Speech Decomposition Based on a Hybrid Speech Model and Optimal Segmentation

Alfredo Esquivel Jaramillo, Jesper Kjær Nielsen, Mads Græsbøll Christensen

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

1 Citationer (Scopus)

Abstract

In a hybrid speech model, both voiced and unvoiced components can coexist in a segment. Often, the voiced speech is regarded as the deterministic component, and the unvoiced speech and additive noise are the stochastic components. Typically, the speech signal is considered stationary within fixed segments of 20-40 ms, but the degree of stationarity varies over time. For decomposing noisy speech into its voiced and unvoiced components, a fixed segmentation may be too crude, and we here propose to adapt the segment length according to the signal local characteristics. The segmentation relies on parameter estimates of a hybrid speech model and the maximum a posteriori (MAP) and log-likelihood criteria as rules for model selection among the possible segment lengths, for voiced and unvoiced speech, respectively. Given the optimal segmentation markers and the estimated statistics, both components are estimated using linear filtering. A codebook-based approach differentiates between unvoiced speech and noise. A better extraction of the components is possible by taking into account the adaptive segmentation, compared to a fixed one. Also, a lower distortion for voiced speech and higher segSNR for both components is possible, as compared to other decomposition methods.
OriginalsprogEngelsk
TitelProc. Interspeech 2021
Publikationsdato2021
Sider1164-1168
DOI
StatusUdgivet - 2021
Begivenhed22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021 - Brno, Tjekkiet
Varighed: 30 aug. 20213 sep. 2021

Konference

Konference22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
Land/OmrådeTjekkiet
ByBrno
Periode30/08/202103/09/2021

Fingeraftryk

Dyk ned i forskningsemnerne om 'Speech Decomposition Based on a Hybrid Speech Model and Optimal Segmentation'. Sammen danner de et unikt fingeraftryk.

Citationsformater