Abstract: The method of the present invention discloses: receiving a source text having a set of source text portions; generating a set of source text summarizations, each having a set of summarization portions, from the source text; calculating a portion score for each of the source text portions based on the source text portion's appearance in the summarizations; and populating a combined text summarization with those source text portions whose portion score exceeds a predetermined threshold. The system of the present invention discloses all means for implementing the method.

Abstract: The invention discloses a system and method for speech-activated navigating or browsing via a speech control interface used in a speech-activated multifunctional communications system. In one embodiment, the invention provides an approach to extend speech-activated navigation by linking an output of an open vocabulary recognizer to an Internet search engine in order that a user may have more options to search information related to his spoken commands. In another embodiment, the invention provides a means to enable the user to orally navigate a database via a speech control interface wherein the selections and associated selection criteria are organized into a hierarchical view menu. In another embodiment, the invention provides an approach with high flexibility and accuracy to recognize the user's command using a new grammar structure and a matching score system.

Abstract: Some embodiments of the present invention provide a speech translation system comprising a display upon which at least one word spoken by a user can be displayed. The speech translation system can include a holographic storage medium having a plurality of frames, each having data representative of at least one word in a source language. In some embodiments, the system includes one or more lasers positioned to direct a first beam of light to the display to generate a first modified beam of light leaving the display. This modified beam of light can be directed to the holographic storage medium to scan for a matching speech segment stored in the holographic storage medium. Upon detecting a match, some embodiments of the system can generate a translation of the speech segment by receiving a second modified beam of light from the holographic storage medium and carrying information representative of the translation.

Abstract: A method for determining intensity characteristics of background noise during speech pauses of speech signals includes determining a proportion of speech pauses in the undisturbed source speech signal so as to define a frequency threshold. The disturbed speech signal is divided into short successive signal elements, an intensity value is determined for each of the signal elements, and a cumulative relative frequency distribution is formed from the determined intensity values of the signal elements. The cumulative relative frequency distribution is used to determine an intensity threshold value which corresponds to the defined frequency threshold. At least one intensity characteristic of the background noise during the speech pauses is determined using a region of the cumulative relative frequency distribution below the intensity threshold value.

Abstract: A method of identifying potential novel word usage in a document comprises determining a part-of-speech assignment for each word in the document using a first part-of-speech tagger, determining a part-of-speech assignment for each word in the document using a second part-of-speech tagger different from the first part-of-speech tagger, and comparing the part-of-speech assignment of the first and second part-of-speech taggers. The method then generates a differential word set having words with different part-of-speech assignment by the first and second part-of-speech taggers. The words in the differential word set are candidates of words of novel usage.

Abstract: An improved method and apparatus is disclosed which uses probabilistic techniques to map an input search string with a prestored audio file, and recognize certain portions of a search string phonetically. An improved interface is disclosed which permits users to input search strings, linguistics, phonetics, or a combination of both, and also allows logic functions to be specified by indicating how far separated specific phonemes are in time.

Abstract: An apparatus and method for encoding and decoding a voice signal. The apparatus includes an encoder configured to generate an output bitstream signal from an input voice signal. The output bitstream signal is associated with at least a first standard of a first plurality of CELP voice compression standards. Additionally, the apparatus includes a decoder configured to generate an output voice signal from an input bitstream signal. The input bitstream signal is associated with at least a first standard of a second plurality of CELP voice compression standards. The CELP encoder includes a plurality of codec-specific encoder modules. Additionally, the CELP encoder includes a plurality of generic encoder modules. The CELP decoder includes a plurality of codec-specific decoder modules. Additionally, the CELP decoder includes a plurality of generic decoder modules.

Abstract: To provide a browser apparatus with the contents of data provided on a network in a form of voice data, voice data indicating a part or the whole of the contents of the data provided on the network is formed and stored on a gateway, on the basis of the data. Data is formed by adding to the data provided on the network an identifier <VOICEOUT . . . > indicating a location where the voice data is stored. This data is provided to the browser apparatus. The browser apparatus receives the voice data from the location indicated by the identifier.

Abstract: A conversation manager processes spoken utterances from a user of a computer. The conversation manager includes a semantics analysis module and a syntax manager. A domain model that is used in processing the spoken utterances includes an ontology (i.e., world view for the relevant domain of the spoken utterances), lexicon, and syntax definitions. The syntax manager combines the ontology, lexicon, and syntax definitions to generate a grammatic specification. The semantics module uses the grammatic specification and the domain model to develop a set of frames (i.e., internal representation of the spoken utterance). The semantics module then develops a set of propositions from the set of frames. The conversation manager then uses the set of propositions in further processing to provide a reply to the spoken utterance.

Abstract: A natural (e.g., handwriting or speech) input recognition system and method that uses contextual mapping to improve recognition accuracy by biasing recognition based on the context of an input field. As natural input data is being entered into an application field, the context (type) of the field is determined and used to locate context-based validation rules and context-based user bias data. When entry is complete, the context-based validation rules and context-based user bias data are provided to a recognition engine with the natural input data. The recognizer biases its recognition result by using the rules and the user bias data to recognize the natural input. A field signature generator is described that determines each field's context, independent of the application, and a data harvesting engine is described that automatically collects user bias data from various data stores.

