Abstract: Method and system are provided for performing random confirmation in a speech system. When a speech recognition result is received with an associated confidence score indicating a level of confidence with respect to the speech recognition result, a confirmation decision is made in terms of whether a confirmation is to be carried out based on the confidence score. The confirmation decision may be made in a random confirmation mode. A confirmation may be performed when the confirmation decision is to carry out a confirmation on the speech recognition result.

Abstract: Building a language model for use in speech recognition includes identifying without user interaction a source of text related to a user. Text is retrieved from the identified source of text and a language model related to the user is built from the retrieved text.

Abstract: Recognizing punctuation in computer-implemented speech recognition includes performing speech recognition on an utterance to produce a recognition result for the utterance. A non-verbalized punctuation mark is identified in a recognition result and the recognition result is formatted based on the identification.

Abstract: An improved echo control system has an adaptive controlled echo canceling filter arrangement in which a background filter updates the filter coefficients of an echo shaping filter responsive to a normalized least mean square (NLMS) algorithm. An adaptive control module determines a weighted reference signal for the background filter in which the weight is proportional to a far signal reference and an estimate of the norm of an echo canceller error vector, and inversely proportional to en estimate of a residue of the echo canceller. And a non-linear normalized convergence term is used in the NLMS algorithm.

Abstract: Correcting incorrect text associated with recognition errors in computer-implemented speech recognition includes receiving a selection of a word from a recognized utterance. The selection indicates a bound of a portion of the recognized utterance to be corrected. A first recognition correction is produced based on a comparison between a first alternative transcript and the recognized utterance. A second recognition correction is produced based on a comparison between a second alternative transcript and the recognized utterance. The duration of the first recognition correction differs from the duration of the second recognition correction. A portion of the recognition result that is replaced with one of the first recognition correction and the second recognition correction. includes at one bound a word indicated by the selection and extends for the duration of the one of the first recognition correction and the second recognition correction with which the portion is replaced.

Abstract: A speech recognition system includes a user interface configured to provide signals indicative of a user's speech. A speech recognizer of the system includes a processor configured to use the signals from the user interface to perform speech recognition operations to attempt to recognize speech indicated by the signals. A control mechanism is coupled to the voice recognizer and is configured to affect processor usage for speech recognition operations in accordance with a loading of the processor.

Abstract: A computer is used to perform recorded actions. The computer receives recorded spoken utterances of actions. The computer then performs speech recognition on the recorded spoken utterances to generate texts of the actions. The computer then parses the texts to determine properties of the actions. After parsing the texts, permits the user to indicate that the user has reviewed one or more actions. The computer then automatically carries out the actions indicated as having been reviewed by the user.

Abstract: A computer-based electronic document and/or paper-based document management application program. The program provides an efficient way to automatically import, index, categorize, store, search, retrieve, manipulate and archive electronic documents. The program is also capable of managing documents regardless of document type or document format.

Abstract: A computer-based electronic document and/or paper-based document management application program. The program provides an efficient way to automatically import, index, categorize, store, search, retrieve, manipulate and archive electronic documents. The program is also capable of managing documents regardless of document type or document format.

Abstract: The present invention is a system and method for performing document recognition and processing in a distributed computing environment. The invention uses applications which are remotely located from one or more users and may be accessed via a network. One or more users utilize terminals including computers, facsimile machines, and/or scanners to transmit documents to be processed to a network or a network server which in turn transmits the documents to various computer software applications which process the documents at a network processing location. Once the documents have been processed, the processed documents are transmitted to the users according to one or more preferences associated with a user identification and/or authentication which may be determined by either a network server or an application server.

Abstract: The excitation in a CELP-like speech coder is recursively calculated. For a given bitrate and a given complexity, the recursive approach described lowers the complexity with minimum impact on speech quality. The excitation signal is a sum of at least three vector terms, each vector term being a product of a codebook vector zk and an associated gain term gk. A first vector term g0z0 is determined that is representative of a target excitation vector x. Each remaining vector term is recursively determined as a vector term gkzk representative of the difference between the target excitation vector x and the sum of previously determined vector terms, ∑ i = 0 k - 1 ⁢ g i ⁢ z i .

