Stories
Slash Boxes
Comments

SoylentNews is people

posted by Fnord666 on Monday October 03 2022, @02:53AM   Printer-friendly

Google Announces Lyra V2 Low Bit-Rate Voice Codec

Lyra V2 is summed up by Google as being "a better, faster, and more versatile speech codec...a new architecture that enjoys a wider platform support, provides scalable bitrate capabilities, has better performance, and generates higher quality audio."

Lyra V2 makes use of the SoundStream end-to-end neural audio codec, continues showing much better performance than the Opus audio codec, improved audio quality, and more. The Lyra V2 open-source code is available today.

Lyra 1.2.0 on GitHub. New features:

  • Speed is significantly faster (~5x improvement seen on Android devices).
  • The SoundStream-based model produces significantly higher quality speech (when comparing 3kbps V1 to 3.2 kbps V2).
  • Selectable bitrate (3200, 6000, 9200 bits per second).
  • Codec latency reduced from 100 ms to 20 ms.
  • Mac and Windows support (in addition to continuing support for Linux and Android). Note: we have verified that these build, and run correctly, but have numerous compilation and linker warnings (Windows in particular due to MSVC/gcc mismatch). These issues and support for other platforms like iOS can be addressed by modifying the .bazelrc file. We welcome community contributions for this.
  • More portable code: The TensorFlow Lite model in the .tflite files can be used in other platforms. The TFLite runtime is optimized for individual platforms, replacing the need to write platform specific assembly.

Lyra (codec).

Previously: Google Unveils Lyra Audio Codec with Better Speech Compression than Opus
Google Posts First Beta Code for Lyra Speech Compression Codec


Original Submission

Related Stories

Google Unveils Lyra Audio Codec with Better Speech Compression than Opus 18 comments

Lyra: A New Very Low-Bitrate Codec for Speech Compression

Since the inception of Lyra, our mission has been to provide the best quality audio using a fraction of the bitrate data of alternatives. Currently, the royalty-free open-source codec Opus, is the most widely used codec for WebRTC-based VOIP applications and, with audio at 32kbps, typically obtains transparent speech quality, i.e., indistinguishable from the original. However, while Opus can be used in more bandwidth constrained environments down to 6kbps, it starts to demonstrate degraded audio quality. Other codecs are capable of operating at comparable bitrates to Lyra (Speex, MELP, AMR), but each suffer from increased artifacts and result in a robotic sounding voice.

Lyra is currently designed to operate at 3kbps and listening tests show that Lyra outperforms any other codec at that bitrate and is compared favorably to Opus at 8kbps, thus achieving more than a 60% reduction in bandwidth. Lyra can be used wherever the bandwidth conditions are insufficient for higher-bitrates and existing low-bitrate codecs do not provide adequate quality.

[...] The implications of technologies like Lyra are far reaching, both in the short and long term. With Lyra, billions of users in emerging markets can have access to an efficient low-bitrate codec that allows them to have higher quality audio than ever before. Additionally, Lyra can be used in cloud environments enabling users with various network and device capabilities to chat seamlessly with each other. Pairing Lyra with new video compression technologies, like AV1, will allow video chats to take place, even for users connecting to the internet via a 56kbps dial-in modem.

This should help make an 8 MiB copy of Shrek sound even better.

Also at CNX Software and Phoronix.


Original Submission

Google Posts First Beta Code for Lyra Speech Compression Codec 16 comments

Google Posts Initial Code For Lyra Speech Codec

Back in February we covered Google's work on the Lyra voice/audio codec designed for fitting with very low bit-rate audio for speech compression in use-cases like WebRTC and video chatting even on the most limited Internet connections. Thanks to leveraging machine learning, Lyra can function at just 3kbps. The code to Lyra is now public.

[...] The Lyra high-quality, low-bitrate speech codec is open-source with an initial v0.0.1 beta commit made today. Building Lyra requires the Bazel build system as well as a particular revision of LLVM/Clang for ABI compatibility.

GitHub (Apache-2.0 License).

Also at VentureBeat and CNX Software.

Previously:
Google Unveils Lyra Audio Codec with Better Speech Compression than Opus


Original Submission

This discussion was created by Fnord666 (652) for logged-in users only, but now has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
(1)
  • (Score: 4, Insightful) by Rosco P. Coltrane on Monday October 03 2022, @03:09AM (2 children)

    by Rosco P. Coltrane (4757) on Monday October 03 2022, @03:09AM (#1274662)

    Being Google, the first question that should come to mind is: how will this cool technology be used to violate people's privacy and slurp up data?

