By submitting this form, you are agreeing to the Terms of Use and Privacy Policy.
Audio codecs compress audio in order to reduce storage requirements or network bandwidth usage.
Audio codecs should ideally be transparent to the end user, with decoded audio that is perceptually indistinguishable from the original and no perceptible latency introduced during the encoding/decoding process.
The North America Audio Codec Market accounted for $XX Billion in 2021 and is anticipated to reach $XX Billion by 2026, registering a CAGR of XX% from 2022 to 2027.
Satin is Microsoft’s new AI-powered audio codec. Satin can produce extremely wide band speech starting at 6 kbps and full-band stereo music starting at 17 kbps, with increasingly better quality as bitrates increase.
Satin was created to deliver excellent audio quality even when packet loss is severe. Furthermore, its high quality at low bitrates allows us to use more of the available bandwidth to improve packet loss resiliency.
Lyra, a neural audio codec for low-bitrate speech, was released by Google.
Introduce “SoundStream: an End-to-End Neural Audio Codec,” a new neural audio codec that improves on existing efforts by offering higher-quality audio and expanding to encode a wider range of sound types, including clear speech, loud and reverberant speech, music, and ambient noises.
SoundStream is the first neural network codec that can handle both voice and music while running in real time on a smartphone CPU. With a single trained model, it can deliver state-of-the-art quality across a wide range of bitrates, which is a huge advancement in learnable codecs.
