Source Coding of Audio Signals with a Generative Model

By Roy Fejgin, Janusz Klejsa, Lars F. Villemoes, Cong Zhou. 2020

17 citations recorded by the source corpus.

We consider source coding of audio signals with the help of a generative model. We use a construction where a waveform is first quantized, yielding a finite bitrate representation. The waveform is then reconstructed by random sampling from a model conditioned on the quantized waveform. The proposed coding scheme is theoretically analyzed. Using SampleRNN as the generative model, we demonstrate that the proposed coding structure provides performance competitive with state-of-the-art source coding tools for specific categories of audio signals.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Generative Speech Coding with Predictive Variance Regularization (2021, background): “Hence, despite extensive research, e.g., [8–12] generative synthesis based speech coding has not yet seen major practical applications.”
End-to-End Neural Speech Coding for Real-Time Communications (2022, neutral): “Existing neural audio codecs could mainly be grouped into two categories, generative de-coder models [1, 2, 3, 4, 5, 6] and end-to-end neural audio coding [7, 8, 9, 10].”
High Quality Audio Coding with Mdctnet (2022, background): “As discussed in [14], this encourages a perceptual noise shaping as designed in the encoder, but in contrast to [14] the MDCTNet operates directly in the perceptual domain.”
Universal Speech Enhancement with Score-based Diffusion (2022, methodology): “Inspired by Fejgin et al. (2020), we decide to use an expectation of the enhanced waveform.”
Cross-Scale Vector Quantization for Scalable Neural Speech Coding (2022, background): “Some researchers leverage advances in speech synthesizing with generative models [1, 2, 3, 4, 5, 6, 7, 8], such as WaveNet [5], its variants WaveGRU in Lyra [6], LPCNet [7] and SampleRNN [8].”