公开(公告)号：US06466907B1

公开(公告)日：2002-10-15

申请号：US09195583

申请日：1998-11-18

Applicant: Alexandre Ferrieux ,  Stephane Peillon

Inventor： Alexandre Ferrieux ,  Stephane Peillon

IPC: G10L1508

CPC classification number: G10L15/26 ,  G10L2015/228

Abstract: A process provides for searching through a written text in response to a spoken question comprising a plurality of words. The first step in the process is to transcribe the written text into a first sequence of phonetic units. Then, a spoken question is segmented into a second sequence of phonetic units. The search is conducted through the written text for an occurrence of the spoken question. The search comprises aligning the first and second sequences of phonetic units.

Abstract translation: 一个过程用于响应于包含多个单词的口语问题来搜索书面文本。 该过程的第一步是将书面文本转录成第一个语音单元。 然后，一个口语问题被分割成第二个语音单元序列。 通过书面文本进行搜索，发现口语问题。 搜索包括对准第一和第二语音单元序列。

公开(公告)号：US20050119876A1

公开(公告)日：2005-06-02

申请号：US10509082

申请日：2003-03-20

Applicant: Alexandre Ferrieux ,  Lionel Delphin-Poulat

Inventor： Alexandre Ferrieux ,  Lionel Delphin-Poulat

IPC: G10L15/02 ,  G10L15/14 ,  G10L15/183 ,  G10L15/28 ,  G06F17/21

CPC classification number: G10L15/183 ,  G10L15/142 ,  G10L15/285 ,  G10L2015/025

Abstract: Input data are translated into a lexical output sequence. Sub-lexical entities and various possible combinations of the entities are identified as states ei and ej of first and second language models, respectively, intended to be stored, with an associated likelihood value and a table having memory areas. Each memory area is intended to contact at least one combination of the states and has an address equal to a value h [(ei:ej)] of a scalar function h applied to parameters peculiar to the combination (ei:ej). There is reduced complexity of accesses to information produced by a single transducer formed by a single Viterbi machine using the models.

Abstract translation: 输入数据被转换成词汇输出序列。 子词汇实体和实体的各种可能的组合被分别被识别为旨在存储的第一和第二语言模型的状态ei和ej，具有相关联的似然值和具有存储区域的表。 每个存储器区域旨在接触状态的至少一个组合，并具有等于组合（ei：ej）特有参数的标量函数h的值h [（ei：ej）]的地址。 由使用这些模型的单个维特比机组形成的单个换能器产生的信息的访问复杂度降低。

公开(公告)号：US08301442B2

公开(公告)日：2012-10-30

申请号：US11918180

申请日：2006-04-06

Applicant: Jean Monne ,  Alexandre Ferrieux

Inventor： Jean Monne ,  Alexandre Ferrieux

IPC: G10L15/00

CPC classification number: G10L25/78 ,  G10L15/26

Abstract: A method of synchronizing an operation for processing, by an automatic speech recognition system of a device, a voice sequence uttered by a speaker and an action of the speaker intended to trigger the processing by the device. The processing operation is effected by the device from a given time preceding the action of the speaker. A time interval between the given time and the action of the speaker corresponds to a given interval.

Abstract translation: 一种用于通过设备的自动语音识别系统来处理由扬声器发出的语音序列和用于触发设备的处理的演讲者的动作的操作的方法。 处理操作由设备从扬声器的动作之前的给定时间进行。 给定时间与扬声器的动作之间的时间间隔对应于给定的间隔。

公开(公告)号：US20090228269A1

公开(公告)日：2009-09-10

申请号：US11918180

申请日：2006-04-06

Applicant: Jean Monne ,  Alexandre Ferrieux

Inventor： Jean Monne ,  Alexandre Ferrieux

IPC: G10L15/00

CPC classification number: G10L25/78 ,  G10L15/26

Abstract: Method of synchronization between an operation for processing, by automatic speech recognition, a voice sequence (Sv) uttered by a speaker and an action of said speaker intended to trigger said processing. According to the invention, said processing operation is effected from a given time (t0) preceding said action of the speaker. Application to automatic speech recognition.

