公开(公告)号：US08049093B2

公开(公告)日：2011-11-01

申请号：US12649458

申请日：2009-12-30

申请人： Woojay Jeon ,  Changxue Ma

发明人： Woojay Jeon ,  Changxue Ma

IPC分类号： G04B13/00

CPC分类号： G10H1/0008 ,  G10H2210/066 ,  G10H2240/141 ,  G10H2250/251

摘要： During operation, a “coarse search” stage applies variable-scale windowing on the query pitch contours to compare them with fixed-length segments of target pitch contours to find matching candidates while efficiently scanning over variable tempo differences and target locations. Because the target segments are of fixed-length, this has the effect of drastically reducing the storage space required in a prior-art method. Furthermore, by breaking the query contours into parts, rhythmic inconsistencies can be more flexibly handled. Normalization is also applied to the contours to allow comparisons independent of differences in musical key. In a “fine search” stage, a “segmental” dynamic time warping (DTW) method is applied that calculates a more accurate similarity score between the query and each candidate target with more explicit consideration toward rhythmic inconsistencies.

摘要翻译： 在操作期间，“粗略搜索”阶段在查询音调轮廓上应用可变尺度窗口，以将其与目标俯仰轮廓的固定长度段进行比较，以在有效扫描可变速度差异和目标位置的同时找到匹配候选。 因为目标段是固定长度的，所以这具有显着减少现有方法所需的存储空间的效果。 此外，通过将查询轮廓分解成部分，可以更灵活地处理节奏不一致。 归一化也适用于轮廓，以便独立于音乐键的差异进行比较。 在“精细搜索”阶段，应用“分段”动态时间扭曲（DTW）方法，通过更明确地考虑节奏不一致来计算查询和每个候选目标之间的更准确的相似性分数。

公开(公告)号：US20110154977A1

公开(公告)日：2011-06-30

申请号：US12649458

申请日：2009-12-30

申请人： Woojay Jeon ,  Changxue Ma

发明人： Woojay Jeon ,  Changxue Ma

IPC分类号： G10H7/00

CPC分类号： G10H1/0008 ,  G10H2210/066 ,  G10H2240/141 ,  G10H2250/251

摘要： During operation, a “coarse search” stage applies variable-scale windowing on the query pitch contours to compare them with fixed-length segments of target pitch contours to find matching candidates while efficiently scanning over variable tempo differences and target locations. Because the target segments are of fixed-length, this has the effect of drastically reducing the storage space required in a prior-art method. Furthermore, by breaking the query contours into parts, rhythmic inconsistencies can be more flexibly handled. Normalization is also applied to the contours to allow comparisons independent of differences in musical key. In a “fine search” stage, a “segmental” dynamic time warping (DTW) method is applied that calculates a more accurate similarity score between the query and each candidate target with more explicit consideration toward rhythmic inconsistencies.

摘要翻译： 在操作期间，“粗略搜索”阶段在查询音调轮廓上应用可变尺度窗口，以将其与目标俯仰轮廓的固定长度段进行比较，以在有效扫描可变速度差异和目标位置的同时找到匹配候选。 因为目标段是固定长度的，所以这具有显着减少现有方法所需的存储空间的效果。 此外，通过将查询轮廓分解成部分，可以更灵活地处理节奏不一致。 归一化也适用于轮廓，以便独立于音乐键的差异进行比较。 在“精细搜索”阶段，应用“分段”动态时间扭曲（DTW）方法，通过更明确地考虑节奏不一致来计算查询和每个候选目标之间的更准确的相似性分数。

公开(公告)号：US08442823B2

公开(公告)日：2013-05-14

申请号：US12907729

申请日：2010-10-19

申请人： Woojay Jeon ,  Yan-Ming Cheng ,  Changxue Ma ,  Dusan Macho

发明人： Woojay Jeon ,  Yan-Ming Cheng ,  Changxue Ma ,  Dusan Macho

IPC分类号： G10L15/00

CPC分类号： G10L15/1822

摘要： A method of performing a search of a database of speakers, includes: receiving a query speech sample spoken by a query speaker; deriving a query utterance from the query speech sample; extracting query utterance statistics from the query utterance; performing Kernelized Locality-Sensitive Hashing (KLSH) using a kernel function, the KLSH using as input the query utterance statistics and utterance statistics extracted from a plurality of utterances included in a database of speakers in order to select a subset of the plurality of utterances; and comparing, using an utterance comparison equation, the query utterance statistics to the utterance statistics for each utterance in the subset to generate a list of speakers from the database of utterances having a highest similarity to the query speaker.

