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

US06778962B1 Speech synthesis with prosodic model data and accent type 失效
标题翻译：语音合成与韵律模型数据和重音类型
公开(公告)号：US06778962B1
公开(公告)日：2004-08-17
申请号：US09621545
申请日：2000-07-21
申请人： Osamu Kasai , Toshiyuki Mizoguchi
发明人： Osamu Kasai , Toshiyuki Mizoguchi
IPC分类号： G10L1308
CPC分类号： G10L13/10 , A63F2300/6063
摘要： A speech synthesizing method includes determining the accent type of the input character string, selecting the prosodic model data from a prosody dictionary for storing typical ones of the prosodic models representing the prosodic information for the character strings in a word dictionary, based on the input character string and the accent type, transforming the prosodic information of the prosodic model when the character string of the selected prosodic model is not coincident with the input character string, selecting the waveform data corresponding to each character of the input character string from a waveform dictionary, based on the prosodic model data after transformation, and connecting the selected waveform data with each other. Therefore, a difference between an input character string and a character string stored in a dictionary is absorbed, then it is possible to synthesize a natural voice.
摘要翻译：语音合成方法包括：确定输入字符串的重音类型，从韵律词典中选择韵律模型数据，用于存储表示词典中字符串的韵律信息的典型韵律模型，基于输入字符字符串和重音类型，当所选择的韵律模型的字符串与输入字符串不一致时，转换韵律模型的韵律信息，从波形词典中选择与输入字符串的每个字符对应的波形数据，基于变形后的韵律模型数据，并将所选择的波形数据相互连接。因此，输入字符串和存储在字典中的字符串之间的差异被吸收，则可以合成自然语音。

2. 发明授权

US06681208B2 Text-to-speech native coding in a communication system 有权
标题翻译：通信系统中的文本到语音本机编码
公开(公告)号：US06681208B2
公开(公告)日：2004-01-20
申请号：US09962747
申请日：2001-09-25
申请人： Bin Wu , Fan He
发明人： Bin Wu , Fan He
IPC分类号： G10L1308
CPC分类号： G10L13/08 , G10L19/00
摘要： A method of converting text to speech in a communication device includes providing a code table containing coded speech parameters. Next steps include inputting a text message into a communication device, and dividing the text message into phonics. A next step includes mapping each of the phonics against the code table to find the coded speech parameters corresponding to each of the phonics. A next step includes processing the coded speech parameters corresponding to each of the phonics to provide an audio signal. In this way, text can be mapped directly to a vocoder table without intermediate translation steps.
摘要翻译：在通信设备中将文本转换为语音的方法包括提供包含编码语音参数的代码表。接下来的步骤包括将文本消息输入到通信设备中，并将文本消息划分成语音。下一步包括将每个语音对准代码表映射以找到与每个语音对应的编码语音参数。下一步骤包括处理对应于每个语音的编码语音参数以提供音频信号。以这种方式，文本可以直接映射到声码器表，而不需要中间的翻译步骤。

3. 发明授权

US06487533B2 Unified messaging system with automatic language identification for text-to-speech conversion 有权
标题翻译：统一消息系统，具有自动语言识别功能，可进行文本转语音转换
公开(公告)号：US06487533B2
公开(公告)日：2002-11-26
申请号：US09480296
申请日：2000-01-10
申请人： Henry C. A. Hyde-Thomson , Roger Liron
发明人： Henry C. A. Hyde-Thomson , Roger Liron
IPC分类号： G10L1308
CPC分类号： H04L51/066 , G10L13/08 , G10L15/005 , H04M3/5307 , H04M2201/60
摘要： A unified messaging system includes a voice gateway server coupled to an electronics mail system and a private branch exchange (PBX). The voice gateway server provides voice messaging services to a set of subscribers. Within the voice gateway server, a trigraph analyzer sequentially examines 3-character combinations within a text message; determines occurrence frequencies for the character combinations; compares the occurrence frequencies with reference occurrence statistics modeled from text samples written in particular languages; and generates a language identifier and a likelihood value for the text message. Based upon the language identifier, a message inquiry unit selects an appropriate text-to-speech engine for converting the text message into computer-generated speech that is played to a subscriber.
摘要翻译：统一消息系统包括耦合到电子邮件系统和专用小交换机（PBX）的语音网关服务器。语音网关服务器向一组用户提供语音消息传送服务。在语音网关服务器内，三元分析器顺序地检查文本消息内的3个字符组合; 确定字符组合的出现频率; 将出现频率与以特定语言编写的文本样本建模的参考出现统计进行比较; 并生成文本消息的语言标识符和似然值。基于语言标识符，消息查询单元选择适当的文本到语音引擎，用于将文本消息转换为对用户播放的计算机生成的语音。

