公开(公告)号：US07729916B2

公开(公告)日：2010-06-01

申请号：US11551901

申请日：2006-10-23

申请人： Daniel Coffman ,  Liam D. Comerford ,  Steven DeGennaro ,  Edward A. Epstein ,  Ponani Gopalakrishnan ,  Stephane H. Maes ,  David Nahamoo

发明人： Daniel Coffman ,  Liam D. Comerford ,  Steven DeGennaro ,  Edward A. Epstein ,  Ponani Gopalakrishnan ,  Stephane H. Maes ,  David Nahamoo

IPC分类号： G10L15/22 ,  G10L15/28

CPC分类号： H04M3/50 ,  G06F17/30899 ,  G10L15/22 ,  G10L15/285 ,  G10L2015/228 ,  H04L67/02 ,  H04M1/72561 ,  H04M3/42204 ,  H04M3/44 ,  H04M3/493 ,  H04M3/4931 ,  H04M3/4936 ,  H04M3/4938 ,  H04M7/00 ,  H04M2201/40 ,  H04M2201/60 ,  H04M2203/355 ,  H04M2250/74

摘要： A conversational computing system that provides a universal coordinated multi-modal conversational user interface (CUI) 10 across a plurality of conversationally aware applications (11) (i.e., applications that “speak” conversational protocols) and conventional applications (12). The conversationally aware applications (11) communicate with a conversational kernel (14) via conversational application APIs (13). The conversational kernel 14 controls the dialog across applications and devices (local and networked) on the basis of their registered conversational capabilities and requirements and provides a unified conversational user interface and conversational services and behaviors. The conversational computing system may be built on top of a conventional operating system and APIs (15) and conventional device hardware (16). The conversational kernel (14) handles all I/O processing and controls conversational engines (18). The conversational kernel (14) converts voice requests into queries and converts outputs and results into spoken messages using conversational engines (18) and conversational arguments (17). The conversational application API (13) conveys all the information for the conversational kernel (14) to transform queries into application calls and conversely convert output into speech, appropriately sorted before being provided to the user.

摘要翻译： 一种对话计算系统，其跨越多个会话感知应用（11）（即，“说”对话协议的应用）和常规应用（12）提供通用协调多模态对话用户界面（CUI）10。 对话感知应用（11）通过对话应用API（13）与对话内核（14）通信。 会话核心14基于其注册的对话能力和需求来控制应用和设备（本地和网络）之间的对话，并提供统一的对话用户界面和对话服务和行为。 对话计算系统可以构建在常规操作系统和API（15）和常规设备硬件（16）之上。 对话内核（14）处理所有I / O处理和控制对话引擎（18）。 会话内核（14）将语音请求转换为查询，并将会话引擎（18）和会话参数（17）将输出和结果转换为口语消息。 对话应用程序API（13）传达对话内核（14）的所有信息，以将查询转换成应用程序调用，并相反地将输出转换为语音，在提供给用户之前进行适当排序。

公开(公告)号：US5465317A

公开(公告)日：1995-11-07

申请号：US62972

申请日：1993-05-18

申请人： Edward A. Epstein

发明人： Edward A. Epstein

IPC分类号： G10L15/06 ,  G10L11/02 ,  G10L15/14 ,  G10L15/28 ,  G10L5/06

CPC分类号： G10L25/78

摘要： A speech recognizer that selects a command model for a current sound if the best match score for the current sound exceeds its corresponding threshold score. The threshold score is assigned a confidence score based on the best match score and recognition threshold of a prior sound. When the best match score for the current sound exceeds a "poor" confidence score but is less than a "good" confidence score: (a) the word corresponding to the acoustic model having the best match score is accepted as highly likely to correspond to the measured sound if the previously recognized word was accepted as having a high likelihood of corresponding to the previous sound; (b) the word corresponding to the acoustic model having the best match score is rejected as highly unlikely to correspond to the measured sound if the previously recognized word was rejected as having a low likelihood of corresponding to the previous sound; or (c) if there is sufficient intervening silence between a previously rejected word and the current word, then the current word is also accepted as having a high likelihood of corresponding to the measured current sound.

