A text-based auxiliary speaker separation method and related device
A technology of speaker separation and text information, applied in the field of auxiliary speaker separation based on text information, can solve problems such as separation errors, and achieve the effect of improving accuracy
Active Publication Date: 2022-08-05
IFLYTEK CO LTD
View PDF11 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In the process of speaker separation, the acoustic characteristics of the speech are generally used as the basis for judgment, and the timbre information of the speech is used to distinguish different speakers. cause separation error
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0022] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0023] like figure 1 shown, figure 1 It is a schematic diagram of an auxiliary speaker separation system 100 based on text information. The text information-based auxiliary speaker separation system 100 includes a voice acquisition device 110 and a voice processing device 120, and the voice acquisition device 110 is connected to the voice processing device 120. , the voice acquisition device 110 is used to acquire voice data and send it to ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The embodiment of the present application discloses a method for separating auxiliary speakers based on text information and a related device. The method includes: acquiring first voice information to be separated; and performing a first separation process on the first voice information to be separated to obtain the first separation As a result, the first separation processing refers to preliminary segmentation and clustering of different speakers in the first voice information; voice processing is performed on the first separation result to obtain second voice information, and the voice processing includes voice recognition or voice representation information collection. ; Input the second speech information into the pre-trained speaker transition point recognition model to determine the speaker transition point in the second speech information; obtain the target separation result according to the speaker transition point and the first separation result. It can be seen that the present application obtains text information through the acquired first voice information, and fuses the underlying acoustic features with the text information for speaker separation, thereby improving the accuracy of speaker separation.
Description
technical field [0001] The present application relates to the technical field of electronic devices, and in particular, to a method and related devices for auxiliary speaker separation based on text information. Background technique [0002] In recent years, with the continuous improvement of audio processing technology, obtaining specific human voices of interest from massive data, such as telephone recordings, news broadcasts, conference recordings, etc., has become a research hotspot. Speaker separation technology refers to the process of automatically dividing speech according to speakers from multi-person conversations and marking them, that is, to solve the problem of "who speaks when". With the help of speaker separation technology, people can achieve a structured management of audio data streams, effectively distinguish the role information of different people in the audio, and then provide a basis for realizing structured audio content at a higher semantic level. S...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G10L21/0272G10L25/03
CPCG10L21/0272G10L25/03
Inventor 方昕柳林刘海波方磊
Owner IFLYTEK CO LTD