Dictionary-Based Sparse Reconstruction of Incomplete Relative Transfer Functions

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F21%3A00008827" target="_blank" >RIV/46747885:24220/21:00008827 - isvavai.cz</a>

Výsledek na webu

<a href="https://asap.ite.tul.cz/wp-content/uploads/sites/3/2021/10/Dictionary_Based_Sparse_Reconstruction_of_Incomplete_Relative_Transfer_Functions.pdf" target="_blank" >https://asap.ite.tul.cz/wp-content/uploads/sites/3/2021/10/Dictionary_Based_Sparse_Reconstruction_of_Incomplete_Relative_Transfer_Functions.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.23919/EUSIPCO54536.2021.9616062" target="_blank" >10.23919/EUSIPCO54536.2021.9616062</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Dictionary-Based Sparse Reconstruction of Incomplete Relative Transfer Functions

Popis výsledku v původním jazyce

For estimating the relative transfer function (RTF) of a speaker from noisy multi-microphone recordings, several statistical methods have been proposed. The estimation accuracy is different over frequencies, which mostly depends on the frequency-dependent signal-to-noise ratio (SNR). Provided that the low-SNR frequencies are identified, the corresponding values of the estimated RTF can be replaced through interpolation using the frequencies with high SNR. In this study, we explore interpolation techniques based on the sparse reconstruction of an incomplete RTF which is obtained when low-SNR values are neglected. Compared to previous attempts where the approximate sparsity of the time-domain representation of RTF (relative impulse response) is exploited, in this paper, we use learned sparse dictionaries trained on dense measurements of RTFs within a confined area of the target speaker. These measurements are obtained from the recently released MIRaGe database acquired in a real room.

Název v anglickém jazyce

Dictionary-Based Sparse Reconstruction of Incomplete Relative Transfer Functions

Popis výsledku anglicky

For estimating the relative transfer function (RTF) of a speaker from noisy multi-microphone recordings, several statistical methods have been proposed. The estimation accuracy is different over frequencies, which mostly depends on the frequency-dependent signal-to-noise ratio (SNR). Provided that the low-SNR frequencies are identified, the corresponding values of the estimated RTF can be replaced through interpolation using the frequencies with high SNR. In this study, we explore interpolation techniques based on the sparse reconstruction of an incomplete RTF which is obtained when low-SNR values are neglected. Compared to previous attempts where the approximate sparsity of the time-domain representation of RTF (relative impulse response) is exploited, in this paper, we use learned sparse dictionaries trained on dense measurements of RTFs within a confined area of the target speaker. These measurements are obtained from the recently released MIRaGe database acquired in a real room.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10102 - Applied mathematics

Projekt

<a href="/cs/project/GA20-17720S" target="_blank" >GA20-17720S: Pokročilé modely směsí pro slepou extrakci signálů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

European Signal Processing Conference (EUSIPCO 2021)

ISBN

978-908279706-0

ISSN

2219-5491

e-ISSN

—

Počet stran výsledku

4

Strana od-do

1005-1009

Název nakladatele

Eurasip

Místo vydání

Ireland

Místo konání akce

Dublin

Datum konání akce

1. 1. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000764066600199