Nec Corporation

Kiyoshi Yamabana

Akihiko Sugiyama

Kenji Sato

Shinichi Ando

Ken Hanazawa

Koji Okabe

Kenji Satoh

Ryosuke Isotani

Shinya Ishikawa

A speech recognition apparatus that performs frame synchronous beam search by using a language model score look-ahead value prevents the pruning of a correct answer hypothesis while suppressing an increase in the number of hypotheses. A language model score look-ahead value imparting deviceis provided with a word dictionarythat defines a phoneme string of a word, a language modelthat imparts a score of appearance easiness of a word, and a smoothing language model score look-ahead value calculation means. The smoothing language model score look-ahead value calculation meansobtains a language model score look-ahead value at each phoneme in the word from the phoneme string of the word defined by the word dictionaryand the language model score defined by the language modelso that the language model score look-ahead values are prevented from concentrating on the beginning of the word.

Language model score look-ahead value imparting device, language model score look-ahead value imparting method, and program storage medium

A speech recognition system for rapidly performing recognition processing while maintaining quality of speech recognition in a speech recognition device, are provided. A speech recognition system includes a speech input device which inputs speech and displays a recognition result, and a speech recognition device which receives the speech from the speech input device, performs recognition processing, and sends back the speech to the speech input device. The speech input device includes a user dictionary section which stores words used for recognizing the input speech, and a reduced user dictionary creation unit which extracts words corresponding to the input speech from the user dictionary and creates a reduced user dictionary. The speech recognition device has a speech recognition unit which inputs the input speech and the reduced user dictionary from the speech input/output device and recognizes the input speech based on the reduced user dictionary and a system dictionary provided beforehand.

System and method for speech recognition using a reduced user dictionary, and computer readable storage medium therefor

A robot for interpreting between a speaker and a listener is provided. The robot includes a direction identifying device for identifying directions of the speaker and the listener, and a motor for moving a robot body to a direction identified by the direction identifying device. The direction identifying device identifies the direction of the speaker at a given time, and in the case where the speaker and the listener are alternated, identifies the direction of an alternated listener by the direction identified at the given time.

Information processing system, method of processing information, and program for processing information

An information processing system includes an information processing unit, an information changing unit, and an information reproducing unit. The information processing unit processes the information received by a sensor and transmits the result of processing to the information reproducing unit. The information changing unit adds or deletes information to or from the result of processing, obtained by the information processing unit, by using an information analysis unit and a change-processing unit. If the information processing is interpretation that includes voice recognition, translation and voice synthesis, the first language received by the sensor is translated into the second language by the information processing unit and is reproduced by the information reproducing unit.

Information processing system, which adds information to translation and converts it to voice signal, and method of processing information for the same

Speech recognition is performed at high speed by processing respective paths of multi-path speech recognition in parallel. A distance calculation unit receives temporal data sequence of acoustic features, calculates the distance values between all acoustic models and the speech features in the respective frames, and writes them in a distance value buffer. An acoustic lookahead unit receives distance values from a plurality of distance value buffers, calculates lookahead values which are relative priorities of respective recognition units, and writes them into the lookahead value buffer. A word string matching unit receives information from a plurality of distance value buffers and the lookahead value buffers, and recognizes the entire utterance in frame synchronization by adequately selecting matching words using the lookahead values to thereby generate a recognition result.

Speech recognition system, method and program that generates a recognition result in parallel with a distance value

A translation supporting apparatus which searches out a translation example useful for a translation task from within a translation example database is disclosed. The translation example database stores character strings of a first language and translation results of a second language corresponding to the character strings in a unit of a document. A retrieval request inputting apparatus inputs a translation target sentence. A similarity retrieval apparatus determines, for each translation example, a similarity to the translation target sentence, a similarity to a translation example context which is another translation example having such a predetermined relationship that it is included in the same document and is present within one sentence before or after the translation example, a similarity to a retrieval request context which is another translation target character string having such a predetermined relationship that it is included in the same document as the translation target character string and is present within the range of one sentence before or after the translation target character string, and a similarity between the translation example context and the retrieval request context, and integrates the four similarities. A similar example outputting apparatus refers to the integrated similarities and outputs those translation examples similar to the translation target character string.

TRANSLATION SUPPORTING APPARATUS AND METHOD AND COMPUTER-READABLE RECORDING MEDIUM, WHEREIN A TRANSLATION EXAMPLE USEFUL FOR THE TRANSLATION TASK IS SEARCHED OUT FROM WITHIN A TRANSLATION EXAMPLE DATABASE

A natural language processing system is disclosed. Upon inputting of a string of words to be analyzed, the natural language processing system generates an initial first chart in which locations between the words included in the input string of words are nodes while the words are edges and an initial second chart containing no edges and in which the words included in the input string of words are nodes, and stores the initial first and second charts in a memory. Then, applying pre-stored rules of a dependency grammar to an adjacent pair of edges on the first chart stored in the memory and an adjacent pair of edges on the second chart, the natural language processing system creates a dependency structure connecting the adjacent pair of edges on the first chart and a dependency structure connecting the adjacent pair of edges on the second chart, and stores the created dependency structures in the memory as new edges to be retained in the first and second charts. The natural language analyzing system repeats creation of the dependency structures and storage of the new edges until all edges contained in the first chart have been processed as target edges. When this condition for terminating the creation and storage is satisfied, the natural language analyzing system outputs the edges contained in the first chart as a result of analysis.

Chart parsing method and system for natural language sentences based on dependency grammars

A word converting apparatus displays converted results and cooccurrent examples in a candidate selection menu for allowing the user to easily and definitely select converted results of words in a cooccurrent relationship. A cooccurrence recognizer 15 recognizes a cooccurrent relationship between words using a cooccurrence dictionary 13. A converter 16 refers to a general dictionary 12 and the cooccurrence dictionary 13 to store a converted result corresponding to a word in a result storage unit 17. If a converted result is derived from the general dictionary 12, a candidate storage unit 18 stores the converted result. If a converted result is derived from the cooccurrence dictionary 13, the candidate storage unit 18 searches the cooccurrence dictionary 13 for a cooccurrent example and stores the cooccurrent example. When candidate selection is indicated, a candidate selector 19 displays converted results and cooccurrent examples stored in the candidate storage unit 18, in a candidate selection menu on a display unit 20. When a candidate alternative is selected from the candidate selection menu, the candidate selector 19 instructs the converter 16 to give highest priority to a selected converted result or a converted result corresponding to a selected cooccurrent example, and the converter 16 changes a converted result in the result storage unit 17.

Growing community of inventors

Tokyo, Japan

Kiyoshi Yamabana