Abstract: This invention maps possibly noisy digital input from any of a number of different hardware or software sources such as keyboards, automatic speech recognition systems, cell phones, smart phones or the web onto an interpretation consisting of an action and one or more physical objects, such as robots, machinery, vehicles, etc. or digital objects such as data files, tables and databases. Tables and lists of (i) homonyms and misrecognitions, (ii) thematic relation patterns, and (iii) lexicons are used to generate alternative forms of the input which are scored to determine the best interpretation of the noisy input. The actions may be executed internally or output to any device which contains a digital component such as, but not limited to, a computer, a robot, a cell phone, a smart phone or the web. This invention may be implemented on sequential and parallel compute engines and systems.

Abstract: Described within are systems and methods for transliterating and translating source non-Romanized language text strings from a plurality of electronic sources to Romanized target language text strings by converting the source non-Romanized language text strings to a standard document encoding format, splitting the source non-Romanized language text strings into smaller units, transforming the smaller units into entity profiles, processing the entities profiles with data from external databases, translating the entities in the entity profiles into a Romanized target language, and outputting the entities into a plurality of data formats for external systems.

Abstract: A system and method for a highly interactive style of speech-to-speech translation is provided. The interactive procedures enable a user to recognize, and if necessary correct, errors in both speech recognition and translation, thus providing robust translation output than would otherwise be possible. The interactive techniques for monitoring and correcting word ambiguity errors during automatic translation, search, or other natural language processing tasks depend upon the correlation of Meaning Cues and their alignment with, or mapping into, the word senses of third party lexical resources, such as those of a machine translation or search lexicon. This correlation and mapping can be carried out through the creation and use of a database of Meaning Cues, i.e., SELECT. Embodiments described above permit the intelligent building and application of this database, which can be viewed as an interlingua, or language-neutral set of meaning symbols, applicable for many purposes.

Abstract: Systems, methods and computer program products are provided for translating a natural language into music. Through systematic parsing, music compositions can be created. These compositions can be created by one or more persons who do not speak the same natural language.

Abstract: An improved mobile electronic device and associated method enable the identification of previously-entered textual objects in one or more custom wordlists to identify possible transliterations of textual inputs. Such textual objects can be stored as data in a Pinyin custom wordlist if it is in the nature of Standard Mandarin characters or it can be stored in a BoPoMoFo custom wordlist if it is in the nature of Traditional Chinese characters, or it can be stored in both if it is in the nature of both Standard Mandarin characters and Traditional Chinese characters.

Abstract: Techniques for providing a translation environment interface to a user are disclosed herein. The techniques include receiving a message template to be translated, the message template including a text portion and one or more template placeholders, parsing the message template to identify the text portion and the template placeholders, generating non-editable objects corresponding to the template placeholders and generating a display message template by replacing each of the one or more template placeholders with its corresponding non-editable object in the message template, the display message template including the text portion to be translated. The techniques further include providing the display message template to a user device and receiving a translated display message template from the user device, the translated message including a translated text portion and the one or more non-editable objects.

Abstract: An example method may include receiving a media stream from a first endpoint, where the media stream is intended for a second endpoint; processing the media stream according to at least one processing option; compressing the media stream; and communicating the media stream to the second endpoint. In more specific instances, the processing may include converting a speech in the media stream to text in a first language; converting the text in the first language to text in a second language; rendering the text in the second language; and adding the rendered text in the media stream.

Abstract: Methods, systems, and products are disclosed for dynamic prosody adjustment for voice-rendering synthesized data that include retrieving synthesized data to be voice-rendered; identifying, for the synthesized data to be voice-rendered, a particular prosody setting; determining, in dependence upon the synthesized data to be voice-rendered and the context information for the context in which the synthesized data is to be voice-rendered, a section of the synthesized data to be rendered; and rendering the section of the synthesized data in dependence upon the identified particular prosody setting.

Abstract: Systems and methods to facilitate programmatic access to a network-based commerce facility via a network are described. In some embodiments, a method includes receiving a request from a third party application via the network at the network based commerce facility. The request performs an action pertaining to electronic commerce and being one of a plurality of requests recognized by the network-based commerce facility. In responsive to the request, the method performs the action pertaining to the electronic commerce and communicates from a result of the action from the network-based commerce facility to the third party application in a programmatically accessible format.

