I
Ioannis Dologlou
Researcher at National Technical University of Athens
Publications - 52
Citations - 555
Ioannis Dologlou is an academic researcher from National Technical University of Athens. The author has contributed to research in topics: Spectral density estimation & Language model. The author has an hindex of 13, co-authored 52 publications receiving 539 citations. Previous affiliations of Ioannis Dologlou include National and Kapodistrian University of Athens & University of Paris.
Papers
More filters
Journal ArticleDOI
A novel feature transformation for vocal tract length normalization in automatic speech recognition
TL;DR: This paper proposes a method to transform acoustic models that have been trained with a certain group of speakers for use on different speech in hidden Markov model based (HMM-based) automatic speech recognition.
Journal ArticleDOI
ASR for emotional speech: Clarifying the issues and enhancing performance
Theologos Athanaselis,Stelios Bakamidis,Ioannis Dologlou,Roderick Cowie,Ellen Douglas-Cowie,Cate Cox +5 more
TL;DR: This paper shows that recognition rate for spontaneous emotionally coloured speech can be improved by using a language model based on increased representation of emotional utterances.
Journal ArticleDOI
Accurate quantification of (1)H spectra: from finite impulse response filter design for solvent suppression to parameter estimation.
TL;DR: The results show that the FIR method, using an automatic filter design scheme, slightly outperforms the HSVD method in most cases and motivates the use of the proposed method.
Journal ArticleDOI
Physical interpretation of signal reconstruction from reduced rank matrices
TL;DR: An enhanced version of a signal is obtained after subtraction of a linear combination of rank one matrices from the signal observation matrix by averaging the elements of this matrix, and a reconstructed signal is generated.
Proceedings ArticleDOI
Speech compression based on exact modeling and structured total least norm optimization
TL;DR: The approach determines the closest signal, which exactly satisfies an all-pole model of the vocal tract, which is demonstrated on a speech signal.