4. 发明授权

US06466909B1 Shared text-to-speech resource 有权
标题翻译：共享的文本到语音资源
公开(公告)号：US06466909B1
公开(公告)日：2002-10-15
申请号：US09340552
申请日：1999-06-28
申请人： Cliff Didcock
发明人： Cliff Didcock
IPC分类号： G10L1308
CPC分类号： G10L13/047
摘要： An architecture is provided for sharing text-to-speech (TTS) resources. A TTS controller manages the allocation of the TTS resources. An application provides a conversion request which is provided to a first queue. An available TTS resource begins a conversion upon sentence boundaries and converts a predetermined minimum amount of text. Once a sufficient amount of text is converted, the digitized speech data is played to a user. The amount of converted data is monitored during the playback operation. As the totality of the converted data falls below a predetermined minimum the TTS controller is notified. If more text remains in a message being converted, the TTS controller places a request into a second queue. The second queue has a higher priority so that continuing conversions are completed before subsequent conversions begin. The user is able to cancel this conversion operation at any time. By cancelling this conversion operation, TTS resources are conserved by not unnecessarily converting the whole text message.
摘要翻译：提供了一种用于共享文本到语音（TTS）资源的体系结构。 TTS控制器管理TTS资源的分配。应用程序提供提供给第一个队列的转换请求。可用的TTS资源开始对句子边界进行转换，并转换预定的最小量的文本。一旦转换了足够数量的文本，就向用户播放数字化的语音数据。在播放操作期间监视转换数据的数量。由于转换数据的总数低于预定的最小值，所以通知TTS控制器。如果正在转换的消息中留下更多文本，则TTS控制器将请求放入第二个队列。第二个队列具有较高的优先级，以便在后续转换开始之前完成持续转换。用户可以随时取消此转换操作。通过取消此转换操作，TTS资源不会不必要地转换整个文本消息而被保存。

5. 发明授权

US06411931B1 Character data transformer and transforming method 失效
标题翻译：字符数据变换和变换方法
公开(公告)号：US06411931B1
公开(公告)日：2002-06-25
申请号：US09269724
申请日：1999-12-13
申请人： Eiichi Yamada
发明人： Eiichi Yamada
IPC分类号： G10L1308
CPC分类号： G10L13/08 , G06F3/16
摘要： An apparatus for converting character data into audio data form includes a storage unit for storing the character data supplied, an operating unit manipulated by the user, and a control unit responsive to the entry of command from the operating unit for producing indicator data indicative of unwanted portions of the character data which are not required for conversion to audio data, comparing the indicator data with the character data read out from the storage unit, and converting the portion of the character data not corresponding to the indicator data into its audio data form. As the character data read out from the storage unit has been compared with the indicator data not indicative of the unwanted portions of the character data required for conversion to audio data, its dedicated portion not corresponding to the indicator data is converted into its audio data form. This allows the dedicated portion of the character data to be readily converted into its audio data form while aborting the unwanted portions of the character data, thus enabling quick acquisition of the information.
摘要翻译：用于将字符数据转换成音频数据形式的装置包括存储单元，用于存储提供的字符数据，由用户操纵的操作单元和响应于来自操作单元的命令的输入的控制单元，用于产生指示不期望的指示符数据比较指示符数据与从存储单元读出的字符数据，将与指示符数据不相对应的字符数据的部分转换为其音频数据形式，将字符数据的部分转换成音频数据不需要。当从存储单元读出的字符数据与未指示转换为音频数据所需的字符数据的不需要部分的指示符数据进行比较时，其与指示符数据不相对应的专用部分被转换为其音频数据形式。这允许字符数据的专用部分容易地转换成其音频数据形式，同时中止字符数据的不希望的部分，从而能够快速获取信息。

