Opus 1.5 Audio Codec Released with ML-Based Features

Opus 1.5 introduces machine learning for an enhanced audio experience, ensuring compatibility and high performance on most CPUs.

Opus, a free and widely adopted audio codec known for its flexibility and high performance across a range of bitrates and applications, has recently released its latest update, Opus 1.5.

This new version is particularly significant due to its major leap in incorporating machine learning techniques to enhance audio quality and the overall listening experience. Here are the highlights of the new release.

What’s New in Opus 1.5 Audio Codec

Opus 1.5 sets a new benchmark by employing deep learning for the first time to process and generate audio signals directly. While it has previously utilized ML for tasks like speech and music detection, the 1.5 update takes a bold step by integrating deep learning to improve signal processing.

This innovation aims to deliver superior audio quality without requiring the development of an entirely new ML-based codec, ensuring full compatibility with existing Opus versions. This step is crucial as it guarantees that Opus will continue functioning seamlessly on older, less powerful devices.

In light of this, deep learning, often linked to high-performance GPUs, has been optimized in Opus 1.5 to run efficiently on most CPUs, including mobile phones. However, users with older devices may notice some impact, so all new ML-based enhancements in Opus 1.5 are disabled by default, requiring manual activation.

Furthermore, Opus 1.5 introduces several key features also powered by ML, including advanced packet loss concealment and deep redundancy mechanisms.

Innovations that significantly improve the resilience and quality of audio transmission over unstable network connections, promising to fill in missing audio with unprecedented accuracy, making dropped words or stuttering audio a thing of the past.

Lastly, this update debuts low-bitrate speech quality enhancement tools such as the Linear Adaptive Coding Enhancer (LACE) and its Non-Linear counterpart (NoLACE), which elevate speech clarity even in bandwidth-constrained environments.

You can refer to the release announcement for detailed information about all the novelties and improvements that Opus 1.5 audio codec brings or visit the project’s website.

Bobby Borisov

Bobby Borisov

Bobby, an editor-in-chief at Linuxiac, is a Linux professional with over 20 years of experience. With a strong focus on Linux and open-source software, he has worked as a Senior Linux System Administrator, Software Developer, and DevOps Engineer for small and large multinational companies.

Think You're an Ubuntu Expert? Let's Find Out!

Put your knowledge to the test in our lightning-fast Ubuntu quiz!
Ten questions to challenge yourself to see if you're a Linux legend or just a penguin in the making.

1 / 10

Ubuntu is an ancient African word that means:

2 / 10

Who is the Ubuntu's founder?

3 / 10

What year was the first official Ubuntu release?

4 / 10

What does the Ubuntu logo symbolize?

5 / 10

What package format does Ubuntu use for installing software?

6 / 10

When are Ubuntu's LTS versions released?

7 / 10

What is Unity?

8 / 10

What are Ubuntu versions named after?

9 / 10

What's Ubuntu Core?

10 / 10

Which Ubuntu version is Snap introduced?

The average score is 68%

Leave a Reply

Your email address will not be published. Required fields are marked *