Abstract: Voice of a user is inputted to a speech recognition section until a start of a no-voice domain from depression of a talk-switch. LPC cepstrum coefficients are calculated from the voice in an LPC analysis section and a cepstrum calculation section, and then temporarily stored in a parameter backward output section. A series of the LPC cepstrum coefficients is re-arranged to the series in which the time axis is inverted and then outputted to a collating section. The collating section calculates a degree of similarity between the LPC cepstrum coefficients and a recognition dictionary of a backward tree-structure stored in a standard pattern section through a backward collating.

Abstract: The invention concerns a method and apparatus for performing packet loss or Frame Erasure Concealment (FEC) for a speech coder that does not have a built-in or standard FEC process. A receiver with a decoder receives encoded frames of compressed speech information transmitted from an encoder. A lost frame detector at the receiver determines if an encoded frame has been lost or corrupted in transmission, or erased. If the encoded frame is not erased, the encoded frame is decoded by a decoder and a temporary memory is updated with the decoder's output. A predetermined delay period is applied and the audio frame is then output. If the lost frame detector determines that the encoded frame is erased, a FEC module applies a frame concealment process to the signal. The FEC processing produces natural sounding synthetic speech for the erased frames.

Abstract: An approach to alignment of transcripts with recorded audio is tolerant of moderate transcript inaccuracies, untranscribed speech, and significant non-speech noise. In one aspect, a number of search terms are formed from the transcript such that each search term is associated with a location within the transcript. Possible locations of the search terms are then determined in the audio recording. The audio recording and the transcript are then aligned using the possible locations of the search terms. In another aspect a search expression is accepted, and then a search is performed for spoken occurrences of the search expression in an audio recording. This search includes searching for text occurrences of the search expression in a text transcript of the audio recording, and searching for spoken occurrences of the search expression in the audio recording.

Abstract: Unique identifiers for each of a plurality of Chinese Pinyin syllables are generated and stored in an array of identifiers. A plurality of Hanzi character candidate lists is also generated, each list including Hanzi character candidates associated with a Pinyin syllable. Each identifier in the array has an array index, and each Hanzi character candidate in each list has a candidate index in the list. For each of a plurality of words having multiple Pinyin syllables, a data record including a key and a value is then generated. In a data record for a word, the key is an array index of the identifier in the array of identifiers and tone information for each of the multiple Pinyin syllables of the word, and the value is a candidate index, in the list of candidates associated with each of the Pinyin syllables, of the candidate that represents each of the Pinyin syllables.

Abstract: A computer extracts important terms, phrases or sentences from a document that it segments. The computer generates a square sum matrix from the document segments. The computer determines the importance of a given term, phrase or sentence on the basis of eigenvectors and eigenvalues of the matrix. The computer thereby selects the important terms, phrases or sentences related to the central concepts of the document.

Abstract: The invention discloses a system and method for speech-activated navigating or browsing via a speech control interface used in a speech-activated multifunctional communications system. In one embodiment, the invention provides an approach to extend speech-activated navigation by linking an output of an open vocabulary recognizer to an Internet search engine in order that a user may have more options to search information related to his spoken commands. In another embodiment, the invention provides a means to enable the user to orally navigate a database via a speech control interface wherein the selections and associated selection criteria are organized into a hierarchical view menu. In another embodiment, the invention provides an approach with high flexibility and accuracy to recognize the user's command using a new grammar structure and a matching score system.

Abstract: A source-controlled Variable bit-rate Multi-mode WideBand (VMR-WB) codec, having a mode of operation that is interoperable with the Adaptive Multi-Rate wideband (AMR-WB) codec, the codec comprising: at least one Interoperable full-rate (I-FR) mode, having a first bit allocation structure based on one of a AMR-WB codec coding types; and at least one comfort noise generator (CNG) coding type for encoding inactive speech frame having a second bit allocation structure based on AMR-WB SID_UPDATE coding type.

Abstract: A method and a system for extracting information from a natural language text corpus based on a natural language query are disclosed. In the method the natural language text corpus is analyzed with respect to surface structure of word tokens and surface syntactic roles of constituents, and the analyzed natural language text corpus is then indexed and stored. Furthermore a natural language query is analyzed with respect to surface structure of word tokens and surface syntactic roles of constituents. From the analyzed natural language query one or more surface variants are then created, where these surface variants are equivalent to the natural language query with respect to lexical meaning of word tokens and surface syntactic roles of constituents.

Abstract: Systems and methods by which voice/data communications may occur in multiple modes/protocols are disclosed. In particular, systems and methods are provided for multiple native mode/protocol voice and data transmissions and receptions with a computing system having a multi-bus structure, including, for example, a TDM bus and a packet bus, and multi-protocol framing engines. Such systems preferably include subsystem functions such as PBX, voice mail and other telephony functions, LAN hub and data router. In preferred embodiments, a TDM bus and a packet bus are intelligently bridged and managed, thereby enabling such multiple mode/protocol voice and data transmissions to be intelligently managed and controlled with a single, integrated system. A computer or other processor includes a local area network controller, which provides routing and hub(s) for one or more packet networks. The computer also is coupled to a buffer/framer, which serves to frame/deframe data to/from the computer from TDM bus.

Abstract: A graphical user interface may include a form with a plurality of fields, each field associated with a predetermined category. Each category may have its own, independent, discrete grammar associated therewith, and the independent grammars may be individually activated, simultaneously with their respective categories. In this way, a voice-recognition system that is inputting spoken data for each of the fields may have a restricted grammar to search when attempting to match a particular voice input with an entry for a particular field in the form. Moreover, a global grammar that is active with any one of the independent grammars may be used to move between the fields or perform other high-level functionality not associated with any one of the independent grammars.