Komori
发明人： Philip Garner , Toshiaki Fukada , Yasuhiro Komori
IPC分类号： G10L11/02 , G10L15/04 , G10L15/20 , G10L21/02 , G10L15/12
CPC分类号： G10L25/78
摘要： Robust signal detection against various types of background noise is implemented. According to a signal detection apparatus and method of this invention, the feature amount of an input signal sequence and the feature amount of a noise component contained in the signal sequence are extracted. After that, the first likelihood indicating probability that the signal sequence is detected and the second likelihood indicating probability that the noise component is detected are calculated on the basis of a predetermined signal-to-noise ratio and the extracted feature amount of the signal sequence. Additionally, a likelihood ratio indicating the ratio between the first likelihood and the second likelihood is calculated. Detection of the signal sequence is determined on the basis of the likelihood ratio.
摘要翻译：实现对各种背景噪声的鲁棒信号检测。根据本发明的信号检测装置和方法，提取输入信号序列的特征量和包含在信号序列中的噪声成分的特征量。之后，基于预定的信噪比和所提取的信号序列的特征量来计算检测到信号序列的概率的第一似然度和指示检测到噪声分量的概率的第二似然。另外，计算表示第一似然率与第二似然率之比的似然比。基于似然比确定信号序列的检测。

6. 发明授权

US07756707B2 Signal processing apparatus and method 失效
标题翻译：信号处理装置及方法
公开(公告)号：US07756707B2
公开(公告)日：2010-07-13
申请号：US11082931
申请日：2005-03-18
申请人： Philip Garner , Toshiaki Fukada , Yasuhiro Komori
发明人： Philip Garner , Toshiaki Fukada , Yasuhiro Komori
IPC分类号： G10L15/20
CPC分类号： G10L25/87
摘要： A signal processing apparatus and method for performing a robust endpoint detection of a signal are provided. An input signal sequence is divided into frames each of which has a predetermined time length. The presence of the signal in the frame is detected. After that, the filter process of smoothing the detection result by using the detection result for a past frame is applied to the detection result for a current frame. The filter output is compared with a predetermined threshold value to determine the state of the signal sequence of the current frame on the basis of the comparison result.
摘要翻译：提供了一种用于执行信号的鲁棒端点检测的信号处理装置和方法。输入信号序列被分成具有预定时间长度的帧。检测到帧中存在信号。之后，通过使用过去帧的检测结果对检测结果进行平滑的滤波处理应用于当前帧的检测结果。将滤波器输出与预定阈值进行比较，以基于比较结果确定当前帧的信号序列的状态。

7. 发明授权

US07475012B2 Signal detection using maximum a posteriori likelihood and noise spectral difference 失效
标题翻译：使用最大后验似然率和噪声光谱差的信号检测
公开(公告)号：US07475012B2
公开(公告)日：2009-01-06
申请号：US11007245
申请日：2004-12-09
申请人： Philip Garner , Toshiaki Fukada , Yasuhiro Komori
发明人： Philip Garner , Toshiaki Fukada , Yasuhiro Komori
IPC分类号： G10L11/02 , G10L15/20
CPC分类号： G10L25/78
摘要： Robust signal detection against various types of background noise is implemented. According to a signal detection apparatus, the feature amount of an input signal sequence and the feature amount of a noise component contained in the signal sequence are extracted. After that, the first likelihood indicating probability that the signal sequence is detected and the second likelihood indicating probability that the noise component is detected are calculated on the basis of a predetermined signal-to-noise ratio and the extracted feature amount of the signal sequence. Additionally, a likelihood ratio indicating the ratio between the first likelihood and the second likelihood is calculated. Detection of the signal sequence is determined on the basis of the likelihood ratio.
摘要翻译：实现对各种背景噪声的鲁棒信号检测。根据信号检测装置，提取输入信号序列的特征量和包含在信号序列中的噪声成分的特征量。之后，基于预定的信噪比和所提取的信号序列的特征量来计算检测到信号序列的概率的第一似然度和指示检测到噪声分量的概率的第二似然。另外，计算表示第一似然率与第二似然率之比的似然比。基于似然比确定信号序列的检测。

