• Publications
  • Influence
Automatic Text Categorization in Terms of Genre and Author
TLDR
This paper proposes a set of style markers including analysis-level measures that represent the way in which the input text has been analyzed and capture useful stylistic information without additional cost to take full advantage of existing natural language processing (NLP) tools.
Comparative Evaluation of Various MFCC Implementations on the Speaker Verification Task
TLDR
A comparative evaluation of the presented MFCC implementations is performed on the task of text-independent speaker verification, by means of the well-known 2001 NIST SRE (speaker recognition evaluation) one-speaker detection database.
Computer-Based Authorship Attribution Without Lexical Measures
TLDR
This paper presents a fully-automated approach to the identification of the authorship of unrestricted text that excludes any lexical measure and adapts aset of style markers to the analysis of the text performed by an already existing natural language processing tool using three stylometric levels.
Text Genre Detection Using Common Word Frequencies
TLDR
It is shown that the most frequent words of the British National Corpus, representing the most Frequence of the written English language, are more reliable discriminators of text genre in comparison to the most frequently spoken words in a training corpus.
Probabilistic Novelty Detection for Acoustic Surveillance Under Real-World Conditions
TLDR
Probabilistic novelty detection can provide an accurate analysis of the audio scene to identify abnormal events and is explored as applied to acoustic surveillance of abnormal situations.
On acoustic surveillance of hazardous situations
TLDR
The present study presents a practical methodology for automatic space monitoring based solely on the perceived acoustic information based on a two stage recognition schema, each one exploiting HMMs for approximating the density function of the corresponding sound class.
Multimedia content analysis for emotional characterization of music video clips
TLDR
Using the proposed methodology, a relatively high performance (up to 90%) of affect recognition is obtained and several fusion techniques are used to combine the information extracted from the audio and video contents of music video clips.
Automatic Authorship Attribution
TLDR
The proposed set of style markers is able to distinguish texts of various authors of a weekly newspaper using multiple regression and is easily trainable and fully-automated requiring no manual text preprocessing nor sampling.
Audio Features Selection for Automatic Height Estimation from Speech
TLDR
This work investigates the applicability of various subsets of speech features, which were formed on the basis of ranking the relevance and the individual quality of numerous audio features, based on the relevance ranking of the large set of openSMILE audio descriptors.
...
...