A method, device and device for synthesizing speech and music

Abstract

The embodiment of the invention provides a method, device and equipment for synthesizing voice and music. The method comprises the steps that input voice data and background music data are obtained; one or more words or phrases are identified in the voice data and tones and lasting time of the words or the phrases are obtained, wherein the voice data are composed of the words or the phrases; tone and lasting time of the background music data are obtained; according to the tone and the lasting time of the background music data, speed change processing and / or tone modification processing are / is conducted on the tones and the lasting time of the words or the phrases; the processed voice data and the background music data are synthesized so that a new audio file can be formed. According to the method, device and equipment for synthesizing voice and music, independent voice data and music data can be perfectly combined together, a music attribute is offered to the monotonous voice data, so that the quality of an whole voice stream is improved, and the gradually improved and changed requirements for voice and music synthesis of users are satisfied.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of speech synthesis, and in particular, relate to a method for synthesizing speech and music, an apparatus for synthesizing speech and music, and a device. Background technique [0002] With the development of electronic technology, users often have the requirement of synthesizing voice and music. Waveform splicing technology (or called waveform synthesis technology) is commonly used in the prior art. The development of waveform splicing technology is inseparable from the development of speech encoding and decoding technology, among which the development of LPC technology (linear predictive coding technology) has had a huge impact on waveform splicing technology. LPC technology is essentially a time waveform encoding technology, the purpose of which is to reduce the transmission rate of time domain signals. The advantage of the LPC technique is that it is simple and intuitive. The sy...

AI Technical Summary

Problems solved by technology

[0008] However, the essence of the above-mentioned processing mechanism is still to simply synthesize the waveform data of each isolated user voice and music waveform data together abruptly, and the user voice and music are only a kind of "superimposition" rather than "fusion". The quality of the entire speech flow is still not ideal, and it cannot meet the increasing and changing needs of users for speech and music synthesis. For example, users hope to combine their own recorded speech with music into a piece of rap music (Rap) , it is completely impossible to achieve with the existing technology

Images