We introduce a state-of-the-art real-time, high-fidelity, audio codec leveraging neural
networks. It consists in a streaming encoder-decoder architecture with quantized latent …

We present SoundStream, a novel neural audio codec that can efficiently compress speech,
music and general audio at bitrates normally targeted by speech-tailored codecs …

Telemeetings such as audiovisual conferences or virtual meetings play an increasingly
important role in our professional and private lives. For that reason, system developers and …

Neural audio codecs are initially introduced to compress audio data into compact codes to
reduce transmission latency. Researchers recently discovered the potential of codecs as …

A good audio codec for live applications such as telecommunication is characterized by
three key properties:(1) compression, ie the bitrate that is required to transmit the signal …

In recent years, large language models have achieved significant success in generative
tasks (eg, speech cloning and audio generation) related to speech, audio, music, and other …

The recent emergence of machine-learning based generative models for speech suggests a
significant reduction in bit rate for speech codecs is possible. However, the performance of …

This paper presents FunCodec, a fundamental neural speech codec toolkit, which is an
extension of the open-source speech processing toolkit FunASR. FunCodec provides …

We present BigCodec, a low-bitrate neural speech codec. While recent neural speech
codecs have shown impressive progress, their performance significantly deteriorates at low …

We introduce LMCodec, a causal neural speech codec that provides high quality audio at
very low bitrates. The backbone of the system is a causal convolutional codec that encodes …