HMS Core Discovery Issue 17 Review | The Voice Moves With Me, The Voice Changes In Seconds

The 17th live broadcast of HMS Core Discovery "Sound Follows Me, Changes Tone Stylist in Seconds" was successfully concluded on August 25. In this live broadcast, we invited product managers, technical experts and innovative entertainment professionals from HMS Core audio editing services . The founder of the application "Singing Duck" was a guest in the live broadcast room, sharing insights on the development of the audio-visual entertainment industry and new ways of playing audio technology. Let's review the exciting content of this issue together!

【Wonderful review】

1. Work together, Sing Duck & HMS Core to explore audio technology

2. The gameplay has been upgraded, and the singing voice synthesis API helps users create easily

3. "Sound" is immersive, and the spatial audio algorithm brings an auditory feast

【expert's point】

Nelson, Product Manager, Audio Editing, Huawei

With the competition of audio content homogenization, the audio industry will pay more attention to the demands of ordinary users' personalized expression in the future. AI audio technology represented by singing voice synthesis can stimulate the huge creative energy contained in ordinary users to form a wider range of creation. mode, thereby driving a wider audience.

Kong, Huawei Audio Editing Technical Expert

When it comes to the virtual world, everyone's first reaction is AR and VR. When everyone pays attention to the visual interaction level, changes in the auditory level are actually happening quietly. Now the increasingly mature spatial audio and 6Dof spatial sound field technology will give everyone Bring a more "sound" immersive listening experience.

Li Yang, founder of Sing Duck APP

Users can use the combination of AI technology and music creation and editing to complete tasks that were very complicated or difficult to complete in the past. It may be a trend in future development, such as voice synthesis and singing synthesis, voiceprint technology, etc. Users do not need to record themselves, but It is through simple editing that you can hear the results, save a lot of links, and can better control the effect of the sound.

【Wonderful Q&A】

Q1: What fields can singing voice synthesis technology be used in?

A: The singing voice synthesis service can be widely used in audio and video creative production, audio and video entertainment, music education, virtual idols and other fields. For example, in the field of virtual idols, through singing voice synthesis, the virtual human can have the ability to sing with specific timbres and make it more vivid; in music creation or creative editing of short videos, the singing voice synthesis service can help users freely create synthetic songs, such as singing By accessing the singing voice synthesis, Duck enables users to synthesize singing voices through simple input to complete various types of singing rhythms, and can also control singing skills, including breathing and portamento, vibrato skills, etc.

Q2: What is the difference between stereo, surround and three-dimensional sound?

Audio develops from mono, stereo, surround to three-dimensional sound. The monophonic audio user listens to the left and right ears exactly the same, without any sense of orientation. In the era of stereo, users can feel the inconsistent presentation of different instruments in the left and right ears, with a certain sense of space. Surround sound is to add more sound channels on the basis of stereo, making the audio more surround. Taking speakers as an example, stereo is two speakers in the front, left and right, while surround sound is played by multiple speakers.

Q3: How do you view the development trend of spatial audio?

A: Spatial audio technology is evolving in two directions. One is evolving from professional venues to personal scenes, bringing the experience of auditioning in theaters and theaters to the terminal. Everyone no longer needs to rely on certain fixed places to experience immersion everywhere. High-quality audio content. The other is the evolution from the current fixed sound field to the 6Dof degree-of-freedom space sound field. (6Dof is based on 3Dof to increase the displacement of left and right, front and rear, and up and down, which is closer to the auditory experience of people in the real world.) Combining AR and VR technology, generate new audio and video experiences, and bring more new interactive gameplay.

Q4: In the UGC era, what is the future evolution trend of the audio industry?

A: In terms of content creation, users gradually move from consumption to creation, and audio content will be more inclined to personalized expressions and demands, and pay more attention to the value brought by copyright and value-added services; It will bring a better sense of immersion and story, and you no longer need to rely on fixed places or devices to experience immersive high-quality audio content anywhere. In terms of audio creation, the combination of AI technology and music creation will make the work that was complicated or difficult to complete in the past easier. Voice-based interactive technology can save a lot of complicated processing.

Welcome to log in to HMS Core Audio Editing Service for more technical details.

If you have relevant technical requirements, please contact [e-mail]

Learn more details>>

Visit the official website of Huawei Developer Alliance
Get development guidance documents
Huawei Mobile Services Open Source Warehouse Address: GitHub , Gitee

Follow us to know the latest technical information of HMS Core for the first time~