Výsledky vyhledávání - "Sinha, Ragini"

Report

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

Autor: Sinha, Ragini, Tammen, Marvin, Rollwage, Christian, Doclo, Simon

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 consisti

Externí odkaz: http://arxiv.org/abs/2205.13851

Zobrazit plný text záznamu

Report

Reduction of Subjective Listening Effort for TV Broadcast Signals with Recurrent Neural Networks

Autor: Westhausen, Nils L., Huber, Rainer, Baumgartner, Hannah, Sinha, Ragini, Rennies, Jan, Meyer, Bernd T.

Listening to the audio of TV broadcast signals can be challenging for hearing-impaired as well as normal-hearing listeners, especially when background sounds are prominent or too loud compared to the speech signal. This can result in a reduced satisf

Externí odkaz: http://arxiv.org/abs/2111.01914

Zobrazit plný text záznamu

Report

Speaker-conditioned Target Speaker Extraction based on Customized LSTM Cells

Autor: Sinha, Ragini, Tammen, Marvin, Rollwage, Christian, Doclo, Simon

Speaker-conditioned target speaker extraction systems rely on auxiliary information about the target speaker to extract the target speaker signal from a mixture of multiple speakers. Typically, a deep neural network is applied to isolate the relevant

Externí odkaz: http://arxiv.org/abs/2104.04234

Zobrazit plný text záznamu