An algorithm to improve speech recognition in noise for hearing-impaired listeners.

By Eric W. Healy, Sarah E. Yoho, Yuxuan Wang, Deliang Wang. 2013

231 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Cognitive Neuroscience, Speech & Audio, Medical & Health AI, 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 Biomedical Engineering

In Cognitive Neuroscience

In Speech & Audio

In Medical & Health AI

In Signal Processing

Citations in the corpus

Diving into the shallows: a computational perspective on large-scale shallow learning (2017, methodology): “We show the results of gradient descent for two subsets of 10000 points from the MNIST and HINT-M datasets (see Section 6 for the description) respectively.”
A deep neural network for time-domain signal reconstruction (2015, methodology): “The proposed system significantly outperforms a recent non-negative matrix factorization based separation system in both objective speech intelligibility and quality.”
Binaural Classification for Reverberant Speech Segregation Using Deep Neural Networks (2014, unknown): “The formulation of segregation as supervised classi ﬁ cation has recently led to monaural IBM estimation algorithms producing the ﬁ rst demonstrations of speech intelligibility improvements for both normal-hearing [20] and hearing-impaired listeners [11].”
Complex Ratio Masking for Monaural Speech Separation (2015, background): “Another factor that motivates us to examine phase estimation is that supervised mask estimation has recently been shown to improve human speech intelligibility in very noisy conditions [8], [9].”
On Training Targets for Supervised Speech Separation (2014, background): “In addition, the effectiveness of IBM estimation has been exempli ﬁ ed by the recent success in improving human speech intelligibility [17], [12].”
A Regression Approach to Speech Enhancement Based on Deep Neural Networks (2015, methodology): “However, the following work presented in [28] adopted a second DNN to capture the context information to improve the separation performance.”