A tutorial review on entropy-based handcrafted feature extraction for information fusion

RC Guido - Information Fusion, 2018 - Elsevier
Entropy (H) is the main subject of this article, concisely written to serve as a tutorial
introducing two feature extraction (FE) methods for usage in digital signal processing (DSP) …

[PDF][PDF] Convolutional Neural Network Based Speaker De-Identification.

F Bahmaninezhad, C Zhang, JHL Hansen - Odyssey, 2018 - isca-archive.org
Concealing speaker identity in speech signals refers to the task of speaker de-identification,
which helps protect the privacy of a speaker. Although, both linguistic and paralinguistic …

Speech variability: A cross-language study on acoustic variations of speaking versus untrained singing

JHL Hansen, M Bokshi… - The Journal of the …, 2020 - pmc.ncbi.nlm.nih.gov
Speech production variability introduces significant challenges for existing speech
technologies such as speaker identification (SID), speaker diarization, speech recognition …

Jointly aligning and predicting continuous emotion annotations

S Khorram, MG McInnis… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Time-continuous dimensional descriptions of emotions (eg, arousal, valence) allow
researchers to characterize short-time changes and to capture long-term trends in emotion …

Trainable time war**: Aligning time-series in the continuous-time domain

S Khorram, MG McInnis… - ICASSP 2019-2019 IEEE …, 2019 - ieeexplore.ieee.org
DTW calculates the similarity or alignment between two signals, subject to temporal war**.
However, its computational complexity grows exponentially with the number of time-series …

Soft context clustering for F0 modeling in HMM-based speech synthesis

S Khorram, H Sameti, S King - EURASIP Journal on Advances in Signal …, 2015 - Springer
This paper proposes the use of a new binary decision tree, which we call a soft decision
tree, to improve generalization performance compared to the conventional 'hard'decision …

[KSIĄŻKA][B] Advancements in Domain Adaptation for Speaker Recognition and Effective Speaker De-Identification

F Bahmaninezhad - 2020 - search.proquest.com
Recent advancements in machine learning and artificial intelligence have significantly
impacted the way humans interact with machines. Voice assistant based solutions are …

[PDF][PDF] l Model for S

B Fahimeh - soheil-khorram.github.io
eil Khorram partment of ses an innovativ corporated in a HMM)-based sp refers to the f
rrelated. The p sian potential fu es in a latent s meter estimation ugh the Broyde zing output …

Context-dependent deterministic plus stochastic model

S Khorram, H Sameti… - 2014 12th International …, 2014 - ieeexplore.ieee.org
This article proposes a method to improve the performance of deterministic plus stochastic
model (DSM-) based feature extraction by integrating the contextual information. One …

[CYTOWANIE][C] Designing and recording a speech database for Persian TTS systems