End-to-End Neural Audio Coding for Real-Time Communications. (arXiv:2201.09429v2 [cs.SD] UPDATED)

Deep-learning based methods have shown their advantages in audio coding over
traditional ones but limited attention has been paid on real-time
communications (RTC). This paper proposes the TFNet, an end-to-end neural audio
codec with low latency for RTC. It takes an encoder-temporal filtering-decoder
paradigm that seldom being investigated in audio coding. An interleaved
structure is proposed for temporal filtering to capture both short-term and
long-term temporal dependencies. Furthermore, with end-to-end optimization, the
TFNet is jointly optimized with speech enhancement and …

arxiv audio coding communications real-time time