A
Alexandros Potamianos
Researcher at National Technical University of Athens
Publications - 229
Citations - 7087
Alexandros Potamianos is an academic researcher from National Technical University of Athens. The author has contributed to research in topics: Semantic similarity & Language model. The author has an hindex of 42, co-authored 216 publications receiving 6370 citations. Previous affiliations of Alexandros Potamianos include University of Crete & Alcatel-Lucent.
Papers
More filters
Journal ArticleDOI
Acoustics of children's speech: developmental changes of temporal and spectral parameters.
TL;DR: The results confirm that the reduction in magnitude and within-subject variability of both temporal and spectral acoustic parameters with age is a major trend associated with speech development in normal children, and support the hypothesis of uniform axial growth of the vocal tract for male speakers.
Journal ArticleDOI
A comparison of the energy operator and the Hilbert transform approach to signal and speech demodulation
TL;DR: Comparisons of two fundamentally different approaches for demodulation of arbitrary signals and of speech resonances modeled by AM-Fm signals provide strong evidence that the estimation errors of the smoothed energy operator approach are similar to the Hilbert transform approach for speech applications, but smaller for communication applications.
Journal ArticleDOI
Multimodal Saliency and Fusion for Movie Summarization Based on Aural, Visual, and Textual Attention
Georgios Evangelopoulos,Athanasia Zlatintsi,Alexandros Potamianos,Petros Maragos,Konstantinos Rapantzikos,Georgios Skoumas,Yannis Avrithis +6 more
TL;DR: Detecting of attention-invoking audiovisual segments is formulated in this work on the basis of saliency models for the audio, visual, and textual information conveyed in a video stream, forming the basis for a generic, bottom-up video summarization algorithm.
Journal ArticleDOI
Robust recognition of children's speech
TL;DR: Through an analysis of age-related acoustic characteristics of children's speech in the context of automatic speech recognition (ASR), effects such as frequency scaling of spectral envelope parameters are demonstrated and speaker normalization algorithm that combines frequency warping and model transformation is shown to reduce acoustic variability.
Journal ArticleDOI
Creating conversational interfaces for children
TL;DR: Issues in ASR of children's speech are introduced by an analysis of developmental changes in the spectral and temporal characteristics of the speech signal using data obtained from 456 children, ages five to 18 years.