Saved in:
Bibliographic Details
Main Authors: Wang, Yabo, Yang, Bing, Li, Xiaofei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.21900
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912607946932224
author Wang, Yabo
Yang, Bing
Li, Xiaofei
author_facet Wang, Yabo
Yang, Bing
Li, Xiaofei
contents IPDnet is our recently proposed real-time sound source localization network. It employs alternating full-band and narrow-band (B)LSTMs to learn the full-band correlation and narrow-band extraction of DP-IPD, respectively, which achieves superior performance. However, processing narrow-band independently incurs high computational complexity and the limited scalability of LSTM layers constrains the localization accuracy. In this work, we extend IPDnet to IPDnet2, improving both localization accuracy and efficiency. IPDnet2 adapts the oSpatialNet as the backbone to enhance spatial cues extraction and provide superior scalability. Additionally, a simple yet effective frequency-time pooling mechanism is proposed to compress frequency and time resolutions and thus reduce computational cost, and meanwhile not losing localization capability. Experimental results show that IPDnet2 achieves comparable localization performance with IPDnet while only requiring less than 2\% of its computation cost. Moreover, the proposed network achieves state-of-the-art SSL performance by scaling up the model size while still maintaining relatively low complexity.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21900
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IPDnet2: an efficient and improved inter-channel phase difference estimation network for sound source localization
Wang, Yabo
Yang, Bing
Li, Xiaofei
Audio and Speech Processing
IPDnet is our recently proposed real-time sound source localization network. It employs alternating full-band and narrow-band (B)LSTMs to learn the full-band correlation and narrow-band extraction of DP-IPD, respectively, which achieves superior performance. However, processing narrow-band independently incurs high computational complexity and the limited scalability of LSTM layers constrains the localization accuracy. In this work, we extend IPDnet to IPDnet2, improving both localization accuracy and efficiency. IPDnet2 adapts the oSpatialNet as the backbone to enhance spatial cues extraction and provide superior scalability. Additionally, a simple yet effective frequency-time pooling mechanism is proposed to compress frequency and time resolutions and thus reduce computational cost, and meanwhile not losing localization capability. Experimental results show that IPDnet2 achieves comparable localization performance with IPDnet while only requiring less than 2\% of its computation cost. Moreover, the proposed network achieves state-of-the-art SSL performance by scaling up the model size while still maintaining relatively low complexity.
title IPDnet2: an efficient and improved inter-channel phase difference estimation network for sound source localization
topic Audio and Speech Processing
url https://arxiv.org/abs/2509.21900