Abstract: A method and system for processing input media for provision to a text to speech engine comprising: a rules engine configured to maintain and update rules for processing the input media; a pre-parsing filter module configured to determine one or more metadata attributes using pre-parsing rules; a parsing filter module configured to identify content component from the input media using the parsing rules; a context and language detector configured to determine a default context and a default language; a learning agent configured to divide the content component into units of interest; a tagging module configured to iteratively assign tags to the units of interest using the tagging rules, wherein each tag is associated with a post-parsing rule; a post-parsing filter module configured to modify the content component by executing the post-parsing rules identified by the tags assigned to the phrases and strings.

Abstract: In a translation display apparatus, when an instruction to enlarge and display a part of an image of a translated sentence-added document displayed on a display unit is inputted from a display instruction input section, a partially-enlarged image creating section creates a partially-enlarged image in which a part of the image of a translated sentence-added document is enlarged. Under the control of a control section, an image creating section creates a partial enlargement-added image which is an image obtained by superimposing the partially-enlarged image created by the partially-enlarged image creating section on the image of the translated sentence-added document. Under the control of the control section, the display unit displays the partial enlargement-added image.

Abstract: Methods, systems, and apparatus, including computer program products, for ranking the output suggestions of a transliteration process. In one aspect, a method includes receiving a plurality of transliteration training pairs comprising a source word in a first writing system and a target word in a second writing system. A plurality of 1-to-N transliteration rules is received. Blocks are generated for each source word character comprising the source word character and a string characters preceding and following the source word character. Generated blocks are associated with the right-hand-side of respective 1-to-N transliteration rules to create a plurality of block rules. Block rules are used to generate a possibly-partial transliteration of a source word. A score is assigned based on an edit distance between the source word and each of one or more respective transliteration output suggestions.

Abstract: Systems and methods to facilitate programmatic access to a network-based commerce facility via a network are described. In some embodiments, a method includes receiving a request from a third party application via the network at the network based commerce facility. The request performs an action pertaining to electronic commerce and being one of a plurality of requests recognized by the network-based commerce facility. In responsive to the request, the method performs the action pertaining to the electronic commerce and communicates from a result of the action from the network-based commerce facility to the third party application in a programmatically accessible format.

Abstract: A method of automatically converting alphabetic text written in a text based language into a non-text based language. The method can include parsing the text to identify at least one word. The method also can include via a processor, identifying within a lexicon database data corresponding to the word, wherein the data corresponding to the word identifies at least one pictograph or symbol selected from a group of pictographs or symbols consisting of between twenty seven and thirty three distinct pictographs or symbols that visually look different than the text, wherein each pictograph or symbol corresponds to a unique speech sound of the text based language. The pictograph or symbol can be rendered in a view.

Abstract: Embodiments for the adaptive learning of translation layout patterns to mine bilingual data are disclosed. In accordance with at least one embodiment, the adaptive learning of patterns to mine bilingual data includes processing a bilingual web page into a plurality bilingual snippet pairs. The embodiment also includes determining one or more best fit candidate patterns based on the plurality of translation snippets. The embodiment additionally includes mining one or more translation pairs from the bilingual web page using the one or more best fit candidate patterns. The translation pairs are further stored in a data storage. The one or more translation pairs including at least one of a term pair, a phrase pair, or a sentence pair.

Abstract: A method and system for configuring a universal remote control (URC) to control a remote-controlled device includes establishing a communication link between the URC and the remote-controlled device in response to detecting a gesture motion of the URC. Device information may be received from the remote-controlled device and used by the URC to program the URC to control the remote-controlled device. The URC may be configured to control a plurality of remote-controlled devices. The communication link may be a near field wireless communication link.

Abstract: The disclosure includes a system and method for generating audio snippets from a subset of audio tracks. In some embodiments an audio snippet is an audio summary of a group or collection of songs.

Abstract: A method for editing timed and annotated data includes acquiring a multimedia data stream; performing a decoding operation upon the multimedia data stream, wherein the decoded data stream comprises a textual data stream; synchronizing the multimedia data stream and the decoded data stream by performing a time stamping operation upon the data streams; editing the decoded data stream; and realigning the time stamp data of the edited decoded data stream in order to synchronize the edited decoded data with the multimedia data stream.

Abstract: Methods and systems for multi level quality checking of transcripts are disclosed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving (i) audio data that encodes a spoken natural language query, and (ii) environmental audio data, obtaining a transcription of the spoken natural language query, determining a particular content type associated with one or more keywords in the transcription, providing at least a portion of the environmental audio data to a content recognition engine, and identifying a content item that has been output by the content recognition engine, and that matches the particular content type.

