Cocktail Party Processing via Structured Prediction

By Yuxuan Wang, Deliang Wang. 2012

46 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Deliang Wang
2. Arun Narayanan
3. Yuxuan Wang
4. Xiao-Lei Zhang
5. Bo Li
6. Qifeng Chen
7. Hakan Erdogan
8. Yi Luo

Citations in the corpus

• Speech Denoising with Deep Feature Losses (2018, background): “However, most pipelines still operate in the spectrogram domain [4, 5, 6, 7, 8, 9, 10, 11].”
• Supervised Speech Separation Based on Deep Learning: An Overview (2017, unknown): “speech separation by Wang and Wang in 2012 in two conference papers [179], [180], which were later extended to a journal version in 2013 [181].”
• Towards Scaling Up Classification-Based Speech Separation (2013, background): “Exploiting the spectrotemporal structure within the deep learning framework is promising [47].”
• Deep neural networks for single channel source separation (2013, methodology): “For example in [20], various clas-sifiers based on GMM, support vector machines, conditional random fields, and deep neural networks were used for classification.”
• Bone-conducted speech enhancement using deep denoising autoencoder (2018, methodology): “In addition to using DDAEs (Lu et al., 20132014) and deep neural networks (DNNs) (Wang and Wang, 2012; Wang and Chen, 2017; Wang et al., 2014; Xu et al., 2014), many neural network models have been developed and used for speech-enhancement applications.”
• Deep Belief Networks Based Voice Activity Detection (2013, background): “1) Can DBN work well in the complicated non-stationary noise environment with multiple noise types? [69], [70] 2) Can we improve the performance of the deep-neural-network-based VAD in the deep layers via the stacked denoising autoencoder [71], [72] or other improved stack modules with different ene”
• On Training Targets for Supervised Speech Separation (2014, methodology): “We use DNNs (multilayer perceptrons) as the discriminative learning machine, which has been shown to work well for speech separation [35], [36].”