CN113066496A - Method for analyzing call robbing of two conversation parties in audio - Google Patents
Method for analyzing call robbing of two conversation parties in audio Download PDFInfo
- Publication number
- CN113066496A CN113066496A CN202110284452.7A CN202110284452A CN113066496A CN 113066496 A CN113066496 A CN 113066496A CN 202110284452 A CN202110284452 A CN 202110284452A CN 113066496 A CN113066496 A CN 113066496A
- Authority
- CN
- China
- Prior art keywords
- block
- judgment
- list
- speaking
- speaking content
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention relates to a method for analyzing the call robbing of two conversation parties in audio, which comprises the following steps: (1) processing and analyzing the audio file into dialogue text information; (2) respectively gathering the speaking contents of the two parties of the conversation into two lists; (3) and (4) judging the call robbing situation according to the comparison of the speaking start time and the speaking end time of the two parties of the conversation. The method of the invention converts the audio file into text information, and can quickly, conveniently and accurately judge the call robbing situation of the two parties in the conversation in the audio by comparing the speaking time nodes of the two parties.
Description
Technical Field
The invention relates to the technical field of dialogue analysis, in particular to a method for analyzing the call robbing of two dialogue parties in audio.
Background
With the need of the client for analyzing the two parties of the conversation in the audio, whether the two parties of the conversation in the audio are robbed or not needs to be analyzed and judged, and the existing manual analysis scheme is not efficient, but easy to leak.
Disclosure of Invention
Aiming at the defects of the existing scheme, the invention discloses a method for analyzing the call robbing of two conversation parties in audio.
The technical scheme of the invention is as follows:
a method for analyzing the double-party call robbing of a conversation in audio is characterized by comprising the following steps: (1) acquiring audio files of two-party conversation, and analyzing the audio files into conversation text information through asr preprocessing; (2) respectively gathering the talking contents of the two parties A and B in the dialogue text information into an a list and a B list; (3) traversing the b list with each dialog block of the a list; (4) judging whether the speaking ending time of a [ i ] block of speaking content in the a list is smaller than the speaking starting time of b [ i ] block of speaking content in the b list; (5) if the judgment in the step (4) is positive, the judgment is finished if the speech is not robbed, and a [ i +1] blocks of speech contents in the a list are obtained;
(6) if the judgment in the step (4) is negative, then judging whether the ending time of the a [ i ] block of speaking content is greater than the starting time of the b [ i ] block of speaking content, and the starting time of the a [ i ] block of speaking content is less than the ending time of the b [ i ] block of speaking content;
(7) if the judgment in the step (6) is negative, the judgment is that no robbery exists, the judgment is finished, and a [ i +1] block speaking content in the a list is obtained;
(8) if the judgment in the step (6) is yes, then judging whether the starting time of the a [ i ] block of speaking content is less than the starting time of the b [ i ] block of speaking content;
(9) if the judgment in the step (8) is yes, the call robbing situation is that when A speaks, B talks, the judgment is finished, and a [ i +1] block speaking content in the a list is obtained;
(10) if the judgment in the step (8) is negative, then judging whether the starting time of b [ i ] block of speaking content is less than the starting time of a [ i ] block of speaking content;
(11) if the judgment in the step (10) is yes, the call robbing situation is that A carries out call robbing when B speaks, the judgment is finished, and a [ i +1] block speaking content in the a list is obtained;
(12) if the acquisition of a [ i +1] block of the speaking content fails, namely the traversal of the list a to the list b is completed, the dialogue analysis is finished.
Preferably, the dialog text information includes a content of a speech, a start time of the speech, and an end time of the speech.
The invention has the beneficial effects that:
the method of the invention converts the audio file into text information, and can quickly, conveniently and accurately judge the call robbing situation of the two parties in the conversation in the audio by comparing the speaking time nodes of the two parties.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a diagram illustrating the conversion of an audio file into text followed by call grabbing in the embodiment.
Detailed Description
For further understanding of the present invention, the present invention will be described in detail with reference to examples, which are provided for illustration of the present invention but are not intended to limit the scope of the present invention.