6. 发明授权

US06269329B1 Input and output communication in a data processing system 失效
标题翻译：数据处理系统中的输入和输出通信
公开(公告)号：US06269329B1
公开(公告)日：2001-07-31
申请号：US08966851
申请日：1997-11-10
申请人： Rabbe Nordstrom
发明人： Rabbe Nordstrom
IPC分类号： G10L1308
CPC分类号： G06F17/2881 , G06F17/277 , G10L13/027
摘要： A processor (47) uses a concepts memory area (10) to interpret received inputs and to generate coherent content-related output communication in text or fluent speech. The processor (47) uses concepts, each being a part of program code and a linked basic communication element. A parallel recursive communication matrix manager (10(a)) is used in processing of the concepts and reference is made to a conception, learning, associative utilisation manager (50) to assist in understanding inputs, learning and enhancing the knowledge base, and in developing outputs. The basic communication elements may trigger associated speech resources (24) which are retrieved and processed downstream, or rule-based speech outputted via a synthesiser (63).
摘要翻译：处理器（47）使用概念存储区域（10）来解释所接收的输入并且在文本或流畅语音中生成相干内容相关的输出通信。处理器（47）使用概念，每个概念是程序代码的一部分和链接的基本通信元件。并行递归通信矩阵管理器（10（a））被用于概念的处理，并且引用概念，学习，关联利用管理器（50）来帮助理解输入，学习和增强知识库，并且开发产出。基本通信元件可以触发经由合成器（63）输出的下游检索和处理的相关语音资源（24）或基于规则的语音。

7. 发明授权

US06182040B2 Voice-synthesizer responsive to panel display message 失效
标题翻译：语音合成器响应面板显示消息
公开(公告)号：US06182040B2
公开(公告)日：2001-01-30
申请号：US09082147
申请日：1998-05-21
申请人： Dino Monaco
发明人： Dino Monaco
IPC分类号： G10L1308
CPC分类号： G10L13/027 , G10L13/04
摘要： A voice-synthesizer driven by matrix-type panel displays of the type that present alpha-numeric characters captures all or part of the digital values that are used to drive the message display and uses the so-capture information to address a look-up table (44) that outputs a series of digital values to a voce-synthesizer (30). The process is triggered by an alarm status signal so that the voce-synthesizer (30) functions to articulate an alarm message and not articulate non-alarm messages.
摘要翻译：由矩阵型面板显示器驱动的语音合成器，其类型表示字母数字字符捕获用于驱动消息显示的全部或部分数字值，并使用所谓捕获信息来寻址查找表（44），其将一系列数字值输出到声音合成器（30）。该过程由报警状态信号触发，使得声音合成器（30）起到清除报警信息的作用，而不能表达非报警信息。

