ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Scalable and Efficient Neural Speech Coding: A Hybrid Design
Cited 10 time in scopus Download 3 time Share share facebook twitter linkedin kakaostory
저자
Kai Zhen, 성종모, 이미숙, 백승권, 김민제
발행일
202112
출처
IEEE/ACM Transactions on Audio, Speech, and Language Processing, v.30, pp.12-25
ISSN
2329-9290
출판사
ACM, IEEE
DOI
https://dx.doi.org/10.1109/TASLP.2021.3129353
협약과제
21HH7300, [통합과제] 초실감 테라미디어를 위한 AV부호화 및 LF미디어 원천기술 개발, 최진수
초록
We present a scalable and efficient neural waveform coding system for speech compression. We formulate the speech coding problem as an autoencoding task, where a convolutional neural network (CNN) performs encoding and decoding as a neural waveform codec (NWC) during its feedforward routine. The proposed NWC also defines quantization and entropy coding as a trainable module, so the coding artifacts and bitrate control are handled during the optimization process. We achieve efficiency by introducing compact model components to NWC, such as gated residual networks and depthwise separable convolution. Furthermore, the proposed models are with a scalable architecture, cross-module residual learning (CMRL), to cover a wide range of bitrates. To this end, we employ the residual coding concept to concatenate multiple NWC autoencoding modules, where each NWC module performs residual coding to restore any reconstruction loss that its preceding modules have created. CMRL can scale down to cover lower bitrates as well, for which it employs linear predictive coding (LPC) module as its first autoencoder. The hybrid design integrates LPC and NWC by redefining LPC's quantization as a differentiable process, making the system training an end-to-end manner. The decoder of proposed system is with either one NWC (0.12 million parameters) in low to medium bitrate ranges (12 to 20 kbps) or two NWCs in the high bitrate (32 kbps). Although the decoding complexity is not yet as low as that of conventional speech codecs, it is significantly reduced from that of other neural speech coders, such as a WaveNet-based vocoder. For wide-band speech coding quality, our system yields comparable or superior performance to AMR-WB and Opus on TIMIT test utterances at low and medium bitrates. The proposed system can scale up to higher bitrates to achieve near transparent performance.
KSP 제안 키워드
AMR-WB, Coding system, Convolution neural network(CNN), Cross-module, Encoding and decoding, End to End(E2E), Entropy Coding, Hybrid design, Model components, Residual Network, Residual coding