Alternative Objective Functions for Deep Clustering
The recently proposed deep clustering framework represents a significant step towards solv-ing the cocktail party problem. This study proposes and compares a variety of alternativeobjective functions for training deep clustering networks. In addition, whereas the originaldeep clustering work relied on k-means clustering for test-time inference, here we investigateinference methods that are matched to the training objective. Furthermore, we explore theuse of an improved chimera network architecture for speech separation, which combines deepclustering with mask-inference networks in a multiobjective training scheme. The deep clus-tering loss acts as a regularizer while training the end-to-end mask inference network for bestseparation. With further iterative phase reconstruction, our best proposed method achievesa state-of-the-art 11.5 dB signal-to-distortion ratio (SDR) result on the publicly availablewsj0-2mix dataset, with a much simpler architecture than the previous best approach.
Code (1)
Tasks
ClusteringDeep ClusteringSpeech SeparationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
An Analysis of the Admissibility of the Objective Functions Applied in Evolutionary Multi-objective Clustering
A variety of clustering criteria has been applied as an objective function in Evolutionary Multi-Objective Clustering approaches (EMOCs). However, most EMOCs do not provide detailed analysis regarding the choice and usag…
ClusteringIncorporating Deep Visual Features into Multiobjective based Multi-view Search Results Clustering
Current paper explores the use of multi-view learning for search result clustering. A web-snippet can be represented using multiple views. Apart from textual view cued by both the semantic and syntactic information, a co…
ClusteringImage CaptioningMultiobjective OptimizationMULTI-VIEW LEARNING+1Beyond Spectral Clustering: Probabilistic Cuts for Differentiable Graph Partitioning
Probabilistic relaxations of graph cuts offer a differentiable alternative to spectral clustering, enabling end-to-end and online learning without eigendecompositions, yet prior work centered on RatioCut and lacked gener…
Contrastive Learninggraph partitioningExpanding the class of global objective functions for dissimilarity-based hierarchical clustering
Recent work on dissimilarity-based hierarchical clustering has led to the introduction of global objective functions for this classical problem. Several standard approaches, such as average linkage, as well as some new h…
ClusteringMinimum Average Cost Clustering
A number of objective functions in clustering problems can be described with submodular functions. In this paper, we introduce the minimum average cost criterion, and show that the theory of intersecting submodular funct…
Clustering