Document detail
ID
oai:arXiv.org:2409.06136
Topic
Computer Science - Sound Electrical Engineering and Systems...Author
Wang, Yiwen Yuan, Zeyu Wu, XihongCategory
Computer Science
Year
2024
listing date
12/18/2024
Keywords
model embeddings extractionAbstract
Target speech extraction (TSE) focuses on extracting the speech of a specific target speaker from a mixture of signals.
Existing TSE models typically utilize static embeddings as conditions for extracting the target speaker's voice.
However, the static embeddings often fail to capture the contextual information of the extracted speech signal, which may limit the model's performance.
We propose a novel dynamic embedding causal target speech extraction model to address this limitation.
Our approach incorporates an autoregressive mechanism to generate context-dependent embeddings based on the extracted speech, enabling real-time, frame-level extraction.
Experimental results demonstrate that the proposed model enhances short-time objective intelligibility (STOI) and signal-to-distortion ratio (SDR), offering a promising solution for target speech extraction in challenging scenarios.
;Comment: The experimental design and results contain errors, and I would like to withdraw the paper
Wang, Yiwen,Yuan, Zeyu,Wu, Xihong, 2024, DENSE: Dynamic Embedding Causal Target Speech Extraction
Projection-Specific Heterogeneity of the Axon Initial Segment of Pyramidal Neurons in the Prelimbic Cortex
heterogeneity projection-specific
