Deep neural network Based Low-latency Speech Separation with Asymmetric analysis-Synthesis Window Pair

2021/06/22 by Shanshan Wang, Wang, Shanshan, Gaurav Naithani +5 · 1 citation
Computer Science · Engineering · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #Ultrasonics and Acoustic Wave Propagation #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2106.11794

openalex publication_date 2021/06/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Time-frequency masking or spectrum prediction computed via short symmetric windows are commonly used in low-latency deep neural network (DNN) based source separation. In this paper, we propose the usage of an asymmetric analysis-synthesis window pair which allows for training with targets with better frequency resolution, while retaining the low-latency during inference suitable for real-time speech enhancement or assisted hearing applications. In order to assess our approach across various model types and datasets, we evaluate it with both speaker-independent deep clustering (DC) model and a speaker-dependent mask inference (MI) model. We report an improvement in separation performance of up to 1.5 dB in terms of source-to-distortion ratio (SDR) while maintaining an algorithmic latency of 8 ms.

Cited by

• Scaling Context Requires Rethinking Attention

Related

• Low-Latency Deep Clustering For Speech Separation
• Deep neural network based speech separation optimizing an objective estimator of intelligibility for low latency applications
• Real-time Speech Enhancement and Separation with a Unified Deep Neural Network for Single/Dual Talker Scenarios
• Exploring Tradeoffs in Models for Low-latency Speech Enhancement
• X-DC: Explainable Deep Clustering based on Learnable Spectrogram Templates