Denoising a signal

Patent metadata

Field	Value
Publication number	US-2019237090-A1
Application number	US-201916379667-A
Country	US
Kind code	A1
Filing date	Apr 9, 2019
Priority date	Mar 18, 2016
Publication date	Aug 1, 2019
Grant date	—

Abstract

A computer-implemented method according to one embodiment includes creating a clean dictionary, utilizing a clean signal, creating a noisy dictionary, utilizing a first noisy signal, determining a time varying projection, utilizing the clean dictionary and the noisy dictionary, denoising a second noisy signal, utilizing the time varying projection, and expanding the clean dictionary and the noisy dictionary by updating the clean dictionary and the noisy dictionary to include new clean spectro-temporal building blocks and new noisy spectro-temporal building blocks created utilizing additional clean and noisy signals.

First claim

What is claimed is:

1 . A computer-implemented method, comprising:
creating a clean dictionary, utilizing a clean signal; creating a noisy dictionary, utilizing a first noisy signal; determining a time varying projection, utilizing the clean dictionary and the noisy dictionary; denoising a second noisy signal, utilizing the time varying projection; and expanding the clean dictionary and the noisy dictionary by updating the clean dictionary and the noisy dictionary to include new clean spectro-temporal building blocks and new noisy spectro-temporal building blocks created utilizing additional clean and noisy signals.

2 . The computer-implemented method of claim 1 , wherein creating the noisy dictionary includes creating a noisy spectrogram, converting the noisy spectrogram into a plurality of noisy spectro-temporal building blocks by applying a convolutive non-negative matrix factorization (CNMF) algorithm may to the noisy spectrogram, and adding the plurality of noisy spectro-temporal building blocks to the noisy dictionary.

3 . The computer-implemented method of claim 1 , wherein determining the time varying projection includes:
generating a time activation matrix for the clean signal, utilizing the clean dictionary; generating a time activation matrix for the first noisy signal, utilizing the noisy dictionary; and comparing the time activation matrix for the clean signal and the time activation matrix for the first noisy signal to create the time varying projection.

4 . The computer-implemented method of claim 1 , wherein the first noisy signal includes a noisy speech audio signal in which one or more individuals are talking.

5 . The computer-implemented method of claim 1 , wherein creating the clean dictionary includes creating a clean spectrogram that includes a visual representation of a spectrum of frequencies in the clean signal as they vary with time.

6 . The computer-implemented method of claim 5 , wherein creating the clean dictionary includes converting the clean spectrogram into a plurality of clean spectro-temporal building blocks.

7 . The computer-implemented method of claim 6 , wherein converting the clean spectrogram into the plurality of clean spectro-temporal building blocks includes applying a convolutive non-negative matrix factorization (CNMF) algorithm to the clean spectrogram, where the CNMF identifies and creates the plurality of clean spectro-temporal building blocks within the clean spectrogram.

8 . The computer-implemented method of claim 6 , wherein creating the clean dictionary includes adding the plurality of clean spectro-temporal building blocks to the clean dictionary.

9 . The computer-implemented method of claim 1 , wherein denoising the second noisy signal includes creating a second noisy spectrogram, utilizing the second noisy signal.

10 . The computer-implemented method of claim 9 , wherein denoising the second noisy signal includes:
converting the second noisy spectrogram into a plurality of noisy spectro-temporal building blocks; adding the plurality of noisy spectro-temporal building blocks to a second noisy dictionary; generating a time activation matrix for the second noisy signal, utilizing the second noisy dictionary; and applying the time varying projection to the time activation matrix for the second noisy signal to obtain a denoised time activation matrix.

11 . The computer-implemented method of claim 10 , wherein the denoised time activation matrix is used to provide noise-robust acoustic features for automatic speech recognition (ASR).

12 . The computer-implemented method of claim 11 , wherein the denoised time activation matrix is used in combination with one or more acoustic features, selected from a group including but not limited to log-mel filterbank engeries and mel-frequency cepstral coefficients (MFCCs), to provide noise-robust acoustic features for ASR.

13 . A computer program product for denoising a signal, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a processor to cause the processor to perform a method comprising:
creating, utilizing a processor, a clean dictionary, utilizing a clean signal; creating, utilizing the processor, a noisy dictionary, utilizing a first noisy signal; determining, utilizing the processor, a time varying projection, utilizing the clean dictionary and the noisy dictionary; denoising, utilizing the processor, a second noisy signal, utilizing the time varying projection; and expanding, utilizing the processor, the clean dictionary and the noisy dictionary by updating the clean dictionary and the noisy dictionary to include new clean spectro-temporal building blocks and new noisy spectro-temporal building blocks created utilizing additional clean and noisy signals.

14 . The computer program product of claim 13 , wherein creating the noisy dictionary includes creating, utilizing the processor, a noisy spectrogram, converting, utilizing the processor, the noisy spectrogram into a plurality of noisy spectro-temporal building blocks by applying a convolutive non-negative matrix factorization (CNMF) algorithm may to the noisy spectrogram, and adding, utilizing the processor, the plurality of noisy spectro-temporal building blocks to the noisy dictionary.

15 . The computer program product of claim 13 , wherein determining the time varying projection includes:
generating, utilizing the processor, a time activation matrix for the clean signal, utilizing the clean dictionary; generating, utilizing the processor, a time activation matrix for the first noisy signal, utilizing the noisy dictionary; and comparing, utilizing the processor, the time activation matrix for the clean signal and the time activation matrix for the first noisy signal to create the time varying projection.

16 . The computer program product of claim 13 , wherein the first noisy signal includes a noisy speech audio signal in which one or more individuals are talking.

17 . The computer program product of claim 13 , wherein creating the clean dictionary includes creating, utilizing the processor, a clean spectrogram that includes a visual representation of a spectrum of frequencies in the clean signal as they vary with time.

18 . The computer program product of claim 13 , wherein creating the clean dictionary includes converting, utilizing the processor, the clean signal into a plurality of clean spectro-temporal building blocks.

19 . The computer program product of claim 18 , wherein converting the clean signal into the plurality of clean spectro-temporal building blocks includes applying, utilizing the processor, a convolutive non-negative matrix factorization (CNMF) algorithm to the clean signal, where the CNMF identifies and creates the plurality of clean spectro-temporal building blocks within the clean signal.

20 . A system, comprising:
a processor, and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor, the logic being configured to: create a clean dictionary, utilizing a clean signal; create a noisy dictionary, utilizing a first noisy signal; determine a time varying projection, utilizing the clean dictionary and the noisy dictionary; denoise a second noisy signal, utilizing the time varying projection; and expand the clean dictionary and the n

Assignees

• IBM

Inventors

• Dimitriadis Dimitrios B
• Thomas Samuel
• Vaz Colin C

Classifications

• G10L21/0208 Primary

  Noise filtering · CPC title