Výsledky vyhledávání - "Goodwin, Mike"

Report

Noise-Robust DSP-Assisted Neural Pitch Estimation with Very Low Complexity

Autor: Subramani, Krishna, Valin, Jean-Marc, Buethe, Jan, Smaragdis, Paris, Goodwin, Mike

Pitch estimation is an essential step of many speech processing algorithms, including speech coding, synthesis, and enhancement. Recently, pitch estimators based on deep neural networks (DNNs) have have been outperforming well-established DSP-based t

Externí odkaz: http://arxiv.org/abs/2309.14507

Zobrazit plný text záznamu

Report

Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexity

Autor: Mustafa, Ahmed, Valin, Jean-Marc, Büthe, Jan, Smaragdis, Paris, Goodwin, Mike

GAN vocoders are currently one of the state-of-the-art methods for building high-quality neural waveform generative models. However, most of their architectures require dozens of billion floating-point operations per second (GFLOPS) to generate speec

Externí odkaz: http://arxiv.org/abs/2212.04532

Zobrazit plný text záznamu

Report

Semi-supervised Time Domain Target Speaker Extraction with Attention

Autor: Wang, Zhepei, Giri, Ritwik, Venkataramani, Shrikant, Isik, Umut, Valin, Jean-Marc, Smaragdis, Paris, Goodwin, Mike, Krishnaswamy, Arvindh

In this work, we propose Exformer, a time-domain architecture for target speaker extraction. It consists of a pre-trained speaker embedder network and a separator network based on transformer encoder blocks. We study multiple methods to combine speak

Externí odkaz: http://arxiv.org/abs/2206.09072

Zobrazit plný text záznamu