Abstract: A system and method for transliteration between two different character-based languages is provided. In some embodiments, the system and method provide transliteration from the Arabic language into Roman-based languages such as English. In some embodiments this system and method allows a user to more easily produce Arabic text on English or Roman-based computer hardware and software.

Abstract: A personalized text-to-speech synthesizing device includes: a personalized speech feature library creator, configured to recognize personalized speech features of a specific speaker by comparing a random speech fragment of the specific speaker with preset keywords, thereby to create a personalized speech feature library associated with the specific speaker, and store the personalized speech feature library in association with the specific speaker; and a text-to-speech synthesizer, configured to perform a speech synthesis of a text message from the specific speaker, based on the personalized speech feature library associated with the specific speaker and created by the personalized speech feature library creator, thereby to generate and output a speech fragment having pronunciation characteristics of the specific speaker.

Abstract: A method, system and a computer program product for an automated interpretation and/or translation are disclosed. An automated interpretation and/or translation occurs by receiving language-based content from a user. The received language-based content is processed to interpret and/or translate the received language-based content into a target language. Also, a presence of a cultural sensitivity in the received language-based content is detected. Further, an appropriate guidance for dealing with the detected cultural sensitivity is provided.

Abstract: The present invention is a system and method for generating a personal voice font including, monitoring voice segments automatically from phone conversations of a user by a voice learning processor to generate a personalized voice font and delivering the personalized voice font (PVF) to the a server.

Abstract: An unsupervised boosting strategy is applied to refining automatic word alignment. In some examples, the strategy improves the quality of automatic word alignment, for example for resource poor language pairs, thus improving Statistical Machine Translation (SMT) performance.

Abstract: A method of automatic speech recognition includes receiving an utterance from a user via a microphone that converts the utterance into a speech signal, pre-processing the speech signal using a processor to extract acoustic data from the received speech signal, and identifying at least one user-specific characteristic in response to the extracted acoustic data. The method also includes determining a user-specific confidence threshold responsive to the at least one user-specific characteristic, and using the user-specific confidence threshold to recognize the utterance received from the user and/or to assess confusability of the utterance with stored vocabulary.

Abstract: A method and system for generating snippet for review on the Internet. The method includes the steps of: receiving a review and a set of feedbacks corresponding to the review, where the review includes a plurality of evaluating sentences that evaluates product features of a product; calculating support degrees of each of the plurality of evaluating sentences by using the set of feedbacks; extracting, by relying on calculated support degrees of each of the evaluating sentences, at least one of the evaluating sentences from the plurality of evaluating sentences; and designating extracted evaluating sentence as a snippet of the review; where at least one of the steps is carried out by using a computer device.

Abstract: A method and system for generating snippet for review on the Internet. The method includes the steps of: receiving a review and a set of feedbacks corresponding to the review, where the review includes a plurality of evaluating sentences that evaluates product features of a product; calculating support degrees of each of the plurality of evaluating sentences by using the set of feedbacks; extracting, by relying on calculated support degrees of each of the evaluating sentences, at least one of the evaluating sentences from the plurality of evaluating sentences; and designating extracted evaluating sentence as a snippet of the review; where at least one of the steps is carried out by using a computer device.

Abstract: A network clearinghouse may be provided that brings together organizations (subjects) requiring outsourcing of a service and service providers (operators). The clearinghouse manages the bidding and awarding of contracts, by collecting and authorizing requests for proposals (RFPs), sending bid invitations to operators that meet the requirements of the subject, sending a notification that the contract has been awarded, and collecting payment from the subject and paying the operator.

Abstract: A system and method for generating word alignments from pairs of aligned text strings are provided. A corpus of text strings provides pairs of text strings, primarily sentences, in source and target languages. A first alignment between a text string pair creates links therebetween. Each link links a single token of the first text string to a single token of the second text string. A second alignment also creates links between the text string pair. In some cases, these links may correspond to bi-phrases. A modified first alignment is generated by selectively modifying links in the first alignment which include a word which is infrequent in the corpus, based on links generated in the second alignment. This results in removing at least some of the links for the infrequent words, allowing more compact and better quality bi-phrases, with higher vocabulary coverage, to be extracted for use in a machine translation system.

Abstract: Example embodiments of the present invention may include a method that provides transcribing spoken utterances occurring during a call and automatically assigning each of the spoken utterances with a corresponding set of first classifications. The method may also include determining a confidence rating associated with each of the spoken utterances and the assigned set of first classifications, and performing at least one of reclassifying the spoken utterances with new classifications based on at least one additional classification operation, and adding the assigned first classifications and the corresponding plurality of spoken utterances to a training data set.

