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 …

Speech coding is the process of compressing speech signals for transmission and storage
in communication systems. In recent years, speech coding has become increasingly …

Abstract Automatic Speech Recognition (ASR) system is an emerging technology used in
various fields such as robotics, traffic controls, and healthcare, etc. The leading cause of …

Bitrate scalability is a desirable feature for audio coding in real-time communications.
Existing neural audio codecs usually enforce a specific bitrate during training, so different …

Speech codec compresses the input signal into compact bit stream, which is then decoded
at the receiver to generate the best possible perceptual quality. This compression makes …

Low and ultra-low-bitrate neural speech codecs achieved unprecedented coding gain by
generating speech signals from compact features. This paper introduces additional coding …

Speech coding aims at compressing digital speech signals with fewer bits and
reconstructing it back to raw signals, maintaining the speech quality as much as possible …

In this paper, we discuss an important aspect of speech privacy: protecting spoken content.
New capabilities from the field of machine learning provide a unique and timely opportunity …

Robustness to packet loss is one of the main ongoing challenges in real-time speech
communication. Deep packet loss concealment (PLC) techniques have recently …

Data scientists need to develop accurate and effective tools and techniques to handle a
huge amount of data. Therefore, machine learning and deep learning algorithms have come …