1686 results about "Language model" patented technology

A speech understanding system includes a language model comprising a combination of an N-gram language model and a context-free grammar language model. The language model stores information related to words and semantic information to be recognized. A module is adapted to receive input from a user and capture the input for processing. The module is further adapted to receive SALT application program interfaces pertaining to recognition of the input. The module is configured to process the SALT application program interfaces and the input to ascertain semantic information pertaining to a first portion of the input and output a semantic object comprising text and semantic information for the first portion by accessing the language model, wherein performing recognition and outputting the semantic object are performed while capturing continues for subsequent portions of the input.

A domain-based speech recognition method and apparatus, the method including: performing speech recognition by using a first language model and generating a first recognition result including a plurality of first recognition sentences; selecting a plurality of candidate domains, by using a word included in each of the first recognition sentences and having a confidence score equal to or higher than a predetermined threshold, as a domain keyword; performing speech recognition with the first recognition result, by using an acoustic model specific to each of the candidate domains and a second language model and generating a plurality of second recognition sentences; and selecting at least one or more final recognition sentence from the first recognition sentences and the second recognition sentences. According to this method and apparatus, the effect of a domain extraction error by misrecognition of a word on selection of a final recognition result can be minimized.

Certain disclosed methods and systems perform multiple different types of message recognition using a shared language model. Message recognition of a first type is performed responsive to a first type of message input (e.g., speech), to provide text data in accordance with both the shared language model and a first model specific to the first type of message recognition (e.g., an acoustic model). Message recognition of a second type is performed responsive to a second type of message input (e.g., handwriting), to provide text data in accordance with both the shared language model and a second model specific to the second type of message recognition (e.g., a model that determines basic units of handwriting conveyed by freehand input). Accuracy of both such message recognizers can be improved by user correction of misrecognition by either one of them. Numerous other methods and systems are also disclosed.

A system is disclosed for selectively applying a paraphrase alternation pattern to a textual input. The system includes a pattern identification component for processing a collection of data and identifying a plurality of potentially applicable paraphrase alternation patterns. A context model provides an objective frame of reference in which to compare one or more of the plurality of potentially applicable paraphrase alternation patterns to the textual input to determine whether the pattern can be applied without changing meaning. A language model provides a principled basis for determining the boundaries of the text segment to be modified.

Systems and methods to process and translate pinyin to Chinese characters and words are disclosed. A Chinese language model is trained by extracting unknown character strings from Chinese inputs, e.g., documents and/or user inputs/queries, determining valid words from the unknown character strings, and generating a transition matrix based on the Chinese inputs for predicting a word string given the context. A method for translating a pinyin input generally includes generating a set of Chinese character strings from the pinyin input using a Chinese dictionary including words derived from the Chinese inputs and a language model trained based on the Chinese inputs, each character string having a weight indicating the likelihood that the character string corresponds to the pinyin input. An ambiguous user input may be classified as non-pinyin or pinyin by identifying an ambiguous pinyin/non-pinyin ASCII word in the user input and analyzing the context to classify the user input.

A spelling system derives a language model for a particular domain of structured data, the language model enabling determinations of alternative spellings of queries or other strings of text from that domain. More specifically, the spelling system calculates (a) probabilities that the various query entity types—such as STREET, CITY, or STATE for queries in the geographical domain—are arranged in each of the various possible orders, and (b) probabilities that an arbitrary query references given particular ones of the entities, such as the street “El Camino Real.” Based on the calculated probabilities, the spelling system generates a language model that has associated scores (e.g., probabilities) for each of a set of probable entity name orderings, where the total number of entity name orderings is substantially less than the number of all possible orderings. The language model can be applied to determine probabilities of arbitrary queries, and thus to suggest alternative queries more likely to represent what a user intended.

Disclosed is a method and apparatus for building a domain-specific language model for use in language processing applications, e.g., speech recognition. A reference language model is generated based on a relatively small seed corpus containing linguistic units relevant to the domain. An external corpus containing a large number of linguistic units is accessed. Using the reference language model, linguistic units which have a sufficient degree of relevance to the domain are extracted from the external corpus. The reference language model is then updated based on the seed corpus and the extracted linguistic units. The process may be repeated iteratively until the language model is of satisfactory quality. The language building technique may be further enhanced by combining it with mixture modeling or class-based modeling.

