利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

18 条记录 (耗时 0.021 秒)

    Hierarchical labeler in a speech recognition system
    11.
    发明授权
    Hierarchical labeler in a speech recognition system 失效
    语音识别系统中的分层标签器

    公开(公告)号：US6023673A

    公开(公告)日：2000-02-08

    申请号：US869061

    申请日：1997-06-04

    申请人： Raimo Bakis ,  David Nahamoo ,  Michael Alan Picheny ,  Jan Sedivy

    发明人： Raimo Bakis ,  David Nahamoo ,  Michael Alan Picheny ,  Jan Sedivy

    IPC分类号： G10L5/06 ,  G10L9/00

    CPC分类号： G10L15/083

    摘要： A speech coding apparatus and method uses a hierarchy of prototype sets to code an utterance while consuming fewer computing resources. The value of at least one feature of an utterance is measured during each of a series of successive time intervals to produce a series of feature vector signals representing the feature values. A plurality of level subsets of prototype vector signals is computed, wherein each prototype vector signal in a higher level subset is associated with at least one prototype vector signal in a lower level subset. Each level subset contains a plurality of prototype vector signals, with lower level subsets containing more prototypes than higher level subsets. The closeness of the feature value of the first feature vector signal is compared to the parameter values of prototype vector signals in the first level subset of prototype vector signals to obtain a ranked list of prototype match scores for the first feature vector signal and each prototype vector signal in the first level subset. The closeness of the feature value of the first feature vector signal is compared to the parameter values of each prototype vector signal in a second (lower) level subset that is associated with the highest ranking prototype vectors in the first level subset, to obtain a second ranked list of prototype match scores. The identification value of the prototype vector signal in the second ranked list having the best prototype match score is output as a coded utterance representation signal of the first feature vector signal.

    摘要翻译： 语音编码装置和方法使用原型集的层次来编码话语，同时消耗更少的计算资源。 在一系列连续时间间隔的每一个期间测量话音的至少一个特征的值，以产生表示特征值的一系列特征向量信号。 计算原型矢量信号的多个级别子集，其中较高级子集中的每个原型矢量信号与较低级子集中的至少一个原型矢量信号相关联。 每个级别子集包含多个原型矢量信号，其中较低级子集包含比较高级子集更多的原型。 将第一特征向量信号的特征值的接近度与原型矢量信号的第一级子集中的原型矢量信号的参数值进行比较，以获得第一特征向量信号和每个原型矢量的原型匹配分数的排序列表 信号在第一级子集。 将第一特征向量信号的特征值的接近度与与第一级子集中的最高排序原型向量相关联的第二（较低）级子集中的每个原型矢量信号的参数值进行比较，以获得第二 排名榜的原型比赛得分。 将具有最佳原型匹配分数的第二等级列表中的原型矢量信号的识别值输出为第一特征向量信号的编码话音表示信号。

    Method and apparatus for a communication device for use by a hearing impaired/mute or deaf person or in silent environments
    16.
    发明授权
    Method and apparatus for a communication device for use by a hearing impaired/mute or deaf person or in silent environments 失效
    用于由听力障碍/静音或聋人或无声环境使用的通信装置的方法和装置

    公开(公告)号：US5995590A

    公开(公告)日：1999-11-30

    申请号：US35493

    申请日：1998-03-05

    申请人： Peter Thomas Brunet ,  Abraham P. Ittycheriah ,  Chandrasekhar Narayanaswami ,  Michael Alan Picheny ,  Bhuvana Ramabhadran

    发明人： Peter Thomas Brunet ,  Abraham P. Ittycheriah ,  Chandrasekhar Narayanaswami ,  Michael Alan Picheny ,  Bhuvana Ramabhadran

