Spatial Loss for Unsupervised Multi-channel Source Separation
원문 초록
We propose a spatial loss for unsupervised multi-channel source separation. The proposed loss exploits the duality of direction of arrival (DOA) and beamforming: the steering and beamforming vectors should be aligned for the target source, but orthogonal for interfering ones. The spatial loss encourages consistency between the mixing and demixing systems from a classic DOA estimator and a neural separator, respectively. With the proposed loss, we train the neural separators based on minimum variance distortionless response (MVDR) beamforming and independent vector analysis (IVA). We also investigate the effectiveness of combining our spatial loss and a signal loss, which uses the outputs of blind source separation as the reference. We evaluate our proposed method on synthetic and recorded (LibriCSS) mixtures. We find that the spatial loss is most effective to train IVA-based separators. For the neural MVDR beamformer, it performs best when combined with a signal loss. On synthetic mixtures, the proposed unsupervised loss leads to the same performance as a supervised loss in terms of word error rate. On LibriCSS, we obtain close to state-of-the-art performance without any labeled training data.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Towards Reliable Objective Evaluation Metrics for Generative Singing Voice Separation Models
Self-Supervised Autoencoder Network for Robust Heart Rate Extraction from Noisy Photoplethysmogram: Applying Blind Source Separation to Biosignal Analysis
Revisiting convolutive blind source separation for identifying spiking motor neuron activity: From theory to practice
Unsupervised Composable Representations for Audio
$S^3$ -- Semantic Signal Separation
Enhancing Deep Learning Models through Tensorization: A Comprehensive Survey and Framework
토론
이 논문과 연결된 포럼 글이 아직 없습니다.