Abstract: The present disclosure provides a speech editor for creating a session file having text segments synchronized with an audio file. The editor receives a text segment and a first file that has tag information lines associated with the text segment. Each tag information line has a portion of original text transcribed from the audio file and a corresponding audio length value. The editor stores the audio length of a current line in a new tag information line for the second file, determines whether the original text portion of the current line is found in the text segment, and if the original text portion of the current line is not found in the text segment, identifies a corrected text of the text segment adjusting the audio length of the new tag information line of the session file to correspond to the corrected text.

Abstract: In a natural language, mixed-initiative system, a method of processing user dialogue can include receiving a user input and determining whether the user input specifies an action to be performed or a token of an action. The user input can be selectively routed to an action interpreter or a token interpreter according to the determining step.

Abstract: A communication supporting apparatus includes a supplemental example storing unit that stores a source language interpretation which is an interpretation of a semantic content of a source language sentence to be translated, and a supplemental example sentence which is an example of a sentence for supporting the semantic content, in association with each other; an input accepting unit that accepts the source language sentence input by a user; an analyzing unit that analyzes the semantic content of the source language sentence and outputs the source language interpretation; a search unit that searches for the supplemental example sentence associated with the source language interpretation from the supplemental example storing unit; and a translation unit that translates the source language sentence and the supplemental example sentence into a target language.

Abstract: A program reservation/playback judgment system for making an automatic judgment of reservation or playback of a program based on the program information in texts written in a natural language. A natural language program information processing section analyzes texts read-out thereby for extracting the program information in the texts. The extracted program information is displayed as a program information screen for confirming the program information. Upon user's operation of a reservation/playback button, the program of the program information is confirmed. Based on a comparison result of the current date and time with the date and start time of the program information by a current date/time acquisition section, a date/time judgment section makes a judgment whether the program of the program information is reserved for recording or played back, thereby instructing a program monitoring device to reserve or playback.

Abstract: Provided are a method and apparatus for automatically completing a text input using speech recognition. The method includes: receiving a first part of a text from a user through a text input device; recognizing a speech of the user, which corresponds to the text; and completing a remaining part of the text based on the first part of the text and the recognized speech. Therefore, accuracy of the text input and convenience of the speech recognition can be ensured, and a non-input part of the text can be easily input based on the input part of the text and the recognized speech at a high speed.

Abstract: When registering speech onto an object, an information processing apparatus selects identification information from an identification information database and stores information including the object, speech for registration, and the selected identification information in a registration database. When a user performs a speech call, the information processing apparatus outputs identification information that is included in the information called by the user.

Abstract: The present invention allows subscribers to an online information service to participate in real-time conferencing or chat sessions in which a message originating from a subscriber in accordance with a first language is translated to one or more languages before it is broadcast to the other conference areas. Messages in a first language are translated automatically to one or more other languages through language translation capabilities resident at online information service host computers. Access software that subscribers use for participating in conference is integrated with speech recognition and speech generation software such that a subscriber may speak the message he or she would like to share with other participants and may hear the messages from the other participants in the conference. Speech-to-speech translation may be accomplished as a message spoken into a computer microphone in accordance with a first language may be recited by a remote computer in accordance with a second language.

Abstract: A system for recognizing patterns is disclosed. Grammar learning from a corpus includes, for the other non-context words, generating frequency vectors for each non-context token in a corpus based upon counted occurrences of a predetermined relationship of the non-context tokens to identified context tokens. Clusters are grown from the frequency vectors according to a lexical correlation or a cluster tree among the non-context tokens. The cluster tree is used for pattern recognition.

Abstract: In an embodiment, a sentence is created that describes a walk of a graph. The graph includes a set of nodes and a set of edges that are incident to the nodes. The sentence includes label words that describe the nodes and relationship words that describe the edges. The walk is an alternating sequence of a subset of the nodes and of the edges. Each of the edges in the walk is incident to two of the nodes that precede and follow the respective edge. The sentence is created by determining a parent node associated with a selected label word, determining the child nodes of the parent node, determining the edges that are incident to the parent nodes and the child nodes, determining relationship words that describe the edges that are incident to the parent nodes and the child nodes, and determining child label words that describe the child nodes. A selected relationship word and a selected child label word are then added to the sentence. In this way, a walk of the graph may be more easily understood.

Abstract: An expressive speech-to-speech generation system which can generate expressive speech output by using expressive parameters extracted from the original speech signal to drive the standard TTS system. The system comprises: speech recognition means, machine translation means, text-to-speech generation means, expressive parameter detection means for extracting expressive parameters from the speech of language A, and expressive parameter mapping means for mapping the expressive parameters extracted by the expressive parameter detection means from language A to language B, and driving the text-to-speech generation means by the mapping results to synthesize expressive speech.

