International Business Machines Corporation

Nuance Communications, Inc.

Guo Kang Fu

Zhao Han

Su Liu

Rui Li Xu

Ying Liu

Yu Chen Zhou

Zhi Jun Wang

Xue Feng Gao

Dan Li

Xing Xing Wang

Bin Jia

Yi Zhi Yao

Bing Xin Wang

Feng Shi

Da Wei Zhang

Zhi Guo Hd Deng

Ya Juan Zhai

Li Qin Shen

Nan Li

Jia Zhong Wu

Xi Ying Zhou

Julian Chengjun Chen

Da Lai Yan

Hai Ping Li

A user reading statistic data set relating to a natural language document is received. The user reading statistic data set includes information indicative of at least one of a set of user reading statistic types. A set of machine logic rules is applied to the user reading statistic data set to generate, as reading assistance to the reader with reading the natural language document, a user reading comprehension data set including information indicative of reading comprehension with respect to content of the natural language document.

Generating a structured document guiding view

Rendering a content item of a social networking system can include dividing, using a processor, a content item into a plurality of sections, determining, using the processor, a score for each of the plurality of sections, and applying, using the processor, a visualization technique to a selected section of the content item based upon the scores of the plurality of sections.

Matching a comment to a section of a content item based upon a score for the section

An operation of a user on a document is received. The received operation is analyzed. A structured guiding view for the document is generated by using a result of the analyzing and a basic structure of the document. In certain implementations, a user's reading interests and reading habits may be analyzed through the user's reading behaviors or notations added to the document by the user, and the result of the analyzing may be mapped into an intuitively presentable structured guiding view for the document.

Applying a visualization technique to a particular section of a content item based upon a relative ranking

The present invention discloses converting a text form into a speech. In the present invention, partial word lists of a data source are obtained by parsing the data source in parallel or in series. The partial word lists are then compiled to obtain phoneme graphs corresponding, respectively, to the partial word lists, and then the obtained phoneme graphs are combined. Speech recognition is then conducted according to the combination results. According to the present invention, computational complexity may be reduced and recognition efficiency may be improved during speech recognition.

Partial word lists into a phoneme tree

A voice authentication system using a removable voice ID card comprises: at server side, a voiceprint database for storing the voiceprints of all authorized users; a voiceprint updating means for updating the voiceprints in said voiceprint database; and a voiceprint digest generator for generating a voiceprint digest according to a request from a client; at client side, a voice ID card for storing the voiceprint of an authorized user; a validation means for validating the voiceprint in the voice ID card on the basis of the voiceprint digest from the server; an audio device for performing voice interaction with a user; and a voice authentication means for determining whether the voiceprint from said voice ID card is of the same speaker as the voice from said audio device.

Voice authentication system and method using a removable voice ID card

Converting partial word lists into a phoneme tree for speech recognition

Dynamically managing an online communication group with a computerized communication tool having at least one processor includes extracting with the computerized communication tool at least one keyword from a private online communication session between at least two parties; and automatically inviting the parties to join an online communication group dedicated to a topic characterized by the at least one keyword with the computerized communication tool.

Dynamically managing online communication groups

A voice authentication system using a removable voice ID card comprises: at server side, a voiceprint database for storing the voiceprints of all authorized users; a voiceprint updating means for updating the voiceprints in said voiceprint database; and a voiceprint digest generator for generating a voiceprint digest according to a request from a client; at client side, a voice ID card for storing the voiceprint of an authorized user; a validation means for validating the voiceprint in the voice ID card on the basis of the voiceprint digest from the server; an audio device for performing voice interaction with a user; and a voice authentication means for determining whether the voiceprint from said voice ID card is of the same speaker as the voice from said audio device. The present invention can significantly avoid the abuse of a voice ID card when it is lost or stolen by using the voiceprint digest stored at server side to verify the voiceprint in the voice ID card.

A method for processing speech data includes obtaining a pitch and at least one formant frequency for each of a plurality of first speech data; constructing a first feature space with the obtained fundamental frequencies and formant frequencies as features; and classifying the plurality pieces of first speech data using the first feature space, and thus a plurality of speech data classes and the corresponding description are obtained.

Method and apparatus for processing speech data with classification models

A method and an apparatus for automatic recognition of tone languages, employing the steps of converting the words of speech into an electrical signal, generating spectral features from the electrical signal, extracting pitch values from the electrical signal, combining said spectral features and the pitch values into acoustic feature vectors, comparing the acoustic feature vectors with prototypes of phonemes in an acoustic prototype database including prototypes of toned vowels to produce labels, and matching the labels to text using a decoder comprising a phonetic vocabulary and a language model database.

Growing community of inventors

Beijing, China

Guo Kang Fu