摘要翻译： 一种执行对扬声器数据库的搜索的方法，包括：接收由查询扬声器所说出的查询语音样本; 从查询语音样本中导出查询语句; 从查询语句中提取查询语句统计信息; 使用核函数执行内核局部敏感哈希（KLSH），所述KLSH使用包括在扬声器数据库中的多个话语中提取的查询话语统计和话音统计作为输入，以便选择所述多个话语的子集; 以及使用话语比较方程比较所述子集中每个话语的话语统计量的查询话语统计量，以从所述数据库中产生具有与所述查询发音者具有最高相似性的话语的说话者列表。

公开(公告)号：US08041700B2

公开(公告)日：2011-10-18

申请号：US12419341

申请日：2009-04-07

申请人： Changxue Ma

发明人： Changxue Ma

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/30675

摘要： A method and apparatus for textual searching of a database is provided herein. During operation a user will input a letter into a search engine. The search engine will score words based on the letter and display results of the highest-scored words. Another letter will again be received and the process repeated. In situations where titles are returned to the user, additional steps of associating the words with a title and scoring the title take place. The highest-scored titles are provided to the user as the displayed results.

摘要翻译： 本文提供了一种用于文本搜索数据库的方法和装置。 在操作期间，用户将输入一个字母到搜索引擎。 搜索引擎将根据最高得分字的字母和显示结果对单词进行分数。 再次收到另一封信，重复过程。 在将标题返回给用户的情况下，会发生将单词与标题相关联并对标题进行评分的其他步骤。 作为显示结果，向用户提供最高分的标题。

公开(公告)号：US20110071826A1

公开(公告)日：2011-03-24

申请号：US12564968

申请日：2009-09-23

申请人： Changxue Ma ,  Harry M. Bliss

发明人： Changxue Ma ,  Harry M. Bliss

IPC分类号： G10L15/26 ,  G06F17/30

CPC分类号： G10L15/083 ,  G06F16/3343

摘要： A method and apparatus for ordering results from a query is provided herein. During operation, a spoken query is received and converted to a textual representation, such as a word lattice. Search strings are then created from the word lattice. For example a set search strings may be created from the N-grams, such as unigrams and bigrams, of the word lattice. The search strings may be ordered and truncated based on confidence values assigned to the n-grams by the speech recognition system. The set of search strings are sent to at least one search engine, and search results are obtained. The search results are then re-arranged or reordered based on a semantic similarity between the search results and the word lattice.

摘要翻译： 本文提供了一种用于排序查询结果的方法和装置。 在操作期间，接收到口语查询并将其转换为文本表示，例如单词格。 搜索字符串然后从单词格中创建。 例如，可以从单词格的N克（例如单字母和双字母）创建集合搜索字符串。 搜索字符串可以基于由语音识别系统分配给n-gram的置信度来排序和截断。 搜索字符串集合被发送到至少一个搜索引擎，并且获得搜索结果。 然后基于搜索结果和单词格之间的语义相似度重新排列或重新排序搜索结果。

公开(公告)号：US20090210226A1

公开(公告)日：2009-08-20

申请号：US12032258

申请日：2008-02-15

申请人： Changxue Ma

发明人： Changxue Ma

IPC分类号： G10L15/08

CPC分类号： G10L15/26 ,  G10L2015/025 ,  G10L2015/088

摘要： A method, system and communication device for enabling voice-to-voice searching and ordered content retrieval via audio tags assigned to individual content, which tags generate uniterms that are matched against components of a voice query. The method includes storing content and tagging at least one of the content with an audio tag. The method further includes receiving a voice query to retrieve content stored on the device. When the voice query is received, the method completes a voice-to-voice search utilizing uniterms of the audio tag, scored against the phoneme latent lattice model generated by the voice query to identify matching terms within the audio tags and corresponding stored content. The retrieved content(s) associated with the identified audio tags having uniterms that score within the phoneme lattice model are outputted in an order corresponding to an order in which the uniterms are structured within the voice query.

摘要翻译： 一种用于通过分配给各个内容的音频标签启用语音到语音搜索和排序内容检索的方法，系统和通信设备，该标签生成与语音查询的组件匹配的单位。 该方法包括存储内容并且将具有音频标签的内容中的至少一个标记。 该方法还包括接收语音查询以检索存储在设备上的内容。 当接收到语音查询时，该方法使用音频标签的单位完成语音到语音搜索，对由语音查询产生的音素潜在网格模型进行评分，以识别音频标签内的匹配项和对应的存储内容。 与所识别的音频标签相关联的检索到的内容，其具有在音素格子模型内得分的单位格式，其顺序与语音查询内的单元格结构的顺序相对应地输出。

公开(公告)号：US20090089059A1

公开(公告)日：2009-04-02

申请号：US11863763

申请日：2007-09-28

申请人： Changxue Ma ,  Harry M. Bliss

发明人： Changxue Ma ,  Harry M. Bliss

IPC分类号： G10L15/04

CPC分类号： G10L15/24 ,  G06F3/016 ,  G06F3/0481 ,  G10L15/06 ,  G10L15/187 ,  H04M1/72538 ,  H04M1/72547 ,  H04M2250/12 ,  H04M2250/22 ,  H04M2250/74

摘要： A method and apparatus for enabling multimodal tags in a communication device is disclosed. The method comprises receiving a first training signal and receiving a second training signal in conjunction with the first training signal. A multimodal tag is created to represent a combination of the first training signal and the second training signal and a function is associated with the created multimodal tag.