Abstract translation: 用于处理的操作，通过自动语音识别，由扬声器发出的语音序列（Sv）和旨在触发所述处理的所述说话者的动作之间的同步的方法。 根据本发明，所述处理操作是从说话者的所述动作之前的给定时间（t0）进行的。 应用于自动语音识别。

公开(公告)号：US20090106026A1

公开(公告)日：2009-04-23

申请号：US11921288

申请日：2006-05-24

Applicant: Alexandre Ferrieux

Inventor： Alexandre Ferrieux

IPC: G10L15/18 ,  G10L15/00

CPC classification number: G10L15/19 ,  G10L15/08

Abstract: A speech recognition method including for a spoken expression: a) providing a vocabulary of words including predetermined subsets of words, b) assigning to each word of at least one subset an individual score as a function of the value of a criterion of the acoustic resemblance of that word to a portion of the spoken expression, c) for a plurality of subsets, assigning to each subset of the plurality of subsets a composite score corresponding to a sum of the individual scores of the words of said subset, d) determining at least one preferred subset having the highest composite score.

Abstract translation: 包括用于口头表达的语音识别方法：a）提供包括预定词组的单词的词汇表，b）将至少一个子集的每个单词分配为单个分数作为声学相似性标准的值的函数 将所述词的一部分写入所述语言表达的一部分，c）对于多个子集，向所述多个子集的每个子集分配与所述子集的单词的各个分数之和相对应的综合分数，d） 具有最高综合得分的最少一个优选子集。

公开(公告)号：US20080120104A1

公开(公告)日：2008-05-22

申请号：US11883970

申请日：2005-12-28

Applicant: Alexandre Ferrieux

Inventor： Alexandre Ferrieux

IPC: G10L15/00 ,  G10L17/00

CPC classification number: G10L15/30

Abstract: A method of transmitting end-of-speech marks in a distributed speech recognition system operating in a discontinuous transmission mode, in which system speech segments (30, 40) are transmitted, followed by periods (34) of silence, each speech segment (30, 40) terminating with an end-of-speech mark (31, 41). The end-of-speech mark (31) is retransmitted continually (31a, 31b, 31c, 31d) throughout the duration of the period of silence (34) following said speech segment (30).

Abstract translation: 一种在以不连续传输模式工作的分布式语音识别系统中发送终端语音标记的方法，其中发送系统语音段（30,40），随后是静音周期（34），每个语音段（30 ，40）终止于语音结束标记（31,41）。 语音结束标记（31）在所述语音片段（30）之后的整个静音期间（34）的持续期间内连续重传（31a，31b，31c，31d）。

公开(公告)号：US20050154581A1

公开(公告)日：2005-07-14

申请号：US10509651

申请日：2003-03-19

Applicant: Alexandre Ferrieux ,  Lione Delphin-Poulat

Inventor： Alexandre Ferrieux ,  Lione Delphin-Poulat

IPC: G10L15/02 ,  G10L15/14 ,  G10L15/183 ,  G10L11/00

CPC classification number: G10L15/183 ,  G10L15/142 ,  G10L2015/025

Abstract: Input data are translated into at least one output sentence by a decoding step which sub-lexical entities represented by the input data are identified by a first model. During decoding, as the sub-lexical entities are identified and with reference to at least one second mode, various possible combinations of the sub-lexical entities are generated. Plural possible combinations of the sub-lexical entities are stored. The most likely possible combination is intended to form the lexical output sequence.

Abstract translation: 通过解码步骤将输入数据转换成至少一个输出句子，由输入数据表示的子词实体由第一模型识别。 在解码期间，当识别子词汇实体并且参考至少一个第二模式时，生成子词汇实体的各种可能的组合。 存储子词汇实体的多种可能的组合。 最可能的组合是用于形成词汇输出序列。