상세정보
학술대회
Coded Speech Enhancement Using Neural Network-Based Vector-Quantized Residual Features
- 저자
- 천영주, 황수중, 한상욱, 장인선, 신종원
- 발행일
- 202109
- 출처
- International Speech Communication Association (INTERSPEECH) 2021, pp.1664-1668
- 협약과제
- 21ZH1200, 초실감 입체공간 미디어·콘텐츠 원천기술연구, 이태진
- 초록
- Various approaches have been proposed to improve the quality of the speech coded at low bitrates. Recently, deep neural networks have also been used for speech coding, providing a high quality of speech with low bitrates. Although designing an entire codec with neural networks may be more effective, backward compatibility with the existing codecs can be desirable so that the systems with the legacy codec can still decode the coded bitstream. In this paper, we propose to generate side information based on neural networks for an existing codec and enhance the decoded speech with another neural networks using the side information. The vector-quantization variational autoencoder (VQ-VAE) is applied to generate vector-quantized side information and reconstruct the residual features, which are the difference between the features extracted from the original and decoded signals. The post-processor in the decoder side, which is another neural network, takes the decoded signal of the main codec and the reconstructed residual features to estimate the features for the original signal. Experimental results show that the proposed method can significantly improve the quality of the enhanced signals with additional bitrate of 0.6 kbps for two of the implementations of the high-efficiency advanced audio coding (HE-AAC) v1.
- KSP 제안 키워드
- Audio coding, Backward compatibility, Deep neural network(DNN), Post-processor, Speech coding, Various approaches, high efficiency, low bit rate, network-based, side information, speech enhancement