Generalization of Multi-Channel Linear Prediction Methods for Blind MIMO Impulse Response Shortening

By Takuya Yoshioka, Tomohiro Nakatani. 2012

274 citations recorded by the source corpus.

Subfields: Computational Mechanics, 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 Computational Mechanics

In Signal Processing

Citations in the corpus

Time-Frequency Masking in the Complex Domain for Speech Dereverberation and Denoising (2017, positive): “Yoshioka and Nakatani [44] use weighted error prediction to develop a filter that removes late reverberation.”
A Review of Speaker Diarization: Recent Advances with Deep Learning (2021, methodology): “One of the most widely used techniques is the weighted prediction error (WPE) based dereverberation [89, 90, 91].”
The USTC-iFlytek systems for CHiME-5 Challenge (2018, methodology): “Meanwhile, we apply a conventional multi-channel noise reduction using log-spectral amplitude [2] which is based on generalized weighted prediction error (GWPE) [3] and independent vector analysis (IVA) [4].”
LINEAR PREDICTION-BASED DEREVERBERATION WITH ADVANCED SPEECH ENHANCEMENT AND RECOGNITION TECHNOLOGIES FOR THE REVERB CHALLENGE (2014, methodology): “[5] derives the following objective function, which reduces to the single-channel objective function (2) when M = 1:”
NARA-WPE: A Python package for weighted prediction error dereverberation in Numpy and Tensorflow for online and offline processing (2018, methodology): “The heuristic context of (δ+1+δ) frames helps to improve the variance estimate in this iterative scheme [3].”
The NTT CHiME-3 system: Advances in speech enhancement and recognition for mobile multi-microphone devices (2015, methodology): “…to these improvements, our system makes use of advanced techniques, such as multi-microphone training [9], weighted prediction error-based (WPE) dereverberation [10, 11], one-pass recurrent neural network language model (RNN-LM) decoding [12], and system combination with cross-adaptation [13].”
Speech dereverberation and denoising using complex ratio masks (2017, background): “Although complex domain dereverberation is presented in [16, 17], their approach is unsupervised and does not handle background noise.”
Speech Processing for Digital Home Assistants: Combining signal processing with deep-learning techniques (2019, background): “116 IEEE SIGNAL PROCESSING MAGAZINE | November 2019 | allowing further multichannel processing, such as beamforming, to follow it [10], [11].”
Front-end processing for the CHiME-5 dinner party scenario (2018, methodology): “Additionally, we apply multi-channel dereverberation based on the Weighted Prediction Error (WPE) principle [14, 15, 16] as Both authors contributed equally. a preprocessing step for GSS.”
An Investigation into the Effectiveness of Enhancement in ASR Training and Test for Chime-5 Dinner Party Transcription (2019, methodology): “Regarding the first stage, the multiple input multiple output version of the Weighted Prediction Error (WPE) method was used for dereverberation (M inputs and M outputs) [15, 16](2) and,”