247 results about "Paiute language" patented technology

Algorithms for synthesizing speech used to identify media assets are provided. Speech may be selectively synthesized from text strings associated with media assets, where each text string can be associated with a native string language (e.g., the language of the string). When several text strings are associated with at least two distinct languages, a series of rules can be applied to the strings to identify a single voice language to use for synthesizing the speech content from the text strings. In some embodiments, a prioritization scheme can be applied to the text strings to identify the more important text strings. The rules can include, for example, selecting a voice language based on the prioritization scheme, a default language associated with an electronic device, the ability of a voice language to speak text in a different language, or any other suitable rule.

Speech recognition may be improved by generating and using a topic specific language model. A topic specific language model may be created by performing an initial pass on an audio signal using a generic or basis language model. A speech recognition device may then determine topics relating to the audio signal based on the words identified in the initial pass and retrieve a corpus of text relating to those topics. Using the retrieved corpus of text, the speech recognition device may create a topic specific language model. In one example, the speech recognition device may adapt or otherwise modify the generic language model based on the retrieved corpus of text.

Techniques that enable a user to select, from among multiple languages, a language to be used for performing text-to-speech conversion. In some embodiments, upon determining that multiple languages may be used to perform text-to-speech conversion for a portion of text, the multiple languages may be displayed to the user. The user may then select a particular language to be used from the multiple languages. The portion of text may then be converted to speech in the user-selected language.

Disclosed are systems, methods, circuits and associated computer executable code for deep learning based natural language understanding, wherein training of one or more neural networks, includes: producing character strings inputs ‘noise’ on a per-character basis, and introducing the produced ‘noise’ into machine training character strings inputs fed to a ‘word tokenization and spelling correction language-model’, to generate spell corrected word sets outputs; feeding machine training word sets inputs, including one or more ‘right’ examples of correctly semantically-tagged word sets, to a ‘word semantics derivation model’, to generate semantically tagged sentences outputs. Upon models reaching a training ‘steady state’, the ‘word tokenization and spelling correction language-model’ is fed with input character strings representing ‘real’ linguistic user inputs, generating word sets outputs that are fed as inputs to the word semantics derivation model for generating semantically tagged sentences outputs.

By inputting words of source language as a keyword (31), a translation pairs are extracted (50) from a parallel corpus database including source language and target one. From the partially corresponding information on the translation sentence, a corresponding phrase group table formed by the corresponding phase of the target language corresponding to the source language phrase including a keyword phrase f the source language is stored (60). Text generator (70) assumes a relationship between the phrases of different language contained in the corresponding phrase group table and generates a text sentence candidate (32) of the target language.

The invention belongs to the field of language processing, in particular to a cross-language text similarity evaluation technology based on bilingual word embedding. The technical route and workflow of cross-language text similarity evaluation technology based on bilingual word embedding can be divided into three stages: the construction of bilingual word embedding model, the construction of textsimilarity calculation framework based on multi-neural network, and the cross-language similarity calculation. Through this model, a bilingual shared word embedding representation can be generated, which is based on the word vector correlation theory and Skip-Gram model is used to train word vectors on artificially constructed pseudo-bilingual corpus. Secondly, in order to make the generated wordembedding space as complete as possible, monolingual corpus is used as a supplement to learn additional word embedding knowledge. The similarity score of sentences is obtained by combining several neural network structures to learn the semantic representation of sentences. By dividing short text into paragraphs and treating paragraphs as long sentences as sequence input, the similarity iteration on a larger scale can be realized.

Using exemplary sentences, usage patterns and thematic roles ascribed in VerbNet to generate “deep pattern trees” for the exemplary sentences. Then, when an arbitrary natural language subject sentence is input, these deep pattern trees can be matched to the natural language subject sentence in order to assign thematic roles to at least some of the “grammatical portions” of the natural language subject sentence.

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.

The invention relates to a method for classifying legal texts by adopting a semi-supervised convolutional neural network (SSC) and belongs to the field of neural networks. According to the method, natural languages are processed by utilizing the SSC to achieve the main objective of a system; and through the processing on the legal case description, the problems that what rights and interests of parties does the legal case description violate or which laws and regulations does the parties violate are preliminarily solved, probably more than one rights and interests of the parties is violated orthe parties violate a plurality of laws and regulations at the same time and multi-label classification is realized. Through the legal service platform, case handlers are helped to efficiently handlevarious legal cases and the various legal cases are subjected to semantic analysis to achieve classification to ensure that not only the ability to understand literal meanings but also the ability tologically reason and understand deep meanings are provided in the aspect of the natural language understanding function.

Automated comparison of Darwin Information Typing Architecture (DITA) documents for revision mark-up includes reading document data from first and second DITA documents into respective document object model trees of nodes, and identifying and collapsing emphasis subtree nodes in the trees into their parent nodes, the collapsing caching emphasis data from the identified subtree nodes. A preorder traversal transforms the model trees into respective pre-order node lists and captures adjacent sibling emphasis subtree nodes as single text nodes. The node lists are merged into a merged node list via a longest common subsequence process that recognizes matches node pairs having primary sort key information and document structure metadata meeting a match threshold, with differences between matching tokens of the node pairs saved. A merged document object model built from the refined merged node list is transformed into a hypertext mark-up language document.

The system and method described herein may provide a natural language content dedication service in a voice services environment. In particular, providing the natural language content dedication service may generally include detecting multi-modal device interactions that include requests to dedicate content, identifying the content requested for dedication from natural language utterances included in the multi-modal device interactions, processing transactions for the content requested for dedication, processing natural language to customize the content for recipients of the dedications, and delivering the customized content to the recipients of the dedications.

A method and computer system for translating sentences between languages from an intermediate language-independent semantic representation is provided. On the basis of comprehensive understanding about languages and semantics, exhaustive linguistic descriptions are used to analyze sentences, to build syntactic structures and language independent semantic structures and representations, and to synthesize one or more sentences in a natural or artificial language. A computer system is also provided to analyze and synthesize various linguistic structures and to perform translation of a wide spectrum of various sentence types. As result, a generalized data structure, such as a semantic structure, is generated from a sentence of an input language and can be transformed into a natural sentence expressing its meaning correctly in an output language. The method and computer system can be applied to in automated abstracting, machine translation, natural language processing, control systems, Internet information retrieval, etc.