专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

61. 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.

62. 发明授权

US06934680B2 Method for generating a statistic for phone lengths and method for determining the length of individual phones for speech synthesis 失效
标题翻译：用于生成电话长度的统计量的方法和用于确定用于语音合成的各个电话的长度的方法
公开(公告)号：US06934680B2
公开(公告)日：2005-08-23
申请号：US09899536
申请日：2001-07-06
申请人： Martin Holzapfel
发明人： Martin Holzapfel
IPC分类号： G10L13/06 , G10L13/08 , G10L15/00
CPC分类号： G10L13/06 , G10L13/08
摘要： A statistic for phone lengths is generated by determining the length of individual phones for speech synthesis. A primary statistic is based on primary clusters (for example triphones), and a secondary statistic is based on secondary clusters (for example phonemes of entire words). Both statistics include average phone lengths and, for example, the standard variation of the average phone lengths. During the determination of phone lengths, it is firstly attempted to determine the average phone lengths and standard variation of the average phone lengths by reference to the secondary statistic which is more language-specific. If this is not the case, the primary statistic, which can always be applied, is resorted to. By this two stage method, a phone length is determined which corresponds significantly better to a natural language than has been possible with the conventional single stage method.
摘要翻译：通过确定用于语音合成的个人电话的长度来产生电话长度的统计量。主要统计数据基于主要群集（例如三重奏），辅助统计数据基于辅助群集（例如整个单词的音素）。这两个统计数据包括平均电话长度，例如平均电话长度的标准变化。在确定电话长度期间，首先尝试通过参考更具体语言的辅助统计来确定平均电话长度的平均电话长度和标准变化。如果不是这种情况，则可以随时应用主要统计信息。通过这种两阶段方法，确定与常规单级方法相比，自然语言显着更好的电话长度。

63. 发明申请

US20050149330A1 Speech synthesis system 有权
标题翻译：语音合成系统
公开(公告)号：US20050149330A1
公开(公告)日：2005-07-07
申请号：US11070301
申请日：2005-03-03
申请人： Nobuyuki Katae
发明人： Nobuyuki Katae
IPC分类号： G10L13/06 , G10L13/00
CPC分类号： G10L13/07 , G10L13/06
摘要： A speech synthesizing system producing a speech of an improved quality of voice by selecting a combination of speech segment most suitable for a synthesis speech unit sequence. The speech synthesizing system comprises a speech segment storage section where speech segment is stored, a speech segment selection information storage section where speech segment selection information including combinations of speech segment constituted of speech segment stored in the speech segment storage section for an arbitrary speech unit sequence and the appropriateness information representing the appropriatenesses of the combinations are stored, a speech segment selecting section for selecting a combination of speech segment most suitable for a synthesis parameter according to the speech segment selection information stored in the speech segment storage section, and a waveform generating section for generating speech waveform data from the combination of speech segment selected by the speech segment selecting section.
摘要翻译：一种语音合成系统，通过选择最适合于合成语音单元序列的语音片段的组合来产生语音质量提高的语音。语音合成系统包括存储语音片段的语音段存储部分，语音段选择信息存储部分，其中语音片段选择信息包括由任意语音单元序列存储在语音片段存储部分中的语音片段组成的语音片段的组合并且存储表示组合的适当性的适当信息，用于根据存储在语音段存储部分中的语音段选择信息来选择最适合于合成参数的语音段的组合的语音段选择部分和产生从用于由语音片段选择部分选择的语音片段的组合产生语音波形数据的部分。

64. 发明申请

US20050060151A1 Automatic speech segmentation and verification method and system 有权
标题翻译：自动语音分段和验证方法和系统
公开(公告)号：US20050060151A1
公开(公告)日：2005-03-17
申请号：US10782955
申请日：2004-02-23
申请人： Chih-Chung Kuo , Chi-Shiang Kuo , Jau-Hung Chen
发明人： Chih-Chung Kuo , Chi-Shiang Kuo , Jau-Hung Chen
IPC分类号： G10L13/06 , G10L15/04 , G10L15/12 , G10L15/08
CPC分类号： G10L15/04 , G10L13/06
摘要： An automatic speech segmentation and verification system and method is disclosed, which has a known text script and a recorded speech corpus corresponding to the known text script. A speech unit segmentor segments the recorded speech corpus into N test speech unit segments referring to the phonetic information of the known text script. Then, a segmental verifier is applied to obtain a confidence measure of syllable segmentation for verifying the correctness of the cutting points of test speech unit segments. A phonetic verifier obtains a confidence measure of syllable verification by using verification models for verifying whether the recorded speech corpus is correctly recorded. Finally, a speech unit inspector integrates the confidence measure of syllable segmentation and the confidence measure of syllable verification to determine whether the test speech unit segment is accepted or not.
摘要翻译：公开了一种自动语音分段和验证系统和方法，其具有与已知文本脚本相对应的已知文本脚本和记录的语音语料库。参考已知文本脚本的语音信息，语音单元分段器将记录的语音语料库分割成N个测试语音单元段。然后，应用分段验证器来获得音节分割的置信度，以验证测试语音单元段的切割点的正确性。语音验证器通过使用验证模型来获得音节验证的置信度量度，以验证录制的语音库是否被正确记录。最后，语音单元检查器整合了音节分割的置信度量度和音节验证的置信度度量，以确定测试语音单元段是否被接受。

