Discriminatively trained recurrent neural networks for single-channel speech separation

By Felix Weninger, John R. Hershey, Jonathan Le Roux, Björn Schuller. 2014

306 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Model Architectures, Speech & Audio, Signal Processing

How researchers see this paper

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

In Artificial Intelligence

In Model Architectures

In Speech & Audio

In Signal Processing

Citations in the corpus

Light Gated Recurrent Units for Speech Recognition (2018, background): “Several works have already highlighted the effectiveness of RNNs in various speech processing tasks, such as speech recognition [35]–[39], speech enhancement [40], speech separation [41], [42] as well as speech activity detection [43].”
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].”
Real Time Speech Enhancement in the Waveform Domain (2020, background): “Alternatively authors in [44, 35] use a recursive neural network (RNN) for speech enhancement.”
End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction (2018, background): “However, this makes their approach equivalent to conventional magnitude spectrum approximation [24], which does not perform as well as the phase-sensitive mask [25].”
Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks (2015, methodology): “This setup is based on [6].”
Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation (2015, result): “Similar observations can be found in related work using LSTM models [19], [39], where the authors observe significant improvements using recurrent neural networks compared with DNN models.”
Improving Speech Recognition by Revising Gated Recurrent Units (2017, background): “Several works have already highlighted the effectiveness of RNNs in various speech processing tasks such as speech recognition [11, 12, 13, 14, 15], speech enhancement [16], speech separation [17, 18] as well as speech activity detection [19].”
A Deep Ensemble Learning Method for Monaural Speech Separation (2016, methodology): “Weninger et al. [35] took signal approximation (SA) as the optimization objective and introduced long short-term memory (LSTM) structure into RNN which outperforms DNN and NMF based methods.”
Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR (2015, methodology): “The D(R)NN topology and training parameters were set as in [16] and [2].”
Speech Enhancement for a Noise-Robust Text-to-Speech Synthesis System Using Deep Recurrent Neural Networks (2016, background): “LSTMs have been applied in a range of speech problems [15, 16], including regression problems such as text-to-speech [17, 18, 19, 20, 21] and as previously mentioned speech enhancement [10, 8].”
Learning Complex Spectral Mapping with Gated Convolutional Recurrent Networks for Monaural Speech Enhancement (2019, methodology): “In [42], [41], [40] and [5], RNNs with long short-term memory (LSTM) are employed to perform speech enhancement.”
Multichannel Audio Source Separation With Deep Neural Networks (2016, background): “However, a framework to exploit DNNs for multichannel audio source separation is lacking.”