Voice processing method and device and medium

Abstract

The embodiment of the invention provides a voice processing method and device, and a device for voice processing, wherein the method is applied to an earphone storage device, and specifically comprises the steps: receiving voice data of a conversation from an earphone device, wherein participants of the conversation comprise at least two conversation users; determining prompt information corresponding to the voice data, wherein the prompt information is obtained according to semantic information and / or emotion information corresponding to the voice data; and in the conversation process, and / orafter the conversation is finished, sending the prompt information to the earphone device, so as to enable the earphone device to output the prompt information. According to the embodiment of the invention, the conversation quality of the current conversation or the subsequent conversation can be improved.

Description

technical field

[0001] The present invention relates to the technical field of voice processing, in particular to a voice processing method and device, and a machine-readable medium. Background technique

[0002] As one of the most natural ways of communication, voice is widely used in voice processing scenarios such as voice dialogue, voice social interaction, Karaok TV, live broadcast, games, and video recording.

[0003] Currently, the collected speech is usually directly used in speech processing scenarios. For example, sending the collected voice to the communication peer; another example, carrying the collected recording in the video.

[0004] In practical applications, there may be situations where the user is not satisfied with the collected voice, and in this case the user will have a need to beautify the voice. For example, some users hope to impress listeners and enhance self-confidence by beautifying their speech. Contents of the invention

[0005] In view o...

Examples

Embodiment 1

[0066] refer to figure 2 , which shows a flow chart of the steps of Embodiment 1 of a speech processing method of the present invention, which is applied to an earphone storage device, and may specifically include the following steps:

[0067] Step 201, receiving the voice data of the dialogue from the earphone device; the above-mentioned dialogue participants specifically include: at least two call users;

[0068] Step 202, determine the prompt information corresponding to the above-mentioned voice data; the above-mentioned prompt information can be obtained based on the semantic information and / or emotional information corresponding to the above-mentioned voice data;

[0069] Step 203. During the conversation and / or after the conversation is over, send the above prompt information to the earphone device, so that the earphone device outputs the above prompt information.

[0070] In step 201, the earphone device may use a microphone array to collect voice data generated by a...

technical field

[0001] The present invention relates to the technical field of voice processing, in particular to a voice processing method and device, and a machine-readable medium. Background technique

[0002] As one of the most natural ways of communication, voice is widely used in voice processing scenarios such as voice dialogue, voice social interaction, Karaok TV, live broadcast, games, and video recording.

[0003] Currently, the collected speech is usually directly used in speech processing scenarios. For example, sending the collected voice to the communication peer; another example, carrying the collected recording in the video.

[0004] In practical applications, there may be situations where the user is not satisfied with the collected voice, and in this case the user will have a need to beautify the voice. For example, some users hope to impress listeners and enhance self-confidence by beautifying their speech. Contents of the invention

[0005] In view o...

Examples

Embodiment 1

[0066] refer to figure 2 , which shows a flow chart of the steps of Embodiment 1 of a speech processing method of the present invention, which is applied to an earphone storage device, and may specifically include the following steps:

[0067] Step 201, receiving the voice data of the dialogue from the earphone device; the above-mentioned dialogue participants specifically include: at least two call users;

[0068] Step 202, determine the prompt information corresponding to the above-mentioned voice data; the above-mentioned prompt information can be obtained based on the semantic information and / or emotional information corresponding to the above-mentioned voice data;

[0069] Step 203. During the conversation and / or after the conversation is over, send the above prompt information to the earphone device, so that the earphone device outputs the above prompt information.

[0070] In step 201, the earphone device may use a microphone array to collect voice data generated by a...

Images