65. 发明申请

US20050060144A1 Voice labeling error detecting system, voice labeling error detecting method and program 有权
标题翻译：语音标签错误检测系统，语音标签错误检测方法和程序
公开(公告)号：US20050060144A1
公开(公告)日：2005-03-17
申请号：US10920454
申请日：2004-08-18
申请人： Rika Koyama
发明人： Rika Koyama
IPC分类号： G10L13/00 , G10L13/06 , G10L19/14
CPC分类号： G10L13/06
摘要： A labeling part 3 analyzes the character string data to produce a phoneme label and a prosody label, partition the voice data stored in a voice database 1 into phonemic data, and label the phonemic data, employing the phoneme label and the like. A phoneme segmenting part 4 connects the voice data labeled with the same kind of phonemic data, and a formant extracting part 5 specifies the frequency of formant of each piece of phonemic data. A processing part 6 decides an evaluation value for each phonemic data based on the frequency of formant, and an error detection part 7 detects the phonemic data of which a deviation of the evaluation value within a set of phonemic data reaches a predetermined amount.
摘要翻译：标签部分3分析字符串数据以产生音素标签和韵律标签，将存储在语音数据库1中的语音数据分割成音素数据，并使用音素标签等标记音素数据。音素分割部分4连接用相同类型的音素数据标记的语音数据，共振峰提取部分5指定每个音素数据的共振峰的频率。处理部分6基于共振峰的频率确定每个音素数据的评估值，并且错误检测部分7检测在一组音素数据内的评估值的偏差达到预定量的音素数据。

66. 发明申请

US20030154081A1 Objective measure for estimating mean opinion score of synthesized speech 失效
标题翻译：评估合成语音平均意见得分的客观量度
公开(公告)号：US20030154081A1
公开(公告)日：2003-08-14
申请号：US10073427
申请日：2002-02-11
发明人： Min Chu , Hu Peng
IPC分类号： G10L013/06
CPC分类号： G10L25/69 , G10L13/06
摘要： A method for estimating mean opinion score or naturalness of synthesized speech is provided. The method includes using an objective measure that has components derived directly from textual information used to form synthesized utterances. The objective measure has a high correlation with mean opinion score such that a relationship can be formed between the objective measure and corresponding mean opinion score. An estimated mean opinion score can be obtained easily from the relationship when the objective measure is applied to utterances of a modified speech synthesizer.
摘要翻译：提供了一种用于估计合成语音的平均意见分数或自然度的方法。该方法包括使用具有直接从用于形成合成话语的文本信息导出的成分的客观度量。客观量度与平均意见分数具有很高的相关性，从而可以在客观量度和相应的平均意见得分之间形成关系。当将客观量度应用于修改语音合成器的话语时，可以从关系中容易地获得估计的平均意见得分。

67. 发明申请

US20030028376A1 Method for prosody generation by unit selection from an imitation speech database 有权
标题翻译：通过模仿语音数据库的单位选择产生韵律的方法
公开(公告)号：US20030028376A1
公开(公告)日：2003-02-06
申请号：US09918595
申请日：2001-07-31
发明人： Joram Meron
IPC分类号： G10L013/00
CPC分类号： G10L13/06 , G10L13/04
摘要： A method is provided for prosody generation by unit selection from an imitation speech database. A rule based method of text to speech conversion is used to produce a set of intonation events by selecting syllables on which there would be either a pitch peak or dip (or a combination), and produces the parameters to generate a pitch curve of the event. The synthetic pitch curve shape generated by the rule based method is then utilized to select the best matching units from an imitation speech database of a speaker's prosody, which are then concatenated to reduce the final prosody.
摘要翻译：提供了通过来自模仿语音数据库的单元选择来产生韵律的方法。基于规则的文本到语音转换的方法被用于通过选择音调峰值或倾角（或组合）上的音节来产生一组语调事件，并且产生用于生成事件的音调曲线的参数。然后利用基于规则的方法生成的合成音调曲线形状，从扬声器韵律的模仿语音数据库中选出最佳匹配单元，然后连接起来，以减少最终的韵律。

