Microphone array processing for distant speech recognition: Towards real-world deployment

By Ken'ichi Kumatani, T. Arakawa, Kazumasa Yamamoto, J. McDonough, Bhiksha Raj, Rita Singh, Ivan J. Tashev. 2012

59 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.

RGB-D datasets using microsoft kinect or similar sensors: a survey (2016, neutral): “1 Kinect hardware configuration Generally, the basic version of Microsoft Kinect consists of a RGB camera, an infrared camera, an IR projector, a multi-array microphone [49] and a motorized tilt.”
An analysis of environment, microphone and data simulation mismatches in robust speech recognition (2017, unknown): “Suspicion about simulated data is common in the speech processing community, due for instance to the misleadingly high performance of direction-of-arrival based adaptive beamformers on simulated data compared to real data (Kumatani et al., 2012).”
Alternative Objective Functions for Deep Clustering (2018, result): “This is motivated by the fact that the histogram of clean STFT magnitudes in anechoic environments is similar to a Laplacian distribution (or a super-Gaussian distribution [15]), and so is the error term distribution, as suggested in our previous study [16].”
A Consolidated Perspective on Multimicrophone Speech Enhancement and Source Separation (2017, unknown): “Some studies [306] evaluate different beamformers as pre-processors for a speech recognizer via speech recognition performance metrics.”