Site News  |   Monitor Keywords  |   Monitor Archive  |   Organizer  |   Account Info  |

Technique for accurately detecting system failure

Technique for accurately detecting system failure description/claims

This application claims priority under 35 U.S.C. § 119 to Japanese Patent Application No. 2006-350936 filed Dec. 27, 2006, the entire text of which is specifically incorporated by reference herein.

The present invention relates to a method for dividing speech. In particular, the present invention relates to a method for dividing speech by use of acknowledgement responses.

In a transcription process on telephone conversation contents in an operator-service support system and the like, a speech of an operator and that of a customer are separately recorded and converted into text data. Conventionally, in order to efficiently search a recorded speech, a position where a predetermined keyword such as a product name is spoken is recorded, and the timestamp of the position is used as an index. The transcription process is performed by specifying a position of the keyword with automatic speech recognition and the like, and then by replaying the speech of a corresponding part. However, information on the conversation contents cannot be accurately extracted in such a method, since the method does not effectively use the customer's speech, particularly an acknowledgement. To be specific, it is difficult to accurately recognize and analyze a speech from a voice stream, since the speech is not divided into appropriate utterance.

An example of a conventional technique is disclosed in Japanese Patent Application Laid-open Publication No. 2006-276754.

The present invention has been made in view of the aforementioned technical problems. An object of the present invention is to divide a conversational dialog into speech units, what is called an utterance in linguistics by use of acknowledgement responses (hereinafter, simply called acknowledgements). In addition, another object of the invention is to accurately recognize a speech from a voice stream.

In order to achieve the aforementioned objects, an aspect of the present invention is to provide an apparatus for dividing a conversational dialog into utterance. The apparatus is configured to include: a word database for storing spellings and pronunciations of words; a grammar database for storing syntactic rules on words; a pause detecting section which detects a pause location in a channel taking a turn, that is to say speaker's channel, hereafter a main speech, among conversational dialogs inputted in at least two channels; an acknowledgement detecting section which detects an acknowledgement location in a channel not speaking (listener's channel); a boundary-candidate extracting section which extracts boundary candidates in the main speech, by extracting the pauses existing within a predetermined range before and after a base point that is the acknowledgement location; and a recognizing unit which outputs a word string of the speech segmented by one of the extracted candidates after dividing the segmented speech into optimal utterance in reference to the word database and grammar database.

In addition, the grammar database may include fixed-phrase grammar, acknowledgement grammar and recognition grammar. Moreover, the fixed-phrase grammar may include fixed phrases for starting and ending a confirmation, and the word database may include spellings and pronunciations of the fixed phrases for starting and ending a confirmation. Then, the apparatus may include a recognition-target segment determination unit which determines in advance a recognition target segment to be divided into utterance, by referring to the fixed-phrase grammar.

Another aspect of the present invention is to provide a method for dividing a conversational dialog into utterance by use of conversational dialogs inputted in separated channels, by use of a word database in which spellings and pronunciations of words are described, and by use of a grammar database in which grammar including syntactic rules on words is described. The method includes the steps of: detecting a pause location in a channel making a main speech; detecting an acknowledgement location in a channel not making the main speech; extracting boundary candidates in the main speech by extracting pauses existing within a predetermined range before and after a base point that is the acknowledgement location; and outputting a word string of the speech segmented by one of the extracted boundary candidates, after dividing the segmented speech into optimal utterance in reference to the word database and grammar database.

For a more complete understanding of the present invention and the advantage thereof, reference is now made to the following description taken in conjunction with the accompanying drawings.

FIG. 1 shows an apparatus for dividing a speech into utterance.

FIG. 2 shows a flowchart of a processing of the present invention.

FIG. 3 shows a diagram of specific examples of each processing of the present invention.

FIG. 4 is a diagram showing differences in segmentation and recognition results between a conventional technique and the embodiment of the present invention.

FIG. 5 shows an example of a hardware configuration capable of implementing the present invention.

• Provisional Patent
• Utility Patent

• What Is a Patent?
• What Is a Trademark or Servicemark?
• What Is a Copyright?
• Patent Laws