Abstract: Answering System enables a user to input a query and responds with answers. Server stores an indexed database of a plurality of S-A-O's (subject-action-object). User generates the query that includes query elements (A-O), (S-A), or (S-X-O), or element (S). The server identifies the database element S, O, or A, or elements (A-O) associated with a respective knowledge base S-A-O that includes the query element(s) in response to the server receiving the query and generates a natural language answer S-A-O that includes the identified and the query elements(s) and transmits the answer to the user apparatus that provides an audio or visual response. The server can conduct WWW searches for documents with S-A-O elements that match query element(s) and adds them to the database, thus treating the WWW as an available knowledge base.

Abstract: A system for creating a structured report using a template having at least one predetermined heading and formatting data associated with each heading. The steps include recording a voice file, creating a speech recognized text file corresponding to the voice file, identifying the location of each heading in the text file, and the text corresponding thereto, populating the template with the identified text corresponding to each heading, and formatting the populated template to create the structured report.

Abstract: Word recommendations are provided in response to text input. For a particular text input, possible word recommendations are identified based on the characters of the input and corresponding neighbor characters on a keyboard layout. The possible word recommendations are scored based on how closely they match the input word on a character-by-character basis, and a subset of the possible word recommendations are selected for presentation to the user.

Abstract: A semantic analysis apparatus includes a data obtaining unit that obtains data in which an item name and an item value belonging to the item name are represented in a predetermined data format; an item value extracting unit that extracts the item value from the data based on the data format; a concept storing unit that stores a concept which is a semantic notion to be attached to the item name and an instance which is specific data of the concept in association with each other; a concept specifying unit that specifies the concept, which is stored in the concept storing unit and which is associated with the instance which at least partially matches with a character string of the extracted item value, as the concept for the item name; and an associating unit that associates the concept with the item name.

Abstract: A system and method for speech-to-speech translation using a translation system includes designating separate input channels for each of a plurality of speakers. In response to speech from a first channel in a first language, the speech from the first channel is translated to a second language, and in response to speech from the second channel in a second language, the speech from the second channel is translated to the first language. Translating the speech from the first channel and translating the speech from the second channel are performed concurrently.

Abstract: A method, system and module for automatically converting a call flow into a state-based representation are disclosed. The method comprises walking a call flow and converting each page of the call flow into a rule of a higher level representation of the call flow, augmenting the higher level representation with terminal symbols representing state variable assignments and comparisons associated with decision and computation shapes in the call flow and converting the higher level representation into a state-based representation.

Abstract: A public speaking self-evaluation tool that helps a user practice public speaking in terms of avoiding undesirable words or sounds, maintaining a desirable speech rhythm, and ensuring that the user is regularly glancing at the audience. The system provides a user interface through which the user is able to define the undesirable words or sounds that are to be avoided, as well as a maximum frequency of occurrence threshold to be used for providing warning signals based on detection of such filler or undesirable words or sounds. The user interface allows a user to define a speech rhythm, e.g. in terms of spoken syllables per minute, that is another maximum threshold for providing a visual warning indication. The disclosed system also provides a visual indication when the user fails to glance at the audience at least as often as defined by a predefined minimum threshold.

Abstract: A translation support device for supporting a process of translating an original sentence in a language into another language, comprising a partial expression setting unit, a dummy head setting unit, an original sentence replacement unit, a translated sentence obtaining unit, and a translated sentence replacement unit.

Abstract: A technique for performing frame erasure concealment (FEC) in a speech decoder. One or more non-erased frames of a speech signal are decoded in a block-independent manner. When an erased frame is detected, a short-term predictive filter and a long-term predictive filter are derived based on previously-decoded portions of the speech signal. A periodic waveform component is generated using the short-term predictive filter and the long-term predictive filter. A random waveform component is generated using the short-term predictive filter. A replacement frame is generated for the erased frame. The replacement frame may be generated based on the periodic waveform component, the random waveform component, or a mixture of both.

Abstract: A method of machine translation, using a bilingual corpus containing translation pairs each consisting of a sentence of a first language and a sentence of a second language, for translating an input sentence of the first language to the second language, including the steps of: receiving the input sentence of the first language and extracting, from the bilingual corpus, a sentence of the second language forming a pair with a sentence of the first language with highest similarity to the input sentence; applying an arbitrary modification among a plurality of predetermined modifications to the extracted sentence of the second language, and computing likelihood of sentences resulting from the modification; selecting a prescribed number of sentences having high likelihood from among the sentences resulting from the modification; repeating, on each of the sentences selected in the step of selecting, the steps of extracting, computing and selecting, until the likelihood no longer improves; and outputting, as a transl