8. 发明申请

US20070046645A1 INFORMATION PROCESSING METHOD AND INFORMATION PROCESSING DEVICE 失效
标题翻译：信息处理方法和信息处理设备
公开(公告)号：US20070046645A1
公开(公告)日：2007-03-01
申请号：US11462670
申请日：2006-08-04
申请人： Makoto Hirota , Toshiaki Fukada , Yasuhiro Komori
发明人： Makoto Hirota , Toshiaki Fukada , Yasuhiro Komori
IPC分类号： G09G5/00
CPC分类号： G10L15/24 , G06K9/6293 , G10L2015/025
摘要： In an information processing method for recognizing a handwritten figure or character, with use of a speech input in combination, in order to increase the recognition accuracy a given target is subjected to figure recognition and a first candidate figure list is obtained. Input speech information is phonetically recognized and a second candidate figure list is obtained. On the basis of the figure candidates obtained by the figure recognition and the figure candidates obtained by the speech recognition, a most likely figure is selected.
摘要翻译：在用于识别手写图形或字符的信息处理方法中，通过组合使用语音输入，为了增加识别精度，给定目标进行图形识别，并获得第一候选图表。语音识别输入语音信息，获得第二候选图表。基于通过图形识别获得的图形候选者和通过语音识别获得的图形候选者，选择最可能的图形。

9. 发明申请

US20050216261A1 Signal processing apparatus and method 失效
标题翻译：信号处理装置及方法
公开(公告)号：US20050216261A1
公开(公告)日：2005-09-29
申请号：US11082931
申请日：2005-03-18
申请人： Philip Garner , Toshiaki Fukada , Yasuhiro Komori
发明人： Philip Garner , Toshiaki Fukada , Yasuhiro Komori
IPC分类号： G10L11/02 , G10L11/06 , G10L15/04
CPC分类号： G10L25/87
摘要： A signal processing apparatus and method for performing a robust endpoint detection of a signal are provided. An input signal sequence is divided into frames each of which has a predetermined time length. The presence of the signal in the frame is detected. After that, the filter process of smoothing the detection result by using the detection result for a past frame is applied to the detection result for a current frame. The filter output is compared with a predetermined threshold value to determine the state of the signal sequence of the current frame on the basis of the comparison result.
摘要翻译：提供了一种用于执行信号的鲁棒端点检测的信号处理装置和方法。输入信号序列被分成具有预定时间长度的帧。检测到帧中存在信号。之后，通过使用过去帧的检测结果对检测结果进行平滑的滤波处理应用于当前帧的检测结果。将滤波器输出与预定阈值进行比较，以基于比较结果确定当前帧的信号序列的状态。

10. 发明授权

US5845047A Method and apparatus for processing speech information using a phoneme environment 失效
标题翻译：使用音素环境处理语音信息的方法和装置
公开(公告)号：US5845047A
公开(公告)日：1998-12-01
申请号：US406487
申请日：1995-03-20
申请人： Toshiaki Fukada , Yasunori Ohora , Yasuhiro Komori , Takashi Aso
发明人： Toshiaki Fukada , Yasunori Ohora , Yasuhiro Komori , Takashi Aso
IPC分类号： G10L15/06 , G10L13/04 , G10L13/08 , G10L15/02 , G10L15/14 , G10L5/00
CPC分类号： G10L15/02 , G10L13/04
摘要： A speech information processing apparatus includes a statistical processing unit for extracting features by performing statistical processing of a feature file formed by extracting features of speech, such as the fundamental frequency and its variations, and the power and its variations of speech, from a speech file, and a label file in which a phoneme environment, comprising the accent type, the number of moras, the mora position, phonemes and the like, is considered, and a pitch pattern forming unit for forming a pitch pattern, in which phoneme environment is considered, based on the result of the statistical processing.
摘要翻译：语音信息处理装置包括：统计处理单元，用于通过从语音文件中提取特征文件的特征文件来提取特征，所述特征文件通过从基本频率及其变化提取语音的特征，以及语音的功率及其变化，以及其中考虑包括重音类型，莫尔斯数，莫尔斯位置，音素等的音素环境的标签文件，以及用于形成音调模式的音调模式形成单元，其中音素环境是根据统计处理结果考虑。

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