-
公开(公告)号：JP2001034451A
公开(公告)日：2001-02-09
申请号：JP2000178069
申请日：2000-06-14
Applicant: LUCENT TECHNOLOGIES INC
Inventor： KUO HONG-KWANG JEFF , LEE CHIN-HUI , PARGELLIS ANDREW NASON
Abstract: PROBLEM TO BE SOLVED: To automatically correct the function of a system, namely dialog on the basis of a dynamic change of an external database by generating a human machine dialog the basis of 1st information and correcting the 1st information on the basis of the 2nd information. SOLUTION: A dialog manager 18 monitors dialog and user's behavior, communicates this type of information to a profile manager 12 through a log file 13, and the manager 12 corrects a user profile and corrects a future dialog session at an appropriate time. This system can accept an explicit request related to profile updating from a user. Further, the user can present another alternative so that the user can meet a dialog interface to the user's inherent behavior, and also, when the user desires, the system allows the user to correct the user profile.
-
公开(公告)号：JP2001005481A
公开(公告)日：2001-01-12
申请号：JP2000166995
申请日：2000-06-05
Applicant: LUCENT TECHNOLOGIES INC
Inventor： LEE CHIN-HUI , RAMESH PADMA
Abstract: PROBLEM TO BE SOLVED: To specify and to take out a segment, which includes key information in a voice message, by putting a tag on the voice message to indicate the position of the key segment detected in the message and taking out the key segment from the message. SOLUTION: A key segment, that is to be registered, is inputted by marking the segment in a message. The segment is processed by using a voice recognition 12 and pronunciation of the segment is generated. Then, an identifier of the key segment and the feature corresponding to the segment are stored in a segment name and feature (pronunciation) 15. Detection of the key segment is executed by using independent models for the feature of the key segment stored in the segment name and feature (pronunciation) 15 and a speaker and a spot is put on the key segment registered in the voice message. The detection of a key segment executed in the key segment detection is executed by a conventional word spot.
-
公开(公告)号：JPH11242495A
公开(公告)日：1999-09-07
申请号：JP34499898
申请日：1998-12-04
Applicant: LUCENT TECHNOLOGIES INC
Inventor： LEE CHIN-HUI , KOICHI SHINODA
Abstract: PROBLEM TO BE SOLVED: To improve the result of a voice recognition by combining a Bayes confroming method having a feature that it is used in the front stage on a hierarchy with a method in which a conversion having a feature that it is used in a hierarchical structure is made a base effectively to cooperatively demonstrate the effect of the confroming of a hidden Markov medel. SOLUTION: A converter 103 obtains samples of an input voices to transmit them to a feature extractor 105. An end point detector 113 uses a finite difference energy characteristic together with energy measurements by the feature extractor 105 in order to determine the starting point and the ending point of a voice signal. A voice recognition device 117 judges what is an uttered language based on the data signal delivered to the device 117 and word models supplied from a word model processor 125, which supplies, for example, hidden Markov models(HMMs) of continuous desity(CD) HMMs at this point of time or the like as to various uttered languages. Here, a system 100 workes in a learning mode and a normal operation mode.
-
公开(公告)号：JPH1173195A
公开(公告)日：1999-03-16
申请号：JP20250898
申请日：1998-07-17
Applicant: LUCENT TECHNOLOGIES INC
Inventor： JUANG BIING-HWANG , LEE CHIN-HUI , LI QI P , ZHOU QIRU
Abstract: PROBLEM TO BE SOLVED: To eliminate the need for enormous investment of the time and labor for a training process by adopting a constitution in which one speech model series is determined in accordance with the partial word transcription of a word series and the partial word transcription consists of a partial word series. SOLUTION: The characteristic of spoken speech utterance is compared with one speech model series and the reliability level reflecting the word series consisting of >=1 words associated with an individual having proposed identification is determined. The one speech model series among the speech model series corresponds to the speech reflecting the word series associated with the individual having the proposed identification is determined. The one speech model series is determined in accordance with the partial word transcription of the word series. The partial word transcription consists of the partial word series consisting of >=1 partial words. A reliability measure module 34 judges the reliability measure, at which a password phrase associated with the individual having the proposed identification is actually the phrase of test utterance by using the strings of target likelihood evaluation points and the strings of anti- likelihood evaluation points.
-
公开(公告)号：JP2001024781A
公开(公告)日：2001-01-26
申请号：JP2000166996
申请日：2000-06-05
Applicant: LUCENT TECHNOLOGIES INC
Inventor： LEE CHIN-HUI , RAMESH PADMA
Abstract: PROBLEM TO BE SOLVED: To obtain the method capable of sortining a lot of voice message speeding up the retrieval processing of the message from a certain caller and giving priority to a message by sorting the voice message according to a caller, who generated the message and specifying the caller for the voice message. SOLUTION: This method has a step for receiving a voice message, a step for analyzing the voice message for deciding the caller, who generated the voice message and a step for sorting the voice message in accordance with the caller. A user registers the caller by pressing the sequence of a prescribed key. Respective received messages are compared with the voice feature of a registered caller in 22. The caller is identified in 21, and otherwise the caller is authenticated in order by using all the voice features registered in order to specify the caller of the message. When the caller of the message is identified, the message is given the tag of a caller ID in 23 and the message is distinguished by the caller.