摘要翻译： 公开了一种用于在通信设备中实现多模式标签的方法和装置。 所述方法包括接收第一训练信号并且与第一训练信号一起接收第二训练信号。 创建多模式标签以表示第一训练信号和第二训练信号的组合，并且功能与所创建的多模态标签相关联。

公开(公告)号：US20090066541A1

公开(公告)日：2009-03-12

申请号：US11853912

申请日：2007-09-12

申请人： Changxue Ma ,  Wei Lin ,  Li-Xin Zhen

发明人： Changxue Ma ,  Wei Lin ,  Li-Xin Zhen

IPC分类号： G06F3/023

CPC分类号： G06F3/0231 ,  G06F3/0237

摘要： A portable electronic communication device, designed for voice and data communication is utilized as a peripheral input device for transmitting/providing character inputs, entered in the first device's touch input mechanism, to a second electronic device. The first device has a mode switching utility that switches the first device between a first standard communication mode and a second peripheral input device mode. When the first device is in the second peripheral input device mode, the first device operates as a peripheral input device for the second device. A character input recognition utility executes on the first device to provide the functions of: detecting an input on the touch screen input mechanism; generating an electronic representation of the input; establishing a communication link between the second communication transmitter and an identified second device; and forwarding the electronic representation of the character input to the communication transmitter for transmission to the identified second device.

摘要翻译： 用于语音和数据通信的便携式电子通信设备被用作用于将输入到第一设备的触摸输入机构中的字符输入发送/提供给第二电子设备的外围输入设备。 第一设备具有模式切换实用程序，用于在第一标准通信模式和第二外围输入设备模式之间切换第一设备。 当第一设备处于第二外设输入设备模式时，第一设备作为第二设备的外围输入设备工作。 字符输入识别实用程序在第一设备上执行以提供以下功能：检测触摸屏输入机构上的输入; 生成输入的电子表示; 建立第二通信发射机和识别的第二设备之间的通信链路; 以及将所述字符输入的电子表示转发到所述通信发射机以便发送到所识别的第二设备。

公开(公告)号：US20070239455A1

公开(公告)日：2007-10-11

申请号：US11278983

申请日：2006-04-07

申请人： Michael Groble ,  Changxue Ma

发明人： Michael Groble ,  Changxue Ma

IPC分类号： G10L13/08

CPC分类号： G10L15/187 ,  G10L13/08

摘要： A voice toolkit (100) and a method (700) for managing pronunciation dictionaries are provided. The visual toolkit can include a user-interface (110) for entering in a text and a corresponding spoken utterance, a text-to-speech system (120) for synthesizing a pronunciation from the text, a talking speech recognizer (132) for generating pronunciations of the spoken utterance, and a voice processor (130) for validating at least one pronunciation. A developer can type a text of a word into the toolkit and listen to the pronunciation to determine whether the pronunciation is acceptable. If the pronunciation is incorrect the developer can speak the word for providing a spoken utterance having a correct pronunciation.

摘要翻译： 提供了一种用于管理发音词典的语音工具包（100）和方法（700）。 视觉工具包可以包括用于输入文本的用户界面（110）和对应的说话话语，用于从文本合成发音的文本到语音系统（120），用于生成语音识别器（132） 讲话语音的发音，以及用于验证至少一个发音的语音处理器（130）。 开发人员可以在工具包中输入单词的文字，并听发音来确定发音是否可以接受。 如果发音不正确，开发人员可以说出提供具有正确发音的口语发音。

公开(公告)号：US07983428B2

公开(公告)日：2011-07-19

申请号：US11746455

申请日：2007-05-09

申请人： Changxue Ma ,  Chen Liu

发明人： Changxue Ma ,  Chen Liu

IPC分类号： H04B15/00

CPC分类号： H04M9/082 ,  H04M1/6066

摘要： A communication device includes: (1) a wireless adapter at which a wireless headset is communicatively connected to the communication device and at which is received a first acoustic input that includes a speech input and a first ambient noise input; (2) a microphone that receives a second acoustic input, which includes a second ambient noise input; and (3) a dual-channel adaptive noise canceller that utilizes the second ambient noise input to filter the first ambient noise input out of the first acoustic input to generate an acoustic output that primarily comprises the speech input.

摘要翻译： 通信设备包括：（1）无线适配器，其中无线耳机通信地连接到通信设备，并且其中接收到包括语音输入和第一环境噪声输入的第一声输入; （2）麦克风，其接收包括第二环境噪声输入的第二声输入; 以及（3）双通道自适应噪声消除器，其利用所述第二环境噪声输入来对从所述第一声输入中输出的所述第一环境噪声进行滤波，以产生主要包括所述语音输入的声输出。