Deep learning-based speech enhancement methods have shown promising result in recent years. However, in practical applications, the model size and computational complexity are important factors that limit their use in end-products. Therefore, in products that require real-time speech enhancement with limited resources, such as TWS headsets, hearing aids, IoT devices, etc., ultra-lightweight models are necessary. In this paper, an ultra-lightweight network FSPEN is proposed for real-time speech enhancement task. We propose a full-band and sub-band network structure for extracting global and local features, and an inter-frame path extension method that can enhance network modeling capacity while preserving complexity. Experiments demonstrate that the proposed FSPEN achieves a performance of PESQ 2.97 on the VoiceBank+Demand dataset at 89M multiply-accumulate operation per second (MAC) and 79k parameters.

The goal of target speaker extraction (TSE) is to extract the target speaker's voice from the mixture speech of multiple speakers. It needs to enroll the speech of the target speaker in advance as a reference. However, in practical applications, too long reference speech during enrollment will decrease the user's motivation to use. In this paper, we propose a Voice Extractor-Voice Extractor (VE-VE) framework for TSE task with ultra-short enrollment speech. The enrollment and voice extraction processes utilize the same RNN-based voice extractor. Speaker characteristics are carried by the RNN state. We design a network VEVEN to test the effectiveness of our proposed framework. Experiments show that it achieves a new state-of-the-art (SOTA) performance on public WSJ0-2mix datasets. Furthermore, our approach has the capacity to support ultra-short reference speech requirement. 17.7dB SI-SDRi is achieved for 0.2s reference speech.

In this paper, a low complexity design for a DFT-based MP3 multi-channel audio decoding system is proposed. By utilizing the proposed decoding system, the advanced MP3 multi-channel decoder can play high-quality multi-channel audio with low processing power. The MP3 multi-channel system is composed of two components, a parametric multi-channel decoder, and an MP3 decoder. A novel convolution-synthesis method in the transform domain can replace the pseudo-quadrature mirror filter (PQMF) module in the MP3 decoder and several small size discrete Fourier transform (DFT) modules can be used instead of a large-size DFT module in the multi-channel decoder. This combination noticeably reduces computing power without significant loss in the decoded audio signal quality. The effect of the error in the decoded audio signal is analyzed by both objective and subjective methods.

Binaural cue coding (BCC) has been introduced for compact representation of multi-channel audio. It exploits binaural cue parameters for capturing the spatial image of multi-channel audio. Recently, it has been standardized within MPEG as the name of "MPEG Surround." In this paper, we propose a sound source location cue coding (SSLCC) system for compressing multi-channel audio to be suitable at the narrow bandwidth transmission environment. To improve the compression ability of the conventional BCC, the SSLCC system utilizes the virtual source location information (VSLI) as a spatial cue parameter instead of the inter-channel level difference (ICLD) of the BCC system. Also the SSLCC system adopts enhanced pre/post processing algorithms to improve perceptual sound quality. Objective and subjective assessment results show that the proposed SSLCC system reveals better performance than the conventional BCC system.