Blind Room Impulse Response Identification via Reverberant Speech Spectrum Reconstruction

2025/09/19 by Pengyu Wang, Xiaofei Li, Wang, Pengyu +1 · 1 citation
Computer Science · Engineering · Neuroscience · #Speech and Audio Processing #Advanced Adaptive Filtering Techniques #Hearing Loss and Rehabilitation

paper · pdf · doi:10.48550/arxiv.2509.15628

Abstract

This paper proposes Rec-RIR for blind room impulse response (RIR) identification. Based on the convolutive transfer function (CTF) approximation, we propose a multi-task deep neural network, which sequentially removes noise and reverberation from speech recording, and estimates the CTF filter by reverberant speech spectrum reconstruction. Subsequently, a pseudo intrusive measurement process is employed to convert the CTF filter into RIR by simulating a common intrusive RIR measurement procedure. Experimental results demonstrate that Rec-RIR achieves state-of-the-art (SOTA) performance in blind RIR identification.

Citations

• CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR
• VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identification
• Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion Models
• EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• SpatialNet: Extensively Learning Spatial Information for Multichannel Joint Speech Separation, Denoising and Dereverberation
• Towards Improved Room Impulse Response Estimation for Speech Recognition
• Speech Dereverberation with A Reverberation Time Shortening Target
• Filtered Noise Shaping for Time Domain Room Impulse Response Estimation From Reverberant Speech
• The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results
• Gaussian Error Linear Units (GELUs)
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems

Cited by

• EchoMark: Perceptual Acoustic Environment Transfer with Watermark-Embedded Room Impulse Response

Related

• Joint Blind Room Acoustic Characterization From Speech And Music Signals Using Convolutional Recurrent Neural Networks
• Towards Improved Room Impulse Response Estimation for Speech Recognition
• Filtered Noise Shaping for Time Domain Room Impulse Response Estimation From Reverberant Speech
• Impulse Response Data Augmentation and Deep Neural Networks for Blind Room Acoustic Parameter Estimation
• DARAS: Dynamic Audio-Room Acoustic Synthesis for Blind Room Impulse Response Estimation