2024
Srcodec: Split-Residual Vector Quantization for Neural Speech Codec
ICASSP 2024accepted
End-to-end neural speech coding achieves state-of-the-art performance by using residual vector quantization. However, it is a challenge to quantize the latent variables with as few bits as possible. In this paper, we propose SRCodec, a neural speech codec that relies on a fully convolutional encoder…