摘要翻译： 如果当前声音的最佳匹配分数超过其对应的阈值分数，则语音识别器选择当前声音的命令模型。 基于最佳匹配分数和先前声音的识别阈值为阈值分数分配置信度分数。 当当前声音的最佳匹配分数超过“不良”置信度分数，但小于“好”置信度分数时：（a）对应于具有最佳匹配分数的声学模型的单词被接受为极有可能对应于 如果先前识别的字被接受为具有对应于先前声音的高可能性的测量声音; （b）如果先前识别的字被拒绝为具有对应于先前声音的低可能性，则与具有最佳匹配得分的声学模型相对应的字被拒绝非常不可能对应于测量的声音; 或者（c）如果先前拒绝的字与当前字之间存在足够的静音，则当前字也被接受为对应于所测量的当前声音的高可能性。

公开(公告)号：US07137126B1

公开(公告)日：2006-11-14

申请号：US09806565

申请日：1999-10-01

申请人： Daniel Coffman ,  Liam D. Comerford ,  Steven DeGennaro ,  Edward A. Epstein ,  Ponani Gopalakrishnan ,  Stephane H. Maes ,  David Nahamoo

发明人： Daniel Coffman ,  Liam D. Comerford ,  Steven DeGennaro ,  Edward A. Epstein ,  Ponani Gopalakrishnan ,  Stephane H. Maes ,  David Nahamoo

IPC分类号： G06F9/54 ,  G06F9/50 ,  G06F9/44 ,  G10L15/00

CPC分类号： H04M3/50 ,  G06F17/30899 ,  G10L15/22 ,  G10L15/285 ,  G10L2015/228 ,  H04L67/02 ,  H04M1/72561 ,  H04M3/42204 ,  H04M3/44 ,  H04M3/493 ,  H04M3/4931 ,  H04M3/4936 ,  H04M3/4938 ,  H04M7/00 ,  H04M2201/40 ,  H04M2201/60 ,  H04M2203/355 ,  H04M2250/74

摘要： A conversational computing system that provides a universal coordinated multi-modal conversational user interface (CUI) (10) across a plurality of conversationally aware applications (11) (i.e., applications that “speak” conversational protocols) and conventional applications (12). The conversationally aware maps, applications (11) communicate with a conversational kernel (14) via conversational application APIs (13). The conversational kernel (14) controls the dialog across applications and devices (local and networked) on the basis of their registered conversational capabilities and requirements and provides a unified conversational user interface and conversational services and behaviors. The conversational computing system may be built on top of a conventional operating system and APIs (15) and conventional device hardware (16). The conversational kernel (14) handles all I/O processing and controls conversational engines (18). The conversational kernel (14) converts voice requests into queries and converts outputs and results into spoken messages using conversational engines (18) and conversational arguments (17). The conversational application API (13) conveys all the information for the conversational kernel (14) to transform queries into application calls and conversely convert output into speech, appropriately sorted before being provided to the user.

摘要翻译： 一种对话计算系统，其跨越多个会话感知应用（11）（即，“说”对话协议的应用“）和常规应用（12）提供通用协调多模态对话用户界面（CUI）（10）。 对话感知地图，应用程序（11）通过对话应用程序API（13）与对话内核（14）进行通信。 对话内核（14）根据其注册的会话能力和要求，控制应用和设备（本地和网络）之间的对话，并提供统一的会话用户界面和对话服务和行为。 对话计算系统可以构建在常规操作系统和API（15）和常规设备硬件（16）之上。 对话内核（14）处理所有I / O处理和控制对话引擎（18）。 会话内核（14）将语音请求转换为查询，并将会话引擎（18）和会话参数（17）将输出和结果转换为口语消息。 对话应用程序API（13）传达对话内核（14）的所有信息，以将查询转换成应用程序调用，并相反地将输出转换为语音，在提供给用户之前进行适当排序。

公开(公告)号：US20090313026A1

公开(公告)日：2009-12-17

申请号：US12544473

申请日：2009-08-20

申请人： Daniel Coffman ,  Liam D. Comeford ,  Steven DeGennaro ,  Edward A. Epstein ,  Ponani Gopalakrishnan ,  Stephane H. Maes ,  David Nahamoo

发明人： Daniel Coffman ,  Liam D. Comeford ,  Steven DeGennaro ,  Edward A. Epstein ,  Ponani Gopalakrishnan ,  Stephane H. Maes ,  David Nahamoo

IPC分类号： G10L15/22

CPC分类号： H04M3/50 ,  G06F17/30899 ,  G10L15/22 ,  G10L15/285 ,  G10L2015/228 ,  H04L67/02 ,  H04M1/72561 ,  H04M3/42204 ,  H04M3/44 ,  H04M3/493 ,  H04M3/4931 ,  H04M3/4936 ,  H04M3/4938 ,  H04M7/00 ,  H04M2201/40 ,  H04M2201/60 ,  H04M2203/355 ,  H04M2250/74