    Here's what I think: lower power requirements and lower bandwidth can only benefit one application: always-on listening devices. Why else would they pursue development of such a codec when bandwidth and battery life for voice applications are typically not an issue for legit applications?

    • (Score: 5, Insightful) by GloomMower on Monday October 03 2022, @04:24AM (1 child)

      by GloomMower (17961) on Monday October 03 2022, @04:24AM (#1274670)

      Because event a 1% savings can be a lot of money across millions of people.

      • (Score: 2) by Freeman on Monday October 03 2022, @04:16PM

        by Freeman (732) on Monday October 03 2022, @04:16PM (#1274737) Journal

        Also, low bandwidth voice service could be useful in this kind of scenario: "SpaceX Has Had 'Promising Conversations' With Apple About iPhone Satellite Service" https://soylentnews.org/article.pl?sid=22/09/13/0311218 [soylentnews.org]

        --
        Joshua 1:9 "Be strong and of a good courage; be not afraid, neither be thou dismayed: for the Lord thy God is with thee"
  • (Score: 0, Funny) by Anonymous Coward on Monday October 03 2022, @04:30AM

    by Anonymous Coward on Monday October 03 2022, @04:30AM (#1274672)

    and we pinky swear that we have no submarine patents on it!

  • (Score: 0, Flamebait) by Frosty Piss on Monday October 03 2022, @05:44AM (2 children)

    by Frosty Piss (4971) on Monday October 03 2022, @05:44AM (#1274681)

    ...3 to 6 months, maybe a year, Google announces the cancellation of the project.

    • (Score: 0, Troll) by Anonymous Coward on Monday October 03 2022, @07:02AM (1 child)

      by Anonymous Coward on Monday October 03 2022, @07:02AM (#1274690)

      If you have the source code it doesn't matter, and this is v2 so they have already stuck with it for over a year.

      • (Score: 2) by PiMuNu on Monday October 03 2022, @04:17PM

        by PiMuNu (3823) on Monday October 03 2022, @04:17PM (#1274738)

        Does that mean it isn't in beta any more?

  • (Score: 2) by crm114 on Monday October 03 2022, @12:08PM (3 children)

    by crm114 (8238) Subscriber Badge on Monday October 03 2022, @12:08PM (#1274716)

    3Kbps = 3096 bits/sec

    (3096*60*60*24)/8 = 33436800 bytes / day
    (((3096*60*60*24)/8)*256.25*100) = Above * 1 year * 100 years

    (((3096*60*60*24)/8)*256.25*100)/1024^4 = .7792 TB

    My entire life, 24/7, for 100 years can now be recorded in less than 1TB.

    Please prove my math is off.

    • (Score: 4, Touché) by crm114 on Monday October 03 2022, @12:10PM (2 children)

      by crm114 (8238) Subscriber Badge on Monday October 03 2022, @12:10PM (#1274717)

      Err... A year is 365.25, not 265.25

      (((3096*60*60*24)/8)*356.25*100)/1024^4

      1.0833 TB for 100 years. :D

      • (Score: 2) by Freeman on Monday October 03 2022, @04:18PM (1 child)

        by Freeman (732) on Monday October 03 2022, @04:18PM (#1274739) Journal

        Might even be correct: (((3096*60*60*24)/8)*365.25*100)/1024^4

        --
        Joshua 1:9 "Be strong and of a good courage; be not afraid, neither be thou dismayed: for the Lord thy God is with thee"
        • (Score: 2) by Ingar on Monday October 03 2022, @04:58PM

          by Ingar (801) on Monday October 03 2022, @04:58PM (#1274743) Homepage

          3kbps = 3000 bits / second

          (((3000*60*60*24)/8)*365.25*100)/1024^4 = 1.0763 TiB or 1.1834 TB

          For the really pedantic, the mean tropical year is approximately 365 days, 5 hours, 48 minutes, 45 seconds. And thanks to the pandemic, the average life expectancy went down a bit.

  • (Score: 0) by Anonymous Coward on Monday October 03 2022, @03:12PM

    by Anonymous Coward on Monday October 03 2022, @03:12PM (#1274729)

    So few examples (none). Why see for yourself when you can read advertising blurb?

(1)