Abstract: The method includes acquiring a target spoken text, where the target spoken text includes a non-spoken morpheme and a spoken morpheme; determining, from a target weighted finite-state transducer (WFST) model database, a target WFST model corresponding to the target spoken text, where output of a state that is corresponding to the spoken morpheme and that is in the target WFST model is empty, and output and input of a state that is corresponding to the non-spoken morpheme and that is in the target WFST model are the same; and determining, according to the target WFST model, a written text corresponding to the target spoken text, where the written text includes the non-spoken morpheme and does not include the spoken morpheme.

Abstract: The method includes acquiring a target spoken text, where the target spoken text includes a non-spoken morpheme and a spoken morpheme; determining, from a target weighted finite-state transducer (WFST) model database, a target WFST model corresponding to the target spoken text, where output of a state that is corresponding to the spoken morpheme and that is in the target WFST model is empty, and output and input of a state that is corresponding to the non-spoken morpheme and that is in the target WFST model are the same; and determining, according to the target WFST model, a written text corresponding to the target spoken text, where the written text includes the non-spoken morpheme and does not include the spoken morpheme.

Abstract: Speech is processed that may be colored by speech accent. A method for recognizing speech includes maintaining a model of speech accent that is established based on training speech data, wherein the training speech data includes at least a first set of training speech data, and wherein establishing the model of speech accent includes not using any phone or phone-class transcription of the first set of training speech data. Related systems are also presented. A system for recognizing speech includes an accent identification module that is configured to identify accent of the speech to be recognized; and a recognizer that is configured to use models to recognize the speech to be recognized, wherein the models include at least an acoustic model that has been adapted for the identified accent using training speech data of a language, other than primary language of the speech to be recognized, that is associated with the identified accent. Related methods are also presented.

Abstract: An utterance verification system and method includes: a new formulation of log-likelihood ratio (LLR) that discriminates between true and mis-recognition scores; a new dynamic threshold setting that permits each keyword to have its own individual threshold; and/or use of higher resolution subword units for HMM based (Hidden Markov Model-based) utterance verification. The system and method are especially suited for automated processing of speech of syllable-based languages, for example, Chinese (for example, Mandarin or Cantonese).

Abstract: A system and associated methods determine the semantic similarity of different sentences to one another. A particularly appropriate application of the present invention is to automatic processing of Chinese-language text, for example, for document retrieval. A method for computing the similarity between a first and a second set of words comprises identifying a word of the second set of words as being most similar to a word of the first set of words, wherein the word of the second set of words need not be identical to the word of the first set of words; and computing a score of the similarity between the first and second set of words based at least in part on the word of the second set of words.

Abstract: A system and associated methods identify documents relevant to an inputted natural-language user query. One associate method includes: selecting a set of keywords from the user query; determining at least one word, not necessarily found in the user query, that is semantically similar to a keyword of the set of keywords; using the set of keywords and the at least one word to determining a subset of word sets from a database of pre-stored word sets, wherein the pre-stored word sets are each pre-associated with at least one document; determining a plurality of word sets, from the subset of word sets, that is most semantically similar to the user query; and identifying documents that have been pre-associated with the plurality of word sets as being relevant to the natural-language user query.

Abstract: A system and method for processing human language input uses collocation information for the language that is not limited to N-gram information for N no greater than a predetermined value. The input is preferably speech input. The system and method preferably recognize at least a portion of the input based on the collocation information.

Abstract: A system and method is provided for responding to remotely-entered input from a plurality of technology platforms. An embodiment of the system includes a database that is configured to retrieve data in response to queries that are based on natural language; a first server that is configured to accept remotely-entered first natural-language input from a first technology platform and to determine a first query based on the first natural-language input and to obtain data from the database based on the first query; and a second server that is configured to accept remotely-entered second natural-language input from a second technology platform and to determine a second query based on the second natural-language input and to obtain data from the database based on the second query.