摘要： A conversational computing system that provides a universal coordinated multi-modal conversational user interface (CUI) 10 across a plurality of conversationally aware applications (11) (i.e., applications that “speak” conversational protocols) and conventional applications (12). The conversationally aware applications (11) communicate with a conversational kernel (14) via conversational application APIs (13). The conversational kernel 14 controls the dialog across applications and devices (local and networked) on the basis of their registered conversational capabilities and requirements and provides a unified conversational user interface and conversational services and behaviors. The conversational computing system may be built on top of a conventional operating system and APIs (15) and conventional device hardware (16). The conversational kernel (14) handles all I/O processing and controls conversational engines (18). The conversational kernel (14) converts voice requests into queries and converts outputs and results into spoken messages using conversational engines (18) and conversational arguments (17). The conversational application API (13) conveys all the information for the conversational kernel (14) to transform queries into application calls and conversely convert output into speech, appropriately sorted before being provided to the user.

摘要翻译： 一种对话计算系统，其跨越多个会话感知应用（11）（即，“说”对话协议的应用）和常规应用（12）提供通用协调多模态对话用户界面（CUI）10。 对话感知应用（11）通过对话应用API（13）与对话内核（14）通信。 会话核心14基于其注册的会话能力和需求来控制应用和设备（本地和网络）之间的对话，并提供统一的对话用户界面和对话服务和行为。 对话计算系统可以构建在常规操作系统和API（15）和常规设备硬件（16）之上。 对话内核（14）处理所有I / O处理和控制对话引擎（18）。 会话内核（14）将语音请求转换为查询，并将会话引擎（18）和会话参数（17）将输出和结果转换为口语消息。 对话应用程序API（13）传达对话内核（14）的所有信息，以将查询转换成应用程序调用，并相反地将输出转换为语音，在提供给用户之前进行适当排序。

公开(公告)号：US4447883A

公开(公告)日：1984-05-08

申请号：US266879

申请日：1981-05-26

申请人： Gregory A. Farrell ,  Edward A. Epstein

发明人： Gregory A. Farrell ,  Edward A. Epstein

IPC分类号： G01N15/14 ,  G01N15/12 ,  G01N33/49 ,  G01N27/00

CPC分类号： G01N15/1227

摘要： New and improved method and apparatus for the correction of coincident errors attendant the automated detection and counting of mixed particles having detectable characteristics of different levels in particle counting applications wherein the detection of "dominant" particles under coincident particle conditions, renders undetectable the "dominated" particles, with resulting inaccuracy in the "dominated" particle count. Such inaccuracy is corrected by modifying the "dominated" particle count in accordance with the time duration of the signals which are generated attendant the detection of the "dominated" particles.

摘要翻译： 用于校正重合误差的新的和改进的方法和装置伴随着在颗粒计数应用中具有不同水平的可检测特性的混合颗粒的自动检测和计数，其中在重合颗粒条件下检测“显性”颗粒，使得“主导” 颗粒，导致“主导”粒子数量的不准确。 通过根据与“主导”的粒子的检测有关的信号的持续时间修改“主导”的粒子数来校正这种不准确性。

公开(公告)号：US08082153B2

公开(公告)日：2011-12-20

申请号：US12544473

申请日：2009-08-20

申请人： Daniel Coffman ,  Liam D. Comerford ,  Steven DeGennaro ,  Edward A. Epstein ,  Ponani Gopalakrishnan ,  Stephane H. Maes ,  David Nahamoo

发明人： Daniel Coffman ,  Liam D. Comerford ,  Steven DeGennaro ,  Edward A. Epstein ,  Ponani Gopalakrishnan ,  Stephane H. Maes ,  David Nahamoo

IPC分类号： G10L15/28 ,  G06F3/16

CPC分类号： H04M3/50 ,  G06F17/30899 ,  G10L15/22 ,  G10L15/285 ,  G10L2015/228 ,  H04L67/02 ,  H04M1/72561 ,  H04M3/42204 ,  H04M3/44 ,  H04M3/493 ,  H04M3/4931 ,  H04M3/4936 ,  H04M3/4938 ,  H04M7/00 ,  H04M2201/40 ,  H04M2201/60 ,  H04M2203/355 ,  H04M2250/74

摘要： A method for conversational computing includes executing code embodying a conversational virtual machine, registering a plurality of input/output resources with a conversational kernel, providing an interface between a plurality of active applications and the conversational kernel processing input/output data, receiving input queries and input events of a multi-modal dialog across a plurality of user interface modalities of the plurality of active applications, generating output messages and output events of the multi-modal dialog in connection with the plurality of active applications, managing, by the conversational kernel, a context stack associated with the plurality of active applications and the multi-modal dialog to transform the input queries into application calls for the plurality of active applications and convert the output messages into speech, wherein the context stack accumulates a context of each of the plurality of active applications.