A dialog device comprises a natural language interfacing device (chat interface or a telephonic device), and a natural language output device (the chat interface, a display device, or a speech synthesizer outputting to the telephonic device). A computer stores natural language dialog conducted via the interfacing device and constructs a current utterance word-by-word. Each word is chosen by applying a plurality of language models to a context comprising concatenation of the stored dialog and the current utterance thus far. Each language model outputs a distribution over the words of a vocabulary. A recurrent neural network (RNN) is applied to the distributions to generate a mixture distribution. The next word is chosen using the mixture distribution. The output device outputs the current natural language utterance after it has been constructed by the computer.

A speech recognition device includes one intention extracting language model and more in which an intention of a focused specific task is inherent, an absorbing language model in which any intention of the task is not inherent, a language score calculating section that calculates a language score indicating a linguistic similarity between each of the intention extracting language model and the absorbing language model, and the content of an utterance, and a decoder that estimates an intention in the content of an utterance based on a language score of each of the language models calculated by the language score calculating section.

Systems, methods, and apparatus for accessing distributed models in automated machine processing, including using large language models in machine translation, speech recognition and other applications.

A frequency counting unit (15A) counts occurrence frequencies (14B) in input text data (14A) for respective words or word chains contained in the input text data (14A). A context diversity calculation unit (15B) calculates, for the respective words or word chains, diversity indices (14C) each indicating the context diversity of a word or word chain. A frequency correction unit (15C) corrects the occurrence frequencies (14B) of the respective words or word chains based on the diversity indices (14C) of the respective words or word chains. An N-gram language model creation unit (15D) creates an N-gram language model (14E) based on the corrected occurrence frequencies (14D) obtained for the respective words or word chains.

A composite language model may include a composite word predictor. The composite word predictor may include a first language model and a second language model that are combined according to a directed Markov random field. The composite word predictor can predict a next word based upon a first set of contexts and a second set of contexts. The first language model may include a first word predictor that is dependent upon the first set of contexts. The second language model may include a second word predictor that is dependent upon the second set of contexts. Composite model parameters can be determined by multiple iterations of a convergent N-best list approximate Expectation-Maximization algorithm and a follow-up Expectation-Maximization algorithm applied in sequence, wherein the convergent N-best list approximate Expectation-Maximization algorithm and the follow-up Expectation-Maximization algorithm extracts the first set of contexts and the second set of contexts from a training corpus.

Speaker recognition is attempted on input speech signals concurrently with provision of input speech signals to a speech recognition system. If a speaker is recognized, a speaker dependent model which has been trained on an enrolled speaker is supplied to the speech recognition system. If not recognized, then a speaker-independent recognition model is used or, alternatively, the new speaker is enrolled. Other speaker specific information such as a special language model, grammar, vocabulary, a dictionary, a list of names, a language and speaker dependent preferences can also be provided to improve the speech recognition function or even configure or customize the speech recognition system or the response of any system such as a computer or network controlled in response thereto. A consistency check in the form of a decision tree is preferably provided to accelerate the speaker recognition process and increase the accuracy thereof. Further training of a model and/or enrollment of additional speakers may be initiated upon completion of speaker recognition and/or adaptively upon each speaker utterance.

A system and method are provided for recognizing a user's speech input. The method includes the steps for detecting the user's speech input, recognizing the user's speech input by comparing the speech input to a list of entries using language model statistics to determine the most likely entry matching the user's speech input, and detecting navigation information of a trip to a predetermined destination, where the most likely entry is determined by modifying the language model statistics taking into account the navigation information. A system and method is further provided that takes into account navigation trip information to determine the most likely entry using language model statistics for recognizing text input.

Techniques are disclosed for automatically generating structured documents based on speech, including identification of relevant concepts and their interpretation. In one embodiment, a structured document generator uses an integrated process to generate a structured textual document (such as a structured textual medical report) based on a spoken audio stream. The spoken audio stream may be recognized using a language model which includes a plurality of sub-models arranged in a hierarchical structure. Each of the sub-models may correspond to a concept that is expected to appear in the spoken audio stream. Different portions of the spoken audio stream may be recognized using different sub-models. The resulting structured textual document may have a hierarchical structure that corresponds to the hierarchical structure of the language sub-models that were used to generate the structured textual document.

A method for creating a language model from a task-independent corpus is provided. In one embodiment, a task dependent unified language model is created. The unified language model includes a plurality of context-free grammars having non-terminals and a hybrid N-gram model having at least some of the same non-terminals embedded therein.