An interactive method and interactive system for parallel reading speech
An interactive method and interactive system technology, applied in the field of interactive method and interactive system of parallel reading speech, can solve problems such as shallow understanding, wrong emotion and prosody information, and users cannot choose among several versions, so as to achieve economical choice time, improve the effect of user experience
Active Publication Date: 2022-05-10
NANJING NANJI INTELLIGENT AGRI MASCH TECH RES INST CO LTD
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] From the perspective of cognitive psychology, the author's creative intentions, especially emotions and emotions, will be reflected in the text with many ambiguities, making it difficult for readers to accurately grasp the author's original intention
More and more Internet information content interactions adopt the method of reading voice combined with text to improve the convenience of users and help users understand the content of the article. However, most of the existing reading voices are in a single version, and users cannot read in several versions. When making choices in the middle, users can only passively accept the errors and poor effects in the middle; one step closer, the reading voice is either pronounced by a real person, or the text is read aloud by artificial intelligence text-to-speech (TTS: Text to Speech) technology, Both have some advantages and disadvantages. For example, real people understand more accurately and more emotionally, but random errors may occur due to factors such as fatigue and distraction; TTS is more stable, but its understanding is relatively shallow, especially for emotional factors.
Users can only choose one and live with its disadvantages
The natural language processing technology (NLP) included in TTS technology is used for emotion and prosody analysis, and because of the lack of real-life guidance information for the current text, there are errors in emotion and prosody information, resulting in a decline in user satisfaction with TTS.
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 1
[0057] Refer to attached Figure 1-Figure 3 As shown, a kind of interactive method of reading voice in parallel in this embodiment, the interactive method comprises the following steps:
[0058] S1, the interactive system provides multiple voice messages;
[0059] S2, according to the mapping principle, perform content time stamping on multiple voice messages;
[0060] S3, the interactive system respectively numbers the multiple voice messages, denoted as n;
[0061] S4, the user selects one of the multiple voice messages for audition;
[0062] S5, the interactive system records the duration of the audition in step S4 as n-k, where k is the duration in seconds;
[0063] S6, the interactive system detects whether the user stops the audition of the current voice information, if so, stops recording the audition time, otherwise continues to play;
[0064] S7, end the audition;
[0065] S8. The interactive system calculates and scores the audition duration rates corresponding ...
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 invention relates to an interactive method for parallel voice reading and its interactive system, which belongs to the technical field of text reading. By analyzing the user's audition habits and duration and other factors, it is possible to judge the user's preferences and facilitate the production of voice information that meets the user's habits. The interactive system Through the time stamp, the inconvenience of switching voices is improved, and the user experience is improved.
Description
technical field [0001] The invention belongs to the technical field of text reading, and more specifically, relates to an interactive method and an interactive system for parallel reading voice. Background technique [0002] From the perspective of cognitive psychology, the author's creative intentions, especially emotions and emotions, will be reflected in the text with many ambiguities, making it difficult for readers to accurately grasp the original intention of the author. More and more Internet information content interactions adopt the method of reading voice combined with text to improve the convenience of users and help users understand the content of the article. However, most of the existing reading voices are in a single version, and users cannot read in several versions. When making choices in the middle, users can only passively accept the errors and poor effects in the middle; one step closer, the reading voice is either pronounced by a real person, or the text...
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): G06F3/16G06F40/205G11B27/10G10L25/60
CPCG06F3/16G06F40/205G11B27/10G10L25/60
Inventor 张向东张毅于航王剑龙
Owner NANJING NANJI INTELLIGENT AGRI MASCH TECH RES INST CO LTD