Abstract: Echo cancellation is handled using a pattern classification technique. During a training phase, the communications device is trained to learn patterns of signal inputs that correspond to certain communication modes. After numerous different patterns have been classified by mode, the classified patterns are used during real-time use of the communications device in order to determine, dynamically, the mode in which the communications device is currently operating. The communications device may then apply, to the microphone-produced signal, a suppression action.

Abstract: A system and method for segmenting a multi-language text is provided. An exemplary method comprises determining an initial probability distribution for sentences in the multi-language text, the initial probability distribution indicating the likelihood of each sentence being in each of a set of languages. A probability of language transitions across sentences may be learned based on the initial probability distribution. Additionally, a highest probability language sequence of sentences in the multi-language text may be determined based on a combination of the probability of language transitions and the prior probability distribution provided by an initial model.

Abstract: A spoken dialog system and method having a dialog management module are disclosed. The dialog management module includes a plurality of dialog motivators for handling various operations during a spoken dialog. The dialog motivators comprise an error handling, disambiguation, assumption, confirmation, missing information, and continuation. The spoken dialog system uses the assumption dialog motivator in either a-priori or a-posteriori modes. A-priori assumption is based on predefined requirements for the call flow and a-posteriori assumption can work with the confirmation dialog motivator to assume the content of received user input and confirm received user input.

Abstract: A computer-implemented voice mail method includes obtaining an electronic audio file of a recorded user message directed to a telephone user, automatically generating a transcript of the recorded user message, and identifying locations in the transcript in coordination with timestamps in the recorded user message so that successive portions of the transcript can be highlighted in coordination with playing of the recorded user message. The method also include identifying one or characteristics of the message using meta data relating to the recorded user message, and storing the recorded user message and information about the identified locations of the recorded user message.

Abstract: A method, a system and a machine-readable medium are provided for an on demand translation service. A translation module including at least one language pair module for translating a source language to a target language may be made available for use by a subscriber. The subscriber may be charged a fee for use of the requested on demand translation service or may be provided use of the on demand translation service for free in exchange for displaying commercial messages to the subscriber. A video signal may be received including information in the source language, which may be obtained as text from the video signal and may be translated from the source language to the target language by use of the translation module. Translated information, based on the translated text, may be added into the received video signal. The video signal including the translated information in the target language may be sent to a display device.

Abstract: According to an embodiment, a translation unit translates a first sentence in a first language into a sentence in a second language using parallel translations. A next utterance table includes first identification information distinguishing between a sentence in the first language and a sentence in the second language included in the parallel translation and includes second identification information identifying a sentence previously selected as the next utterance of the sentence indicated by the first identification information. An acquiring unit acquires next utterance candidates, which are sentences indicated by the second identification information associated with the first identification information of the first sentence. If the selected next utterance candidate is the first language, the translation unit translates the selected next utterance candidate into the second language.

Abstract: The performance of traditional speech recognition systems (as applied to information extraction or translation) decreases significantly with, larger domain size, scarce training data as well as under noisy environmental conditions. This invention mitigates these problems through the introduction of a novel predictive feature extraction method which combines linguistic and statistical information for representation of information embedded in a noisy source language. The predictive features are combined with text classifiers to map the noisy text to one of the semantically or functionally similar groups. The features used by the classifier can be syntactic, semantic, and statistical.

Abstract: A method of using conversation state information in a conversational interaction system is disclosed. A method of inferring a change of a conversation session during continuous user interaction with an interactive content providing system includes receiving input from the user including linguistic elements intended by the user to identify an item, associating a linguistic element of the input with a first conversation session, and providing a response based on the input. The method also includes receiving additional input from the user and inferring whether or not the additional input from the user is related to the linguistic element associated with the conversation session. If related, the method provides a response based on the additional input and the linguistic element associated with the first conversation session. Otherwise, the method provides a response based on the second input without regard for the linguistic element associated with the first conversation session.

Abstract: Methods, systems, and apparatus, including computer program products, for user interaction with machine translation. A user interface for receiving requests to translate text and/or documents from a first language text to a second language text. The translated text and/or document is displayed such that the first language text corresponding to a selected portion of the second language text can be accessed and displayed in the same user interface.

