Cascaded Cross-Module Residual Learning towards Lightweight End-to-End Speech Coding

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 only 0.9 million trainable parameters, a significantly less complex architecture than the other DNN-based codecs in the literature.

Accepted for publication in INTERSPEECH 2019

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
• Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
• Bitwise Neural Networks
• Low Bit-Rate Speech Coding with VQ-VAE and a WaveNet Decoder
• Composition of Deep and Spiking Neural Networks for Very Low Bit Rate Speech Coding
• High-Quality, Low-Delay Music Coding in the Opus Codec
• Wavenet based low rate speech coding

Cited by in corpus (5)

• Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding
• Scalable and Efficient Neural Speech Coding: A Hybrid Design
• A Dual-Staged Context Aggregation Method Towards Efficient End-To-End Speech Enhancement
• Efficient And Scalable Neural Residual Waveform Coding With Collaborative Quantization
• Source-Aware Neural Speech Coding for Noisy Speech Compression