    IPC分类号： G10L13/00 ,  H04M1/247 ,  H04M11/00

    CPC分类号： H04M1/2475 ,  G10L13/00

    摘要： A method and apparatus is disclosed that allows people to carry on unobtrusive phone conversations in business or other settings where it is either not possible or impolite to talk. In the system of FIG. 1, the telephone user one will listen in the same manner as with a regular telephone. However, he will not speak into the telephone microphone. User one instead employs a unit including a keyboard to enter the text corresponding to what he wants to say. The text is converted into a synthesized speech using TTS apparatus and a voice output is sent to the microphone of the phone apparatus. The telephone apparatus transmits the synthesized voice signal over a standard telephone line to a unit including a conventional telephone speaker 26 and telephone microphone. User two, the party using the telephone at the other end, listens to a synthesized voice, but user one listens to the actual voice of user two with the telephone speaker, unless user two is also using a system similar to that of user one. Handwritten text may also be used in the system by employing a computer with a character recognition program as an input. In such a case handwriting is converted into synthesized sound and inputted into the telephone microphone. The telephone system can be used by the hearing impaired without involving a third party human transcriber.

    摘要翻译： 公开了一种方法和装置，其允许人们在不可能或不礼貌地谈论的商业或其他设置中进行不引人注意的电话对话。 在图1的系统中 1，电话用户将以与普通电话相同的方式收听。 不过，他不会和电话麦克风说话。 用户1使用包括键盘的单元来输入与他想说的对应的文本。 使用TTS装置将文本转换成合成语音，并且将语音输出发送到电话装置的麦克风。 电话设备通过标准电话线将合成语音信号发送到包括常规电话扬声器26和电话麦克风的单元。 用户二，在另一端使用电话的一方侦听合成语音，但用户一听电话扬声器听用户二的实际语音，除非用户二也使用类似于用户二的系统。 通过采用具有字符识别程序的计算机作为输入，也可以在系统中使用手写文本。 在这种情况下，笔迹被转换成合成声音并被输入到电话麦克风。 电话系统可以由听力障碍者使用，而不涉及第三方人类录音机。

    Method and apparatus for improving acoustic fast match speed using a cache for phone probabilities
    17.
    发明授权
    Method and apparatus for improving acoustic fast match speed using a cache for phone probabilities 失效
    用于使用用于电话概率的缓存来改善声速快速匹配速度的方法和装置

    公开(公告)号：US5963905A

    公开(公告)日：1999-10-05

    申请号：US957200

    申请日：1997-10-24

    申请人： Miroslav Novak ,  Michael Alan Picheny

    发明人： Miroslav Novak ,  Michael Alan Picheny

    IPC分类号： G10L5/06

    CPC分类号： G10L15/14 ,  G10L2015/081

    摘要： Methods and apparatus for performing a tree search based acoustic fast match in a speech recognition system for decoding a speech utterance, the tree having a tree root and tree nodes connected by tree branches, the tree nodes having phonetic models associated therewith, are provided. An illustrative embodiment of the method comprises: providing a cache having cache cells for storing phone probabilities therein; selecting a first branch leading to a next node, said branch selection starting at the tree root; accessing the cache to select a particular cache cell where the probability of a particular match is stored; evaluating the phonetic model to obtain the probability and storing the probability and an associated end time in the cache cell, if the cache cell accessed in the accessing step does not contain the required probability; using the probability value and the associated end time stored in the cache cell, if the cache cell accessed in the accessing step contains the required probability; selecting a new branch to proceed to the next node; and iteratively continuing from the accessing step until the whole tree is traversed and all possible word candidates associated with the speech recognition system are evaluated.

    摘要翻译： 提供了在用于解码语音话语的语音识别系统中执行基于树搜索的声学快速匹配的方法和装置，所述树具有树根和由树枝连接的树节点，所述树节点具有与之相关联的语音模型。 该方法的说明性实施例包括：提供具有用于存储电话概率的高速缓存单元的高速缓存; 选择通向下一个节点的第一分支，所述分支选择从树根开始; 访问高速缓存以选择存储特定匹配的概率的特定高速缓存单元; 如果在访问步骤中访问的缓存单元不包含所需的概率，则评估语音模型以获得概率并将该概率和相关联的结束时间存储在高速缓存单元中; 如果在访问步骤中访问的高速缓存单元包含所需的概率，则使用存储在高速缓存单元中的概率值和相关联的结束时间; 选择一个新分支进行下一个节点; 并且从访问步骤迭代地继续，直到整个树被遍历，并且评估与语音识别系统相关联的所有可能的单词候选。