摘要翻译： 一种用于对话计算的方法包括执行体现对话虚拟机的代码，用对话内核注册多个输入/输出资源，提供多个活动应用与对话内核处理输入/输出数据之间的接口，接收输入查询和 通过多个活动应用程序的多个用户界面模式输入多模态对话的事件，生成与多个活动应用相关联的多模式对话的输出消息和输出事件，由对话内核管理， 与所述多个活动应用相关联的上下文栈以及将所述输入查询转换为所述多个活动应用的应用调用并将所述输出消息转换为语音的所述多模态对话，其中，所述上下文堆栈累积所述多个活动应用中的每一个的上下文 的活跃应用。

公开(公告)号：US07043432B2

公开(公告)日：2006-05-09

申请号：US09941301

申请日：2001-08-29

申请人： Raimo Bakis ,  Hari Chittaluru ,  Edward A. Epstein ,  Steven J. Friedland ,  Abraham Ittycheriah ,  Stephen G. Lawrence ,  Michael A. Picheny ,  Charles Rutherfoord ,  Maria E. Smith

发明人： Raimo Bakis ,  Hari Chittaluru ,  Edward A. Epstein ,  Steven J. Friedland ,  Abraham Ittycheriah ,  Stephen G. Lawrence ,  Michael A. Picheny ,  Charles Rutherfoord ,  Maria E. Smith

IPC分类号： G10L13/08 ,  G10L13/00

CPC分类号： G10L13/047

摘要： In a text-to-speech system, a method of converting text-to-speech can include receiving a text input and comparing the received text input to at least one entry in a text-to-speech cache memory. Each entry in the text-to-speech cache memory can specify a corresponding spoken output. If the text input matches one of the entries in the text-to-speech cache memory, the cached speech output specified by the matching entry can be provided.

公开(公告)号：US5280562A

公开(公告)日：1994-01-18

申请号：US770495

申请日：1991-10-03

申请人： Lalit R. Bahl ,  Jerome R. Bellegarda ,  Edward A. Epstein ,  John M. Lucassen ,  David Nahamoo ,  Michael A. Picheny

发明人： Lalit R. Bahl ,  Jerome R. Bellegarda ,  Edward A. Epstein ,  John M. Lucassen ,  David Nahamoo ,  Michael A. Picheny

IPC分类号： G10L19/00 ,  G10L15/02 ,  G10L19/02 ,  H03M7/30 ,  G10L9/02

CPC分类号： G10L19/038 ,  H03M7/3082

摘要： In speech recognition and speech coding, the values of at least two features of an utterance are measured during a series of time intervals to produce a series of feature vector signals. A plurality of single-dimension prototype vector signals having only one parameter value are stored. At least two single-dimension prototype vector signals having parameter values representing first feature values, and at least two other single-dimension prototype vector signals have parameter values representing second feature values. A plurality of compound-dimension prototype vector signals have unique identification values and comprise one first-dimension and one second-dimension prototype vector signal. At least two compound-dimension prototype vector signals comprise the same first-dimension prototype vector signal. The feature values of each feature vector signal are compared to the parameter values of the compound-dimension prototype vector signals to obtain prototype match scores. The identification values of the compound-dimension prototype vector signals having the best prototype match scores for the feature vectors signals are output as a sequence of coded representations of an utterance to be recognized. A match score, comprising an estimate of the closeness of a match between a speech unit and the sequence of coded representations of the utterance, is generated for each of a plurality of speech units. At least one speech subunit, of one or more best candidate speech units having the best match scores, is displayed.

摘要翻译： 在语音识别和语音编码中，在一系列时间间隔期间测量话音的至少两个特征的值，以产生一系列特征向量信号。 存储仅具有一个参数值的多个单维原型矢量信号。 具有表示第一特征值的参数值和至少两个其它单维原型矢量信号的至少两个单维原型矢量信号具有表示第二特征值的参数值。 多个复合尺寸原型矢量信号具有唯一的识别值，并且包括一个第一维和一个第二维原型矢量信号。 至少两个复合维度原型矢量信号包括相同的第一维原型矢量信号。 将每个特征向量信号的特征值与化合物维度原型矢量信号的参数值进行比较，以获得原型匹配分数。 具有特征矢量信号的具有最佳原型匹配分数的复合维度原型矢量信号的识别值被输出为将被识别的话语的编码表示的序列。 针对多个语音单元中的每一个生成包括语音单元与语音编码表示序列之间的匹配的接近度的估计的匹配分数。 显示具有最佳匹配分数的一个或多个最佳候选语音单元的至少一个语音子单元。