Session segmentation method, electronic device and computer readable medium
A technology that ends a session and starts a session, applied in the computer field, can solve problems such as single consideration factors and inability to achieve accurate session segmentation, and achieve the effect of avoiding low detection accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0018] refer to figure 1 , shows a flow chart of steps of a method for session segmentation according to Embodiment 1 of the present invention.
[0019] The session segmentation method of the present embodiment includes the following steps:
[0020] Step S102: Determine the session start point for the current session in the multimedia data.
[0021] Wherein, the multimedia data may be data including at least one of audio data and video data. The multimedia data contains at least one session, each session includes at least one sentence, and each session corresponds to a corresponding session start point.
[0022] The determination of the conversation start point can be realized by a person skilled in the art in an appropriate manner. For example, the multimedia data can be firstly subjected to speech recognition to recognize the text corresponding to each sentence (that is, each sentence), and the text also has time information at the same time. Such as timestamp. In this c...
Embodiment 2
[0043] refer to figure 2 , shows a flow chart of steps of a session segmentation method according to Embodiment 2 of the present invention.
[0044] The session segmentation method of the present embodiment includes the following steps:
[0045] Step S202: Perform speech detection on the multimedia data, and obtain sentence starting points of multiple sentences contained therein.
[0046] In this embodiment, multimedia data containing multiple (two or more) sentences is taken as an example, but those skilled in the art should understand that the solutions of the embodiments of the present invention are also applicable to multimedia data containing only one sentence.
[0047] Speech detection for multimedia data may be implemented by those skilled in the art in any appropriate manner, for example, an ASR (Automatic Speech Recognition, automatic speech recognition) manner, etc., which is not limited in this embodiment of the present invention.
[0048] By performing speech de...
Embodiment 3
[0086] refer to Figure 3A , shows a flow chart of steps of a method for session segmentation according to Embodiment 3 of the present invention.
[0087] This embodiment describes the session segmentation method provided by the embodiment of the present invention in the form of a specific example. In this specific example, one-to-one teaching is used as the scene, the multimedia data is in the form of video including audio, and the dialogue between the teacher and the students is in the form of conversation.
[0088] Based on this, the session segmentation method of the present embodiment includes the following steps:
[0089] Step S302: Determine the session start point for the session in the video, and detect the session end point of each session.
[0090] Initially, the first sentence spoken by the teacher in the video can be used as the starting point of the conversation, and the ending point of the conversation can be detected. After the session start point and sessio...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


