A Streamwise GAN Vocoder for Wideband Speech Coding at Very Low Bit Rate
Ahmed Mustafa, Jan B\"uthe, Srikanth Korse, Kishan Gupta, Guillaume, Fuchs, Nicola Pia

TL;DR
This paper introduces a streamwise GAN vocoder capable of generating high-quality wideband speech from extremely low bit rate parameters, outperforming traditional autoregressive models and rivaling advanced codecs.
Contribution
The paper presents a modified StyleMelGAN-based vocoder that operates in a frame-by-frame manner for streaming, achieving superior quality at very low bit rates.
Findings
Outperforms LPCNet in low bit rate speech coding
Achieves competitive quality to EVS codec at 5.9 kbit/s
Operates with about 5 GMACs computational complexity
Abstract
Recently, GAN vocoders have seen rapid progress in speech synthesis, starting to outperform autoregressive models in perceptual quality with much higher generation speed. However, autoregressive vocoders are still the common choice for neural generation of speech signals coded at very low bit rates. In this paper, we present a GAN vocoder which is able to generate wideband speech waveforms from parameters coded at 1.6 kbit/s. The proposed model is a modified version of the StyleMelGAN vocoder that can run in frame-by-frame manner, making it suitable for streaming applications. The experimental results show that the proposed model significantly outperforms prior autoregressive vocoders like LPCNet for very low bit rate speech coding, with computational complexity of about 5 GMACs, providing a new state of the art in this domain. Moreover, this streamwise adversarial vocoder delivers…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSpeech and Audio Processing · Advanced Data Compression Techniques · Speech Recognition and Synthesis
