A network of deep neural networks for Distant Speech Recognition

By Mirco Ravanelli, Philemon Brakel, Maurizio Omologo, Yoshua Bengio. 2017

41 citations recorded by the source corpus.

Despite the remarkable progress recently made in distant speech recognition, state-of-the-art technology still suffers from a lack of robustness, especially when adverse acoustic conditions characterized by non-stationary noises and reverberation are met.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering, 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 Electrical and Electronic Engineering

In Speech & Audio

In Signal Processing

Citations in the corpus

Light Gated Recurrent Units for Speech Recognition (2018, background): “nique is effective both to improve the system performance and to speed-up the training procedure [20], [22], [37], [49], [50].”
Learning Speaker Representations with Mutual Information (2018, background): “Deep learning has shown remarkable success in numerous speech tasks, including speech recognition [1–4] and speaker recognition [5, 6].”
Deep Learning for Environmentally Robust Speech Recognition (2017, background): “To this end, a novel architecture was proposed in Ravanelli et al. (2017).”
Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding (2018, methodology): “We evaluated it against 60 the state-of-the-art DNN-HMM-based ASR system Kaldi [25], which is one of the most popular 61 toolchains for ASR among researchers [26, 27, 28, 29, 23] and is also used in commercial products 62 such as Amazon’s Echo/Alexa and by IBM and Microsoft [30, 31].”
Speaker Recognition from Raw Waveform with SincNet (2018, background): “Deep learning has shown remarkable success in numerous speech tasks [4–8], including recent studies in speaker recognition [9, 10].”
The Pytorch-kaldi Speech Recognition Toolkit (2018, unknown): “It is also possible to employ models based on an ecosystem of neural networks performing different tasks, as done in the context of joint training between speech enhancement and speech recognition [28, 29] or in the context of the recently-proposed cooperative networks of deep neural networks [30].”
Interpretable Convolutional Filters with SincNet (2018, background): “Moreover, this work not only considers standard close-talking speech recognition, but it also extends the validation of SincNet to distant-talking speech recognition [54, 55, 56].”