High-quality Speech Coding With Samplernn
2018 · Janusz Klejsa, Per Hedelin, Cong Zhou, et al.
Abstract
We provide a speech coding scheme employing a generative model based on SampleRNN that, while operating at significantly lower bitrates, matches or surpasses the perceptual quality of state-of-the-art classic wide-band codecs. Moreover, it is demonstrated that the proposed scheme can provide a meaningful rate-distortion trade-off without retraining. We evaluate the proposed scheme in a series of listening tests and discuss limitations of the approach.
Authors
(none)
Tags
Stats
Related papers
- Wavenet Based Low Rate Speech Coding (2017)0.00
- Low Bit-rate Wideband Speech Coding: A Deep Generative Model Based Approach (2021)0.00
- Speech Quality Factors For Traditional And Neural-based Low Bit Rate Vocoders (2020)7.16
- Analysis By Adversarial Synthesis -- A Novel Approach For Speech Vocoding (2019)3.58
- Postgan: A Gan-based Post-processor To Enhance The Quality Of Coded Speech (2022)9.76
- Improving Opus Low Bit Rate Quality With Neural Speech Synthesis (2019)10.48
- Voice Conversion With Conditional Samplernn (2018)7.50
- Low Bit-rate Speech Coding With VQ-VAE And A Wavenet Decoder (2019)14.80