BROWSE
Detail
Conference Paper
Perceptual Improvement of Deep Neural Network (DNN) Speech Coder Using Parametric and Non-parametric Density Models
Cited - time in 
Share 
Share
- Authors
- Joon Byun, Seungmin Shin, Jongmo Sung, Seungkwon Beack, Youngcheol Park
- Issue Date
- 2023-08
- Citation
- International Speech Communication Association (INTERSPEECH) 2023, pp.859-863
- Publisher
- ISCA
- Language
- English
- Type
- Conference Paper
- Abstract
- This paper proposes a method to improve the perceptual quality of an end-to-end neural speech coder using density models for bottleneck samples. Two parametric and non-parametric approaches are explored for modeling the bottleneck sample density. The first approach utilizes a sub-network to generate meanscale hyperpriors for bottleneck samples, while the second approach models the bottleneck samples using a separate subnetwork without any side information. The whole network, including the sub-network, is trained using PAM-based perceptual losses in different timescales to shape quantization noise below the masking threshold. The proposed method achieves a framedependent entropy model that enhances arithmetic coding efficiency while emphasizing perceptually relevant audio cues. Experimental results show that the proposed density model combined with PAM-based losses improves perceptual quality compared to conventional speech coders in both objective and subjective tests.
- KSP Keywords
- Audio cues, Coding efficiency, Deep neural network(DNN), End to End(E2E), Entropy model, Masking threshold, Perceptual Quality, Sample density, Speech coder, Sub-networks, Subjective test