8. 发明授权

US06173262B2 Text-to-speech system with automatically trained phrasing rules 失效
标题翻译：具有自动训练的措辞规则的文本到语音系统
公开(公告)号：US06173262B2
公开(公告)日：2001-01-09
申请号：US08548794
申请日：1995-11-02
申请人： Julia Hirschberg
发明人： Julia Hirschberg
IPC分类号： G10L1308
CPC分类号： G10L13/04
摘要： A method of training a TTS or other system to assign intonational features, such as intonational phrase boundaries, is described. The method of training involves taking a set of predetermined text (not speech or a signal representative of speech) and having a human annotate it with intonational feature annotations. This results in annotated text. Next, the structure of the set of predetermined text is analyzed to generate information. This information is used, along with the intonational feature annotations, to generate a statistical representation. The statistical representation may then be stored and repeatedly used to generate synthesized speech from new sets of input text without training the TTS system further.
摘要翻译：描述了训练TTS或其他系统以分配语调特征（例如语调短语边界）的方法。训练的方法涉及采用一组预定文本（而不是语音或代表语音的信号），并且使人们用语言特征注释来注释它。这将导致注释文本。接下来，分析该组预定文本的结构以生成信息。该信息与语义特征注释一起用于生成统计表示。然后可以存储并重复使用统计表示，以从新的输入文本集合生成合成语音，而不进一步训练TTS系统。

9. 发明授权

US06813604B1 Methods and apparatus for speaker specific durational adaptation 有权
标题翻译：讲话者具体持续适应的方法和装置
公开(公告)号：US06813604B1
公开(公告)日：2004-11-02
申请号：US09711563
申请日：2000-11-13
申请人： Chi-Lin Shih , Jan Pieter Hendrik van Santen
发明人： Chi-Lin Shih , Jan Pieter Hendrik van Santen
IPC分类号： G10L1308
CPC分类号： G10L13/033 , G10L15/07 , G10L2021/0135
摘要： A text to speech system modeling durational characteristics of a target speaker is addressed herein. A body of target speaker training text is selected having maximum possible information about speaker specific characteristics. The body of target speaker training text is read by a target speaker to produce a target speaker training corpus. A previously generated source model reflecting characteristics of a source model is retrieved and the target speaker training corpus is processed to produce modification parameters reflecting differences between durational characteristics of the target speaker and those predicted by the source model. The modification parameters are applied to the source model to produce a target model. Text inputs are processed using the target model to produce speech outputs reflecting durational characteristics of the target speaker.
摘要翻译：本文解决了目标扬声器的文本到语音系统建模持续时间特征。选择具有关于扬声器特定特征的最大可能信息的目标扬声器训练文本的主体。目标扬声器训练文本的主体由目标演讲者读取，以产生目标讲话者训练语料库。检索反映源模型特征的先前产生的源模型，并处理目标说话者训练语料库以产生反映目标讲话人的持续时间特征与源模型预测的持续时间特征之间的差异的修改参数。将修改参数应用于源模型以产生目标模型。使用目标模型处理文本输入以产生反映目标扬声器的持续特性的语音输出。

10. 发明授权

US06708152B2 User interface for text to speech conversion 有权
标题翻译：用户界面进行文字转换
公开(公告)号：US06708152B2
公开(公告)日：2004-03-16
申请号：US09739792
申请日：2000-12-20
申请人： Mika Kivimäki
发明人： Mika Kivimäki
IPC分类号： G10L1308
CPC分类号： H04M1/72547 , G10L13/04
摘要： An electronic device which comprises a speech synthesizer including a loudspeaker, arranged to convert an input dependent upon punctuated text, to an audio output representative of a human vocally reproducing the text. It also comprises a user input device for inputting instructions to navigate through text, between positions defined by punctuation identifiers of the text, to a desired position, and a controller arranged to control navigation to the desired position and provide the speech synthesizer with an input corresponding to a portion of the text from the desired position, in response to input navigation instructions.
摘要翻译：一种电子设备，其包括语音合成器，该语音合成器包括扬声器，其布置成将取决于标点符号的文本的输入转换为代表人类声音再现文本的音频输出。它还包括一个用户输入装置，用于输入指令以在文本之间进行导航，在由文本的标点符号标识符定义的位置到期望的位置之间，以及控制器，其被布置成控制导航到期望的位置，并向语音合成器提供相应的输入响应于输入导航指令，从期望位置到文本的一部分。

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