Cascaded Cross-module Residual Learning Towards Lightweight End-to-end Speech Coding
2019 · Kai Zhen, Jongmo Sung, Mi Suk Lee, et al.
Abstract
Speech codecs learn compact representations of speech signals to facilitate data transmission. Many recent deep neural network (DNN) based end-to-end speech codecs achieve low bitrates and high perceptual quality at the cost of model complexity. We propose a cross-module residual learning (CMRL) pipeline as a module carrier with each module reconstructing the residual from its preceding modules. CMRL differs from other DNN-based speech codecs, in that rather than modeling speech compression problem in a single large neural network, it optimizes a series of less-complicated modules in a two-phase training scheme. The proposed method shows better objective performance than AMR-WB and the state-of-the-art DNN-based speech codec with a similar network architecture. As an end-to-end model, it takes raw PCM signals as an input, but is also compatible with linear predictive coding (LPC), showing better subjective quality at high bitrates than AMR-WB and OPUS. The gain is achieved by using onl
Authors
(none)
Tags
Stats
Related papers
- Efficient And Scalable Neural Residual Waveform Coding With Collaborative Quantization (2020)8.60
- Msr-codec: A Low-bitrate Multi-stream Residual Codec For High-fidelity Speech Generation With Information Disentanglement (2025)2.35
- Neural Feature Predictor And Discriminative Residual Coding For Low-bitrate Speech Coding (2022)6.77
- Optimizing Neural Speech Codec For Low-bitrate Compression Via Multi-scale Encoding (2024)0.00
- Speaking From Coarse To Fine: Improving Neural Codec Language Model Via Multi-scale Speech Coding And Generation (2024)3.58
- ESC: Efficient Speech Coding With Cross-scale Residual Vector Quantized Transformers (2024)5.84
- Language-codec: Bridging Discrete Codec Representations And Speech Language Models (2024)4.64
- Composition Of Deep And Spiking Neural Networks For Very Low Bit Rate Speech Coding (2016)9.92