A Two-stage Speaker Extraction Algorithm Under Adverse Acoustic Conditions Using A Single-microphone

Abstract

In this work, we present a two-stage method for speaker extraction under reverberant and noisy conditions. Given a reference signal of the desired speaker, the clean, but the still reverberant, desired speaker is first extracted from the noisy-mixed signal. In the second stage, the extracted signal is further enhanced by joint dereverberation and residual noise and interference reduction. The proposed architecture comprises two sub-networks, one for the extraction task and the second for the dereverberation task. We present a training strategy for this architecture and show that the performance of the proposed method is on par with other state-of-the-art (SOTA) methods when applied to the WHAMR! dataset. Furthermore, we present a new dataset with more realistic adverse acoustic conditions and show that our method outperforms the competing methods when applied to this dataset as well.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyeisenberg2023a

Related papers

• Multi-stage Speaker Extraction With Utterance And Frame-level Reference Signals (2020)12.54
• Robust Speaker Extraction Network Based On Iterative Refined Adaptation (2020)0.00
• Time-domain Speech Extraction With Spatial Information And Multi Speaker Conditioning Mechanism (2021)7.81
• Audio-visual Speech Separation And Dereverberation With A Two-stage Multimodal Network (2019)12.47
• Speaker Reinforcement Using Target Source Extraction For Robust Automatic Speech Recognition (2022)7.50
• Single Microphone Speaker Extraction Using Unified Time-frequency Siamese-unet (2022)3.58
• Two-stage Model And Optimal SI-SNR For Monaural Multi-speaker Speech Separation In Noisy Environment (2020)0.00
• End-to-end Multi-microphone Speaker Extraction Using Relative Transfer Functions (2025)0.00