Multiframe maximum a posteriori estimators for single‐microphone speech enhancement
Abstract Multiframe maximum a posteriori (MAP) estimators are applied to a single‐microphone noise reduction problem. Several attempts have been made to exploit the interframe correlation (IFC) between speech coefficients in the short‐time Fourier transform domain. In a noise‐reduction algorithm, al...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Jezik: | English |
| Izdano: |
Wiley
2021-09-01
|
| Serija: | IET Signal Processing |
| Teme: | |
| Online dostop: | https://doi.org/10.1049/sil2.12045 |
| _version_ | 1826820184952799232 |
|---|---|
| author | Raziyeh Ranjbaryan Hamid Reza Abutalebi |
| author_facet | Raziyeh Ranjbaryan Hamid Reza Abutalebi |
| author_sort | Raziyeh Ranjbaryan |
| collection | DOAJ |
| description | Abstract Multiframe maximum a posteriori (MAP) estimators are applied to a single‐microphone noise reduction problem. Several attempts have been made to exploit the interframe correlation (IFC) between speech coefficients in the short‐time Fourier transform domain. In a noise‐reduction algorithm, all available information of recorded signals should be optimally utilized in the estimation process. Single‐microphone multiframe minimum variance distortion‐less response and single‐microphone multiframe Wiener filters (MFWFs) have been presented in this approach. Incorporating the concept of IFC in the MAP estimator leads to multiframe MAP estimators in a single‐microphone case. In each time‐frequency unit, the current and a finite number of past noisy signals are utilized to develop the estimators. A complex factor is adopted to model the IFC between speech signals, which allows the application of multiframe MAP estimators. The noise reduction performance is compared for the proposed estimators with the joint MAP estimator (which ignores the correlation between successive frames) and benchmark MFWFs and speech‐distortion weighted interframe Wiener filters for different input noise types. These evaluations verify that the proposed methods exhibit good performance. |
| first_indexed | 2024-03-09T07:22:02Z |
| format | Article |
| id | doaj.art-88a230efc92b4142a1c07123edf2e3e7 |
| institution | Directory Open Access Journal |
| issn | 1751-9675 1751-9683 |
| language | English |
| last_indexed | 2025-02-16T06:24:36Z |
| publishDate | 2021-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Signal Processing |
| spelling | doaj.art-88a230efc92b4142a1c07123edf2e3e72025-02-03T06:47:26ZengWileyIET Signal Processing1751-96751751-96832021-09-0115746748110.1049/sil2.12045Multiframe maximum a posteriori estimators for single‐microphone speech enhancementRaziyeh Ranjbaryan0Hamid Reza Abutalebi1Electrical Engineering Department Yazd University Yazd IranElectrical Engineering Department Yazd University Yazd IranAbstract Multiframe maximum a posteriori (MAP) estimators are applied to a single‐microphone noise reduction problem. Several attempts have been made to exploit the interframe correlation (IFC) between speech coefficients in the short‐time Fourier transform domain. In a noise‐reduction algorithm, all available information of recorded signals should be optimally utilized in the estimation process. Single‐microphone multiframe minimum variance distortion‐less response and single‐microphone multiframe Wiener filters (MFWFs) have been presented in this approach. Incorporating the concept of IFC in the MAP estimator leads to multiframe MAP estimators in a single‐microphone case. In each time‐frequency unit, the current and a finite number of past noisy signals are utilized to develop the estimators. A complex factor is adopted to model the IFC between speech signals, which allows the application of multiframe MAP estimators. The noise reduction performance is compared for the proposed estimators with the joint MAP estimator (which ignores the correlation between successive frames) and benchmark MFWFs and speech‐distortion weighted interframe Wiener filters for different input noise types. These evaluations verify that the proposed methods exhibit good performance.https://doi.org/10.1049/sil2.12045maximum likelihood estimationmicrophonessignal denoisingspeech enhancementWiener filters |
| spellingShingle | Raziyeh Ranjbaryan Hamid Reza Abutalebi Multiframe maximum a posteriori estimators for single‐microphone speech enhancement IET Signal Processing maximum likelihood estimation microphones signal denoising speech enhancement Wiener filters |
| title | Multiframe maximum a posteriori estimators for single‐microphone speech enhancement |
| title_full | Multiframe maximum a posteriori estimators for single‐microphone speech enhancement |
| title_fullStr | Multiframe maximum a posteriori estimators for single‐microphone speech enhancement |
| title_full_unstemmed | Multiframe maximum a posteriori estimators for single‐microphone speech enhancement |
| title_short | Multiframe maximum a posteriori estimators for single‐microphone speech enhancement |
| title_sort | multiframe maximum a posteriori estimators for single microphone speech enhancement |
| topic | maximum likelihood estimation microphones signal denoising speech enhancement Wiener filters |
| url | https://doi.org/10.1049/sil2.12045 |
| work_keys_str_mv | AT raziyehranjbaryan multiframemaximumaposterioriestimatorsforsinglemicrophonespeechenhancement AT hamidrezaabutalebi multiframemaximumaposterioriestimatorsforsinglemicrophonespeechenhancement |