As shown in fig. 1, the present embodiment relates to a method for analyzing the double-party robbing of a conversation in audio, which is characterized in that the method comprises the following steps: (1) acquiring audio files of two-party conversation, and analyzing the audio files into conversation text information through asr preprocessing; (2) respectively gathering the talking contents of the two parties A and B in the dialogue text information into an a list and a B list; (3) traversing the b list with each dialog block of the a list; (4) judging whether the speaking ending time of a [ i ] block of speaking content in the a list is smaller than the speaking starting time of b [ i ] block of speaking content in the b list; (5) if the judgment in the step (4) is positive, the judgment is finished if the speech is not robbed, and a [ i +1] blocks of speech contents in the a list are obtained;
(6) if the judgment in the step (4) is negative, then judging whether the ending time of the a [ i ] block of speaking content is greater than the starting time of the b [ i ] block of speaking content, and the starting time of the a [ i ] block of speaking content is less than the ending time of the b [ i ] block of speaking content;
(7) if the judgment in the step (6) is negative, the judgment is that no robbery exists, the judgment is finished, and a [ i +1] block speaking content in the a list is obtained;
(8) if the judgment in the step (6) is yes, then judging whether the starting time of the a [ i ] block of speaking content is less than the starting time of the b [ i ] block of speaking content;
(9) if the judgment in the step (8) is yes, the call robbing situation is that when A speaks, B talks, the judgment is finished, and a [ i +1] block speaking content in the a list is obtained;
(10) if the judgment in the step (8) is negative, then judging whether the starting time of b [ i ] block of speaking content is less than the starting time of a [ i ] block of speaking content;
(11) if the judgment in the step (10) is yes, the call robbing situation is that A carries out call robbing when B speaks, the judgment is finished, and a [ i +1] block speaking content in the a list is obtained;
(12) if the acquisition of a [ i +1] block of the speaking content fails, namely the traversal of the list a to the list b is completed, the dialogue analysis is finished.
As shown in fig. 2, the dialog text information includes the contents of the utterance, the utterance start time, and the utterance end time.
The present invention and its embodiments have been described above schematically, without limitation, and the embodiments of the present invention are shown in the drawings, and the actual structures are not limited thereto. Therefore, those skilled in the art should understand that they can easily and effectively design and modify the structure and embodiments of the present invention without departing from the spirit and scope of the present invention.
Claims (2)
1. A method for analyzing the double-party call robbing of a conversation in audio is characterized by comprising the following steps: (1) acquiring audio files of two-party conversation, and analyzing the audio files into conversation text information through asr preprocessing; (2) respectively gathering the talking contents of the two parties A and B in the dialogue text information into an a list and a B list; (3) traversing the b list with each dialog block of the a list; (4) judging whether the speaking ending time of a [ i ] block of speaking content in the a list is smaller than the speaking starting time of b [ i ] block of speaking content in the b list; (5) if the judgment in the step (4) is positive, the judgment is finished if the speech is not robbed, and a [ i +1] blocks of speech contents in the a list are obtained;
(6) if the judgment in the step (4) is negative, then judging whether the ending time of the a [ i ] block of speaking content is greater than the starting time of the b [ i ] block of speaking content, and the starting time of the a [ i ] block of speaking content is less than the ending time of the b [ i ] block of speaking content;
(7) if the judgment in the step (6) is negative, the judgment is that no robbery exists, the judgment is finished, and a [ i +1] block speaking content in the a list is obtained;
(8) if the judgment in the step (6) is yes, then judging whether the starting time of the a [ i ] block of speaking content is less than the starting time of the b [ i ] block of speaking content;
(9) if the judgment in the step (8) is yes, the call robbing situation is that when A speaks, B talks, the judgment is finished, and a [ i +1] block speaking content in the a list is obtained;
(10) if the judgment in the step (8) is negative, then judging whether the starting time of b [ i ] block of speaking content is less than the starting time of a [ i ] block of speaking content;
(11) if the judgment in the step (10) is yes, the call robbing situation is that A carries out call robbing when B speaks, the judgment is finished, and a [ i +1] block speaking content in the a list is obtained;
(12) if the acquisition of a [ i +1] block of the speaking content fails, namely the traversal of the list a to the list b is completed, the dialogue analysis is finished.