68. 发明授权

US5897617A Method and device for preparing and using diphones for multilingual text-to-speech generating 失效
标题翻译：用于准备和使用双语言的多语言文本到语音生成的方法和设备
公开(公告)号：US5897617A
公开(公告)日：1999-04-27
申请号：US696431
申请日：1996-08-14
申请人： Rene P. G. Collier
发明人： Rene P. G. Collier
IPC分类号： G06F17/28 , G10L13/06 , G10L15/06 , G10L5/06 , G10L9/00
CPC分类号： G10L15/063 , G10L13/06
摘要： Diphones are prepared for text-to-speech converting by selectively pronouncing a set of selected diphones and processing each such diphone for persistent storage. Finally, each processed diphone is stored in an individually addressable manner. In particular, amongst such set as spoken by a single person, on a basis of homophony each diphone is assigned to one or more diverse languages. Sharing of selective diphones amongst more than one language diminishes required storage. The storage may entail language-specific processing qualifiers.
摘要翻译：通过选择性地发出一组选定的双声道并且处理每个这样的狄更斯以进行持续存储，准备了用于文本到语音转换的抽头。最后，每个处理的笛卡儿以可单独寻址的方式存储。特别地，在由单个人所说的这样的设置中，基于同音，每个双音素被分配到一种或多种不同的语言。在多种语言之间共享选择性双键可减少所需的存储空间。存储可能需要语言特定的处理限定符。

69. 发明授权

US5008942A Diagnostic voice instructing apparatus 失效
标题翻译：诊断语音指导装置
公开(公告)号：US5008942A
公开(公告)日：1991-04-16
申请号：US277865
申请日：1988-11-30
申请人： Hiromi Kikuchi
发明人： Hiromi Kikuchi
IPC分类号： A61B6/00 , A61B6/03 , G06F3/16 , G10L13/00 , G10L13/06
CPC分类号： A61B6/00 , A61B6/468 , G10L13/06
摘要： A diagnostic voice instructing apparatus has a recording/playback device including a voice recording/playback LSI and a RAM, and converts an arbitrary instruction voice to a patient, which has been input through a microphone by a user for use in a scanning operation, into a digital signal and stores the signal in corresponding one of 15 channels of the RAM, the instructing voice may be input in an arbitrary language, dialect or expression. The recording/playback device is coupled to a scan controller, which controls the scanning operation of a CT apparatus, and a host controller, which sends commands to the recording/playback device and scan controller and receives control data from the scan controller. The host controller permits an operator to prepare ID data to each patient, which includes the name, and condition, of the patient, as well as designation of the necessary instructing voice to the patient in terms of a channel quantity. When the patient ID data is read out from the host controller and supplied to the recording/playback device, and when the CT apparatus starts scanning the patient in response to a command from the scan controller, an instructing voice is read out from the channel designated by the patient ID data at the proper timing in synchronism with the scanning operation and is supplied through an amplifier to a speaker for its reproduction.
摘要翻译：诊断语音指示装置具有包括语音记录/再现LSI和RAM的记录/重放装置，并且将用户经由麦克风输入的用于扫描操作的病人的任意指令语音转换为患者，数字信号并将信号存储在RAM的15个通道的相应的一个中，可以以任意语言，方言或表达形式输入指令语音。记录/重放装置耦合到控制CT装置的扫描操作的扫描控制器和向记录/重放装置和扫描控制器发送命令并从扫描控制器接收控制数据的主机控制器。主机控制器允许操作者准备每个患者的ID数据，包括患者的姓名和状况，以及根据信道数量向病人指定必要的指示语音。当从主机控制器读取患者ID数据并提供给记录/重放装置时，当CT装置响应于来自扫描控制器的命令开始扫描患者时，从指定的信道中读出指示语音通过与扫描操作同步的适当定时的患者ID数据，并通过放大器提供给扬声器以进行再现。

70. 发明授权

US4760245A Method and apparatus for providing a voice output for card-based automatic transaction system 失效
标题翻译：为基于卡的自动交易系统提供语音输出的方法和装置
公开(公告)号：US4760245A
公开(公告)日：1988-07-26
申请号：US010485
申请日：1987-02-03
申请人： Sadao Fukaya
发明人： Sadao Fukaya
IPC分类号： G07D9/00 , G06F3/16 , G06Q40/00 , G06Q40/02 , G07F19/00 , G10L13/06 , G06F15/30
CPC分类号： G07F19/201 , G07F19/20 , G10L13/06
摘要： In an automatic transaction system such as a cash dispenser, a telephone or a ticket vending machine having a card reader for reading the content of a card and a voice output unit for guiding an operation procedure following a card loading with synthesized speech, when a card in which a data of user's hearing sensitivity is recorded/embossed is inserted, the hearing sensitivity data is read out from the card the voice output unit is accordingly controlled to output an indication voice or a guidance voice for the user with a volume and a quality of tone corresponding to the read hearing sensitivity data, and the hearing sensitivity data set for the voice output is updated each time a predetermined time for an operation of the user lapses to increase the volume of the output voice, and/or modify the tone quality thereof to thereby aid the hearing of the speech guidance.
摘要翻译：在自动交易系统中，例如自动取款机，具有用于读取卡片内容的读卡器的电话机或售票机，以及用于引导在合成语音卡加载之后的操作过程的语音输出单元，当卡片其中插入了用户听力敏感度的数据/压印，从卡中读出听力敏感度数据，声音输出单元相应地被控制，以输出音量和质量的用户的指示语音或指导语音对应于读取的听力敏感度数据的音调，并且每当用户的操作的预定时间失效以增加输出语音的音量时，更新用于语音输出的听力敏感度数据，和/或修改音调质量从而有助于语音引导的听觉。

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