Single-channel Speech Separation With Auxiliary Speaker Embeddings

Abstract

We present a novel source separation model to decompose asingle-channel speech signal into two speech segments belonging to two different speakers. The proposed model is a neural network based on residual blocks, and uses learnt speaker embeddings created from additional clean context recordings of the two speakers as input to assist in attributing the different time-frequency bins to the two speakers. In experiments, we show that the proposed model yields good performance in the source separation task, and outperforms the state-of-the-art baselines. Specifically, separating speech from the challenging VoxCeleb dataset, the proposed model yields 4.79dB signal-to-distortion ratio, 8.44dB signal-to-artifacts ratio and 7.11dB signal-to-interference ratio.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliu2019single

Related papers

• End-to-end Networks For Supervised Single-channel Speech Separation (2018)0.00
• Supervised Speaker Embedding De-mixing In Two-speaker Environment (2020)0.00
• Independence-based Joint Dereverberation And Separation With Neural Source Model (2021)4.52
• New Insights On Target Speaker Extraction (2022)0.00
• Separate And Reconstruct: Asymmetric Encoder-decoder For Speech Separation (2024)0.00
• Sepit: Approaching A Single Channel Speech Separation Bound (2022)10.35
• Individualized Conditioning And Negative Distances For Speaker Separation (2022)2.26
• Single-channel Multi-speaker Separation Using Deep Clustering (2016)0.00