2. The method as claimed in claim 1, wherein the dialog text information includes the content of the utterance, the start time of the utterance, and the end time of the utterance.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110284452.7A CN113066496A (en) | 2021-03-17 | 2021-03-17 | Method for analyzing call robbing of two conversation parties in audio |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110284452.7A CN113066496A (en) | 2021-03-17 | 2021-03-17 | Method for analyzing call robbing of two conversation parties in audio |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113066496A true CN113066496A (en) | 2021-07-02 |
Family
ID=76560897
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110284452.7A Pending CN113066496A (en) | 2021-03-17 | 2021-03-17 | Method for analyzing call robbing of two conversation parties in audio |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113066496A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105895116A (en) * | 2016-04-06 | 2016-08-24 | 普强信息技术(北京)有限公司 | Dual track voice break-in and interruption analysis method |
JP2018206055A (en) * | 2017-06-05 | 2018-12-27 | コニカミノルタ株式会社 | Conversation recording system, conversation recording method, and care support system |
CN112511698A (en) * | 2020-12-03 | 2021-03-16 | 普强时代(珠海横琴)信息技术有限公司 | Real-time call analysis method based on universal boundary detection |
-
2021
- 2021-03-17 CN CN202110284452.7A patent/CN113066496A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105895116A (en) * | 2016-04-06 | 2016-08-24 | 普强信息技术(北京)有限公司 | Dual track voice break-in and interruption analysis method |
JP2018206055A (en) * | 2017-06-05 | 2018-12-27 | コニカミノルタ株式会社 | Conversation recording system, conversation recording method, and care support system |
CN112511698A (en) * | 2020-12-03 | 2021-03-16 | 普强时代(珠海横琴)信息技术有限公司 | Real-time call analysis method based on universal boundary detection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110379412B (en) | Voice processing method and device, electronic equipment and computer readable storage medium | |
CN108962282B (en) | Voice detection analysis method and device, computer equipment and storage medium | |
CN110047481B (en) | Method and apparatus for speech recognition | |
US20220253700A1 (en) | Audio signal time sequence processing method, apparatus and system based on neural network, and computer-readable storage medium | |
CN105261356A (en) | Voice recognition system and method | |
CN103886871A (en) | Detection method of speech endpoint and device thereof | |
CN101315772A (en) | Speech reverberation eliminating method based on Wiener filtering | |
CN111294468A (en) | Tone quality detection and analysis system for customer service center calling | |
US11238869B2 (en) | System and method for reconstructing metadata from audio outputs | |
CN111462758A (en) | Method, device and equipment for intelligent conference role classification and storage medium | |
CN112735385B (en) | Voice endpoint detection method, device, computer equipment and storage medium | |
CN1622193A (en) | Voice signal detection method | |
CN113192535B (en) | Voice keyword retrieval method, system and electronic device | |
CN103514882A (en) | Voice identification method and system | |
CN109215634A (en) | A kind of method and its system of more word voice control on-off systems | |
CN111081219A (en) | End-to-end voice intention recognition method | |
CN105895116B (en) | Double-track voice break-in analysis method | |
CN206977582U (en) | A kind of video conference echo cancellation system | |
CN109800299B (en) | Speaker clustering method and related device | |
CN113066496A (en) | Method for analyzing call robbing of two conversation parties in audio | |
CN110931016A (en) | Voice recognition method and system for offline quality inspection | |
CN112802498A (en) | Voice detection method and device, computer equipment and storage medium | |
CN113099043A (en) | Customer service control method, apparatus and computer-readable storage medium | |
CN113438368B (en) | Method, device and computer readable storage medium for realizing ring back tone detection | |
CN112511698B (en) | Real-time call analysis method based on universal boundary detection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210702 |