@conference{bf3f083cc3d748f1b7bb273e769e5a97,
author = " Pasi Pertil{\"a} and  Mikko Parviainen",
abstract = "The Time Difference of Arrival (TDoA) of a sound wavefront impinging on a microphone pair carries spatial information about the source. However, captured speech typically contains dynamic non-speech interference sources and noise. Therefore, the TDoA estimates fluctuate between speech and interference. Deep Neural Networks (DNNs) have been applied for Time-Frequency (TF) masking for Acoustic Source Localization (ASL) to filter out non-speech components from a speaker location likelihood function. However, the type of TF mask for this task is not obvious. Secondly, the DNN should estimate the TDoA values, but existing solutions estimate the TF mask instead. To overcome these issues, a direct formulation of the TF masking as a part of a DNN-based ASL structure is proposed. Furthermore, the proposed network operates in an online manner, i.e., producing estimates frame-by-frame. Combined with the use of recurrent layers it exploits the sequential progression of speaker related TDoAs. Training with different microphone spacings allows model re-use for different microphone pair geometries in inference. Real-data experiments with smartphone recordings of speech in interference demonstrate the network's generalization capability.",
booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",
day = "1",
doi = "10.1109/ICASSP.2019.8682574",
keywords = "Acoustic Source Localization; Microphone Arrays; Recurrent Neural Networks; Time-Frequency Masking",
month = "5",
pages = "436--440",
publisher = "IEEE",
title = "{T}ime {D}ifference of {A}rrival {E}stimation of {S}peech {S}ignals {U}sing {D}eep {N}eural {N}etworks with {I}ntegrated {T}ime-frequency {M}asking",
year = "2019",
}