Lyra is a lossy

audio codec An audio codec is a device or computer program capable of encoding or decoding a digital data stream (a codec) that encodes or decodes audio. In software, an audio codec is a computer program implementing an algorithm that compresses and decompres ...

developed by

Google Google LLC () is an American Multinational corporation, multinational technology company focusing on Search Engine, search engine technology, online advertising, cloud computing, software, computer software, quantum computing, e-commerce, ar ...

that is designed for compressing speech at very low bitrates. Unlike most other audio formats, it compresses data using a

machine learning Machine learning (ML) is a field of inquiry devoted to understanding and building methods that 'learn', that is, methods that leverage data to improve performance on some set of tasks. It is seen as a part of artificial intelligence. Machine ...

-based algorithm.

Features

The Lyra codec is designed to transmit speech in real-time when bandwidth is severely restricted, such as over slow or unreliable network connections. It runs at a fixed bitrate 3 kbps and it is intended to provide better quality than codecs that use traditional waveform-based algorithms at similar bitrates. Instead, compression is achieved via a

algorithm that encodes the input with feature extraction, and then reconstructs an approximation of the original using a generative model. This model was trained on thousands of hours of speech recorded in over 70 languages to function with various speakers. Because generative models are more computationally complex than traditional codecs, a simple model that processes different frequency ranges in parallel is used to obtain acceptable performance. Lyra operates on frames of 40 ms and Google claims it can run with 90 ms of latency on typical hardware. Google's reference implementation is available for Android and

Linux Linux ( or ) is a family of open-source Unix-like operating systems based on the Linux kernel, an operating system kernel first released on September 17, 1991, by Linus Torvalds. Linux is typically packaged as a Linux distribution, which i ...

Quality

Lyra performs significantly better than traditional codecs at similar bitrates. Ian Buckley at MakeUseOf says, "It succeeds in creating almost eerie levels of audio reproduction with bitrates as low as 3 kbps." Google claims that is reproduces natural-sounding speech, and that Lyra at 3 kbps beats Opus at 8kps. Tsahi Levent-Levi writes that Satin,

Microsoft's Microsoft Corporation is an American multinational technology corporation producing computer software, consumer electronics, personal computers, and related services headquartered at the Microsoft Redmond campus located in Redmond, Washingt ...

AI-based codec, outperforms it at higher bitrates.

History

Lyra was first announced in February 2021, and in April, Google released the source code of their reference implementation.

Support

Implementations

Google's implementation is available on

Github GitHub, Inc. () is an Internet hosting service for software development and version control using Git. It provides the distributed version control of Git plus access control, bug tracking, software feature requests, task management, co ...

under the Apache License. Written in C++, it is optimized for 64-bit

ARM In human anatomy, the arm refers to the upper limb in common usage, although academically the term specifically means the upper arm between the glenohumeral joint (shoulder joint) and the elbow joint. The distal part of the upper limb between t ...

but also runs on x86, on either Android or Linux.

Applications

Google Duo Google Duo is a proprietary voice over IP (VoIP) and videotelephony service developed by Google, available for Android, iOS and web browsers. It lets users make and receive one-to-one and group audio and video calls with other Duo users in hig ...

uses Lyra to transmit sound for video chats when bandwidth is limited.

References

{{Reflist

External links

Lyra: A New Very Low-Bitrate Codec for Speech Compression
Google blog post with a demonstration comparing codecs