Speech signal sending method and device, equipment and readable memory medium
A voice signal and transmission method technology, applied in voice analysis, instruments, etc., can solve the problem of high cost of audio signal transmission bandwidth, achieve the effect of reducing the encoding length, reducing bandwidth occupation, and improving transmission efficiency
Pending Publication Date: 2020-02-11
TENCENT TECH (SHENZHEN) CO LTD
View PDF5 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] Embodiments of the present application provide a method, device, device, and readable storage medium for transmitting voice signals, which can solve the problem of the transmission bandwidth of the audio signal when the non-environmental sound includes many voice frames with low voice probability. The problem of high cost
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
[0034] In order to make the purpose, technical solution and advantages of the present application clearer, the implementation manners of the present application will be further described in detail below in conjunction with the accompanying drawings.
[0035] First, a brief introduction to the nouns involved in the embodiments of this application:
[0036] Speech frame: refers to the original digital signal of speech in a single time slice. Optionally, the speech frame can be implemented as any one of ambient sound frame, silent frame, and human voice frame. Among them, the environmental sound frame refers to the audio frame in which the human voice accounts for a small proportion in the original digital signal of the voice, that is, the main sound in the environmental sound frame is not a sound made by a person. Usually, a required probability is set, and the human voice is performed on the voice frame. After detection, when the human voice probability of the voice frame is le...
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 discloses a speech signal sending method and device, equipment and a readable memory medium and relates to the field of multimedia processing. The method comprises the steps of carryingout human voice probability detection on speech frames in target speech signals, thereby obtaining human voice frames; obtaining first human voice frames and second human voice frames, wherein a humanvoice probability of the first human voice frames is greater than or equal to a first required probability, and the human voice probability of the second human voice frames is smaller than the firstrequired probability; normalizing the second human voice frames into mute frames; carrying out variable length coding on the first human voice frames and the mute frames; and sending audio coding streams. Before the target speech signals are coded, the second human voice frames with the relatively low human voice probability in the target speech signals are normalized into the mute frames; the target speech signals are coded in a variable length coding mode; a coding result length of the mute frames is smaller than that of the second human voice frames; a coding length is reduced; and bandwidth occupation of the target speech signals in a sending process is reduced.
Description
technical field [0001] The embodiments of the present application relate to the field of multimedia processing, and in particular to a method, device, device, and readable storage medium for sending voice signals. Background technique [0002] The real-time voice function is a function that realizes real-time communication between two terminals. In the real-time voice function, the sending terminal continuously collects audio signals through a microphone, encodes the collected audio signals, and sends the coded stream to To the receiving terminal, the receiving terminal receives the coded stream and decodes the coded stream to play. [0003] In related technologies, before the audio signal is sent by the sending terminal, the audio signal needs to be filtered. First, the audio signal is detected by human voice to determine the voice probability of the audio signal. The voice probability is used to indicate that the audio signal is human. The probability of the sound, when i...
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 Applications(China)
IPC IPC(8): G10L19/008G10L19/012G10L21/0208
CPCG10L19/008G10L19/012G10L21/0208G10L2021/02082
Inventor 曹木勇周佳庆
Owner TENCENT TECH (SHENZHEN) CO LTD