Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR

By Felix Weninger, Hakan Erdogan, Shinji Watanabe, Emmanuel Vincent, Jonathan Le Roux, John R. Hershey, Björn Schuller. 2015

650 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Optimization & Training, 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 Optimization & Training

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].”
SEANet: A Multi-modal Speech Enhancement Network (2020, methodology): “Early works include methods based on denoising auto-encoders [8] and recurrent models [9].”
Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition (2017, background): “networks have also been investigated in the literature for enhancement, such as denoising autoencoders [12], convolution networks [13] and recurrent networks [14].”
A Wavenet for Speech Denoising (2017, methodology): “e two term loss towards conserving the energy of the original mixture: E m^ t E m t . Previous work considered energy-conservative pipelines: for source separation [23, 3], or for speech enhancement [34]. Finally, note that the ﬁrst-term of the proposed loss corresponds to the standard L1 loss – tha”
SEGAN: Speech Enhancement Generative Adversarial Network (2017, background): “In [15] and [16], noise features are estimated and included in the input features of deep neural networks.”
Real Time Speech Enhancement in the Waveform Domain (2020, background): “Over the last years, there has been a growing interest towards DNN based methods for speech enhancement [34, 35, 36, 37, 20, 38, 39, 22, 40, 7, 41, 8, 42, 21, 37].”
Looking to listen at the cocktail party (2018, neutral): “Wang and Chen [2017] give a comprehensive overview of recent audio-only methods based on deep learning that tackle both speech denoising [Erdogan et al. 2015; Weninger et al. 2015] and speech separation tasks.”
Permutation invariant training of deep models for speaker-independent multi-talker speech separation (2016, background): “Typieally, networks are trained based on parallel sets of mixtures and their constituent target sources [19, 20, 21, 22].”
End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction (2018, background): “The real component is equivalent to the earlier proposed phase-sensitive mask [21], which contains patterns clearly predictable from energy-based features [21, 25].”
Improving GANs for Speech Enhancement (2020, background): “Speech enhancement can serve as a frontend to improve performance of an automatic speech recognition system [3].”
Supervised Speech Separation Based on Deep Learning: An Overview (2017, neutral): “In [185], [186], 752 RNNs with LSTM were used for speech enhancement and its 753 application to robust ASR, where training aims for signal ap- 754 proximation (see Section III.”
Single-Channel Multi-talker Speech Recognition with Permutation Invariant Training (2017, result): “In the simplest architecture, which is denoted as Arch#1 and illustrated in Figure 1(a), feature separation can be considered as a multi-class regression problem, similar to many previous works [29], [30], [31], [32], [33], [34].”
Cycle-Consistent Speech Enhancement (2018, methodology): “The mask learning approach [9, 10, 11] was proposed to estimate the ideal ratio mask or ideal binary mask based on noisy input features using a DNN.”