Abstract: Disclosed herein are systems, methods, and computer readable-media for enriching spoken language translation with prosodic information in a statistical speech translation framework. The method includes receiving speech for translation to a target language, generating pitch accent labels representing segments of the received speech which are prosodically prominent, and injecting pitch accent labels with word tokens within the translation engine to create enriched target language output text. A further step may be added of synthesizing speech in the target language based on the prosody enriched target language output text. An automatic prosody labeler can generate pitch accent labels. An automatic prosody labeler can exploit lexical, syntactic, and prosodic information of the speech. A maximum entropy model may be used to determine which segments of the speech are prosodically prominent.

Abstract: A system, apparatus, and method is disclosed for receiving user input at a client device, interpreting the user input to identify a selection of at least one of a plurality of web interaction modes, producing a corresponding client request based in part on the user input and the web interaction mode; and sending the client request to a server via a network.

Abstract: A method of generating a statistical machine translation database through a game in which a monolingual structure is provided to a plurality of players. A first translation attempt is received from each of the plurality of players. The first translation attempt from each of the plurality of players is compared. Feedback is provided to each of the plurality of players and the attempts are received and compared to provide feedback to iteratively converge subsequent translations from each of the plurality of players into a final translated structure.

Abstract: Techniques for employing improved prompts in a speech-to-speech translation system are disclosed. By way of example, a technique for use in indicating a dialogue turn in an automated speech-to-speech translation system comprises the following steps/operations. One or more text-based scripts are obtained. The one or more text-based scripts are synthesizable into one or more voice prompts. At least one of the one or more voice prompts is synthesized for playback from at least one of the one or more text-based scripts, the at least one synthesized voice prompt comprising an audible message in a language understandable to a speaker interacting with the speech-to-speech translation system, the audible message indicating a dialogue turn in the automated speech-to-speech translation system.

Abstract: An automated speech processing method, system and computer program product are disclosed. In one embodiment, a speech-to-text (STT) engine is used for converting an audio input to text data in a source language, and a machine translation (MT) engine is used for translating this text data to text data in a target language. In this embodiment, the text data in the target language is rendered on a display device, and different visualization schemes are applied to different parts of the rendered text data based on defined characteristics of the STT engine and the MT engine. In one embodiment, the defined characteristics include a defined confidence value representing the accuracy of the rendered text. For example, this confidence value may be based on both the accuracy of the conversion of the audio input and the accuracy of the translation of the text data to the target language.

Abstract: Incoming e-mails, instant messages, SMS, and MMS, are scanned for new language objects such as words, abbreviations, text shortcuts and, in appropriate languages, ideograms, that are placed in a list for use by a text input process of a handheld electronic device to facilitate the generation of text. Systems and methods consistent with the present invention may gather new language objects from sources of text external to the handheld electronic device, and may ignore new language objects that are not considered to be in a current language of the handheld electronic device.

Abstract: A phonetic language translation system receives audio output from an audible program presented to the user, so as to identify any speech signal contained within the audio output. The speech signals are broken down into recognizable phonemes which make up the most basic elements of speech in spoken languages. The sequentially generated phonemes are then regrouped to form recognizable words in one of native languages spoken around the world. While watching the audible program, the activity of language area of user's brain is recorded using electrodes in the cap. The recorded language area brain signals are analyzed and compared with brain language area activity knowledge base to identify the native language of user. Sentences are formed using the grammatical rules of the native language. Each sentence is then translated into the identified native language and broadcast to the user using a voice synthesizer.

Abstract: In one embodiment, the invention provides a method for translating a document in an input language into an output language comprising: a) for each document fragment for which a translation is readily available, translating said document fragment based on said readily available translation; and b) for each remaining untranslated fragment for which a translation is not readily available, translating said untranslated fragment based on a model-based machine translation technique. A translation is readily available if a search reveals at least one matching translation for the document fragment in a translation database.

Abstract: A system and method are disclosed for providing semi-supervised learning for a spoken language understanding module using semantic role labeling. The method embodiment relates to a method of generating a spoken language understanding module. Steps in the method comprise selecting at least one predicate/argument pair as an intent from a set of the most frequent predicate/argument pairs for a domain, labeling training data using mapping rules associated with the selected at least one predicate/argument pair, training a call-type classification model using the labeled training data, re-labeling the training data using the call-type classification model and iteratively several of the above steps until training set labels converge.

Abstract: A natural language-independent computer program is constructed. A data element is defined by a graphical representation in a user interface. A data element has a data type and a value. An operator is defined on multiple data elements by association of the graphical representations in the user interface. A natural language-independent graph data structure is defined by the association of data elements representing the logic of a computer program. The data types and operators have referenced descriptions in one or more natural languages, enabling a logical expression such as a computer program to be defined and understood in one or more natural languages.