Speaker-conditioning Single-channel Target Speaker Extraction Using Conformer-based Architectures

Abstract

Target speaker extraction aims at extracting the target speaker from a mixture of multiple speakers exploiting auxiliary information about the target speaker. In this paper, we consider a complete time-domain target speaker extraction system consisting of a speaker embedder network and a speaker separator network which are jointly trained in an end-to-end learning process. We propose two different architectures for the speaker separator network which are based on the convolutional augmented transformer (conformer). The first architecture uses stacks of conformer and external feed-forward blocks (Conformer-FFN), while the second architecture uses stacks of temporal convolutional network (TCN) and conformer blocks (TCN-Conformer). Experimental results for 2-speaker mixtures, 3-speaker mixtures, and noisy mixtures of 2-speakers show that among the proposed separator networks, the TCN-Conformer significantly improves the target speaker extraction performance compared to the Conformer-FFN a

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keysinha2022speaker

Related papers

• Spectron: Target Speaker Extraction Using Conditional Transformer With Adversarial Refinement (2024)0.00
• Speaker-conditioned Target Speaker Extraction Based On Customized LSTM Cells (2021)0.00
• On Time Domain Conformer Models For Monaural Speech Separation In Noisy Reverberant Acoustic Environments (2023)5.84
• Target Confusion In End-to-end Speaker Extraction: Analysis And Approaches (2022)9.59
• Speakerfilter-pro: An Improved Target Speaker Extractor Combines The Time Domain And Frequency Domain (2020)5.84
• New Insights On Target Speaker Extraction (2022)0.00
• Target Speaker Extraction By Directly Exploiting Contextual Information In The Time-frequency Domain (2024)9.59
• Time-domain Speech Extraction With Spatial Information And Multi Speaker Conditioning Mechanism (2021)7.81