Abstract: A high quality speech synthesizer in various embodiments concatenates speech waveforms referenced by a large speech database. Speech quality is further improved by speech unit selection and concatenation smoothing.

Abstract: A system is presented for automatically responding to a user inquiry comprising a dialog manager and a presentation manager. The dialog manager executes a machine-controlled human/machine dialog to determine a set of query items, and in response thereto, retrieves information items from memory. The presentation manager determines the inquiring user's intentions motivating and associated with the query, and in response thereto selects a preferred manner of presenting the retrieved information items, or presentation scenario. In so doing, at least one natural language phrase is generated to match the selected presentation scenario, and a speech generator verbally presents the generated phrasing to the inquiring user.

Abstract: A method of analyzing a collection of calls at one or more call center stations. The method includes receiving lexical content of a telephone call handled by a call center agent and identifying one or more features of the telephone call based on the received lexical content. The method also includes collectively analyzing the stored features along with the stored features of other telephone calls and reporting results of the analyzing.

Abstract: A speech recognition system recognizes an input utterance of spoken words. The system includes a set of word models for modeling vocabulary to be recognized, each word model being associated with a word in the vocabulary, each word in the vocabulary considered as a sequence of phones including a first phone and a last phone, wherein each word model begins in the middle of the first phone of its associated word and ends in the middle of the last phone of its associated word; a set of word connecting models for modeling acoustic transitions between the middle of a word's last phone and the middle of an immediately succeeding word's first phone; and a recognition engine for processing the input utterance in relation to the set of word models and the set of word connecting models to cause recognition of the input utterance.

Abstract: An action position is manipulated in computer-implemented speech recognition by receiving data representing a spoken command. The command includes a command identifier (e.g., insert before, insert after, resume with) and a designation of at least one previously-spoken word. Speech recognition is performed on the data to identify the command identifier and the designation. Finally, an action position is established relative to the previously-spoken word based on the command identifier. Text may be selected using a spoken selection command that includes a command identifier and a text block identifier identifying a block of previously-recognized text. At least one word included in the block of text is not included in the text block identifier.

Abstract: A method for generating a semi-literal transcript from a partial transcript of recorded speech. The method includes augmenting the partial transcript with words from one of a filled pause model and a background model to build an augmented probabilistic finite state model for the partial transcript, inputting the recorded speech and the augmented probabilistic finite state model to a speech recognition system, and generating a hypothesized output for the recorded speech using the speech recognition system, whereby the hypothesized output may be used as the semi-literal transcript.

Abstract: In a graphical user interface for accessing a large number of files, such as text files, graphics files, or spreadsheets, a system allows quick glances of “thumbnails” or highly reduced versions of the files. When a folder is opened, every file in the folder is opened as a background operation and thumbnail data, such as a reduced image or text summary of the file, is derived and retained in a cache folder for quick access. When a cursor is touched, without a mouse-click, to a particular icon in the opened folder, the thumbnail for the file identified by the icon is accessed from the cache folder and displayed.

Abstract: A method of a continuous speech recognition system is given for discriminatively training hidden Markov for a system recognition vocabulary. An input word phrase is converted into a sequence of representative frames. A correct state sequence alignment with the sequence of representative frames is determined, the correct state sequence alignment corresponding to models of words in the input word phrase. A plurality of incorrect recognition hypotheses is determined representing words in the recognition vocabulary that do not correspond to the input word phrase, each hypothesis being a state sequence based on the word models in the acoustic model database. A correct segment of the correct word model state sequence alignment is selected for discriminative training. A frame segment of frames in the sequence of representative frames is determined that corresponds to the correct segment.

Abstract: A method is given for automatically rewriting orthography of a stream of text words, for example, automatically and properly capitalizing words in the stream. If a word in the stream has an entry in an orthography rewrite lexicon, the word is automatically replaced with an orthographically rewritten form of the word from the orthography rewrite lexicon. In addition, selected words in the stream are compared to a plurality of features weighted by a maximum entropy-based algorithm, to automatically determine whether to rewrite orthography of any of the selected words.