Pejman Mowlaee

Learn More
In conventional single-channel speech enhancement, typically the noisy spectral amplitude is modified while the noisy phase is used to reconstruct the enhanced signal. Several recent attempts have shown the effectiveness of utilizing an improved spectral phase for phase-aware speech enhancement and consequently its positive impact on the perceived speech(More)
While much progress has been made in designing robust automatic speech recognition (ASR) systems, the combination of high noise levels and reverberant room acoustics still poses a major challenge even to state-of-the-art systems. The following paper describes how robust automatic speech recognition in such difficult environments can be approached by(More)
In this paper, we present an overview on the previous and recent methods proposed to estimate a clean spectral phase from a noisy observation in the context of single-channel speech enhancement. The importance of phase estimation in speech enhancement is inspired by the recent reports on its usefulness in finding a phase-sensitive amplitude estimation. We(More)
Single-channel speech separation algorithms frequently ignore the issue of accurate phase estimation while reconstructing the enhanced signal. Instead, they directly employ the mixed-signal phase for signal reconstruction which leads to undesired traces of the interfering source in the target signal. In this paper, assuming a given knowledge of signal(More)
Many short-time Fourier transform (STFT) based single-channel speech enhancement algorithms are focused on estimating the clean speech spectral amplitude from the noisy observed signal in order to suppress the additive noise. To this end, they utilize the noisy amplitude information and the corresponding a priori and a posteriori SNRs while they employ the(More)
In this paper, the segment proportionate variable-step-size normalized least mean square (SPVS-NLMS) algorithm is proposed. Using computer simulations, we show that the proposed SPVS-NLMS algorithm performs a faster convergence compared to the segment proportionate normalized least mean square algorithm by Hongyang and Doroslovacki (2005) with a higher(More)
In this paper, we address the small vocabulary track (track 1) described in the CHiME 2 challenge dedicated to recognize utterances of a target speaker with small head movements. The utterances are recorded in a reverberant room acoustics corrupted with highly non-stationary noise sources. Such adverse noise scenario imposes a challenge to state-of-the-art(More)
One of the most important objectives in mobile communication systems is secure voice and data communication (including text, picture, video and voice) esp. in high bit rates. In this paper, a new procedure is proposed in which the intended data or voice is encrypted and modulated onto speech-like waveforms. The modulated waveforms are transmitted over the(More)
Sound quality estimation of a speech enhancement or source separation system in a realistic adverse noise scenario is a challenge. In particular, the connection between results obtained by quality metrics versus those obtained from human subjective listening tests is unknown. In this paper, as the first attempt, we present results, which examine the(More)
One of the most important objectives in mobile communication systems is secure data communication (including text, picture, video and voice) especially, in high bit rate. For this reason, in this paper, a new procedure is proposed in which the intended data or voice is modulated onto speech-like waveforms; Then the modulated waveforms are transmitted over(More)