-
Patent Agency Ranking
公开(公告)号：JPH1173196A
公开(公告)日：1999-03-16
申请号：JP20250998
申请日：1998-07-17
Applicant: LUCENT TECHNOLOGIES INC
Inventor： JUANG BIING-HWANG , LEE CHIN-HUI , LI QI P , ZHOU QIRU
Abstract: PROBLEM TO BE SOLVED: To eliminate the need for enormous investment of the time and labor for a training process, by adopting a constitution, in which one speech model series among speech model series corresponds to the speech reflecting the information associated with an individual having proposed identification. SOLUTION: The characteristic of spoken speech utterance is compared with one speech model series and the reliability level reflecting the information associated with an individual having proposed identification is determined by this spoken speed utterance. The one speech model series among the speech model series corresponds to the speech reflecting the information associated with the individual having the proposed identification. A reliability measure module 34 judges the reliability measure, at which a password phrase associated with the individual having the proposed identification is actually the phrase of test utterance by using the strings of target likelihood evaluation points and the strings of anti-likelihood evaluation points.
-
公开(公告)号：DE69800320T2
公开(公告)日：2001-05-10
申请号：DE69800320
申请日：1998-07-07
Applicant: LUCENT TECHNOLOGIES INC
Inventor： JUANG BIING-HWANG , LI QI P , LEE CHIN-HUI , ZHOU QIRU
-
8.发明专利
公开(公告)号：CA2239340A1
公开(公告)日：1999-01-18
申请号：CA2239340
申请日：1998-05-29
Applicant: LUCENT TECHNOLOGIES INC
Inventor： ZHOU QIRU , JUANG BIING-HWANG , LI QI P , LEE CHIN-HUI
Abstract: A method and apparatus for authenticating a proffered identity of a speaker in which the verbal information content of a speaker's utterance, rather than the v ocal characteristics of the speaker, are used to identify or verify the identity of a speaker. Specifically, features of a speech utterance spoken by a speaker are compared wi th at least one sequence of speaker-independent speech models, where one of these sequences of speech models corresponds to speech reflecting information associat ed with an individual having said proffered identity. Then, a confidence level that the speech utterance in fact reflects the information associated with the individual having said proffered identity is determined based on said comparison. In accordance wi th one illustrative embodiment, the proffered identity is an identity claimed by th e speaker, and the claimed identity is verified based upon the determined confiden ce level. In accordance with another illustrative embodiment, each of a plurality o f proffered identities is checked in turn to identify the speaker as being a parti cular one of a corresponding plurality of individuals. The features of the speech utteranc e may comprise cepstral (i. e., frequency) domain data, and the speaker-independent sp eech models may comprise Hidden Markov Models of individual phonemes. Since speaker-independent models are employed, the need for each system user to perfor m an individual training session is eliminated.
-
公开(公告)号：CA2311145A1
公开(公告)日：2000-12-15
申请号：CA2311145
申请日：2000-06-02
Applicant: LUCENT TECHNOLOGIES INC
Inventor： LEE CHIN-HUI , PARGELLIS ANDREW NASON , KUO HONG-KWANG JEFF
Abstract: A customized method or algorithm for holding an interactive dialogue session between a (human) user and a machine (hereinafter referred to simply as a "dialogue") is generated, such that the resulting dialogue advantageously responds to the user's requests and wherein the system's capability (i.e., the dialogue) is automatically modified thereafter based on dynamically changing external databases. Specifically, a computer system acts as a Dialogue Generator agent by creating such a customized dialogue consisting of services that are organized and presented in a form that is a combination of the user's expectations and the system's capabilities. In particular, the system's capabilities advantageously include the information content of database/service providers (such as, for example, a distributed information source such as the World Wide Web or a corporate file system), and the Dialogue Generator advantageously modifies the dialogue periodically in response to this dynamically changing external environment.
-
公开(公告)号：CA2310176A1
公开(公告)日：2000-12-03
申请号：CA2310176
申请日：2000-05-29
Applicant: LUCENT TECHNOLOGIES INC
Inventor： LEE CHIN-HUI , RAMESH PADMA
IPC: G10L15/08 , G10L13/00 , G10L15/00 , G10L15/10 , G10L15/18 , G10L15/22 , G10L19/00 , H04M3/533 , H04M3/50
Abstract: A method and system of identifying and spotting segments containing key information in voice messages. The method can be used to spot a key segment such as a name segment in a voice message by detecting and verifying the presence of a phrase such as "My name is ..." or "This is ...". Once the key segment of interest has been spotted, the method provides the user with only the pertinent information (e. g., the name of the caller), which is contained in the key segment. This allows a user retrieving a message to hear just a desired section or sections of a message without listening to the rest of the message.
-
-
-
-
-
-
-
-
-
Search Results
14
records
(took 0.023 seconds)
