Jorge A. Gurlekian
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Jorge A. Gurlekian has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Humberto Maximiliano Torres
Laboratorio de Investigaciones Sensoriales, INIGEM, CONICET-Universidad de Buenos Aires
6 shared publications - Diego Alexis Evin
Centro de Investigación y Transferencia en Acústica (CINTRA), CONICET, Universidad Tecnológica Nacional Facultad Regional Córdoba, Córdoba, Argentina
2 shared publications - María Mercedes Güemes
Instituto de Ciencias de la Salud, UNO - CONICET & Instituto de Filología y Literaturas Hispánicas "Dr. Amado Alonso”, UBA
2 shared publications Pedro Univaso
Argentine Catholic University (UCA), BlackVox Company, Ciudad de Buenos Aires, Argentina
2 shared publicationsBárbara Sampedro
Consejo Nacional de Investigaciones Científicas y Técnicas, Argentina
1 shared publicationChristian Cossio-Mercado
Laboratorio de Investigaciones Sensoriales LIS-INIGEM
1 shared publication
Latest Publications
- Open Access
- 31 March 2025
- Published by Pontificia Universidad Catolica de Chile in Onomázein
- No. 67,p. 102-123
Normalización del texto “Los sentidos” y su aplicación en la evaluación de habla continua
The aim of this paper is to present “Los sentidos” passage, designed to provide a contextual sample for speech and voice evaluation. The passage includes specific text attributes: proper length, words of increasing syllabic complexity, prosodic contrasts, words containing all Spanish phonemes, among others, targeted to assess a diversity of speech disorders. The text presents academic and clinical interest in two major fields: linguistics and speech therapy. Together with the passage, the analysis of supra-segmental features obtained from normal voices from Buenos Aires and Córdoba, two main linguistic Argentinean regions, are compared. As an example of its utility in examining motor speech performance, CPPS was measured in voices without disorders for text normalization. Results demonstrated that the passage's length did not affect CPPS measures in comparison with a short reading passage used as a control variable.
- 31 March 2025
- Published by Pontificia Universidad Catolica de Chile in Onomázein
- No. 67,p. 102-123
Open AccessNormalización del texto “Los sentidos” y su aplicación en la evaluación de habla continua
The aim of this paper is to present “Los sentidos” passage, designed to provide a contextual sample for speech and voice evaluation. The passage includes specific text attributes: proper length, words of increasing syllabic complexity, prosodic contrasts, words containing all Spanish phonemes, among others, targeted to assess a diversity of speech disorders. The text presents academic and clinical interest in two major fields: linguistics and speech therapy. Together with the passage, the analysis of supra-segmental features obtained from normal voices from Buenos Aires and Córdoba, two main linguistic Argentinean regions, are compared. As an example of its utility in examining motor speech performance, CPPS was measured in voices without disorders for text normalization. Results demonstrated that the passage's length did not affect CPPS measures in comparison with a short reading passage used as a control variable.
- 21 March 2022
- Published by Elsevier in Journal of Voice
- Vol. 38 (4) , 816-825.e3
Determining the Likelihood Ratio From Perceptual Attributes of Voice
- 21 March 2022
- Published by Elsevier in Journal of Voice
- Vol. 38 (4) , 816-825.e3
Determining the Likelihood Ratio From Perceptual Attributes of Voice
- 21 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 29 (23299290) , 1977-1986
F0 Perturbation Due to Articulatory Movements: Filtering, Characterization and Applications
This paper addresses the issue of local disturbances in the fundamental frequency contour of speech, caused by the articulation of voiced/unvoiced consonant phonemes. Depending on the intended use of the F0 contour, these disturbances are usually eliminated by a filtering, smoothing or stylization procedure. These procedures that seek to preserve only the F0 points perceptually relevant, are generally applied roughly at a global level, which may not completely eliminate micro intonation in some cases or distort macro intonation in others. In this work we propose a local filtering algorithm based on a fine level analysis of the microprosodic morphologies. The performance of the algorithm is validated by a perceptual experiment. Assuming the algorithm allows partial/total disturbance elimination, we perform a statistical description of the perturbation morphologies. Statistics were collected from a corpus of 741 sentences designed to study Argentine Spanish prosody. The corpus was recorded by four professional announcers native speakers from Buenos Aires city. The results show that perturbation morphologies are affected by: consonant phoneme identity; global F0 contour shape; and speaker identity. As an application case, we use the proposed filtering algorithm as a pre-processing stage in our automatic prominent syllable detection system, with a statistically significant improvement in its performance.
- 21 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 29 (23299290) , 1977-1986
F0 Perturbation Due to Articulatory Movements: Filtering, Characterization and Applications
This paper addresses the issue of local disturbances in the fundamental frequency contour of speech, caused by the articulation of voiced/unvoiced consonant phonemes. Depending on the intended use of the F0 contour, these disturbances are usually eliminated by a filtering, smoothing or stylization procedure. These procedures that seek to preserve only the F0 points perceptually relevant, are generally applied roughly at a global level, which may not completely eliminate micro intonation in some cases or distort macro intonation in others. In this work we propose a local filtering algorithm based on a fine level analysis of the microprosodic morphologies. The performance of the algorithm is validated by a perceptual experiment. Assuming the algorithm allows partial/total disturbance elimination, we perform a statistical description of the perturbation morphologies. Statistics were collected from a corpus of 741 sentences designed to study Argentine Spanish prosody. The corpus was recorded by four professional announcers native speakers from Buenos Aires city. The results show that perturbation morphologies are affected by: consonant phoneme identity; global F0 contour shape; and speaker identity. As an application case, we use the proposed filtering algorithm as a pre-processing stage in our automatic prominent syllable detection system, with a statistically significant improvement in its performance.
- 1 July 2019
- Published by Elsevier in Journal of Voice
- Vol. 33 (4) , 453-464
A Perceptual Method to Rate Dysphonic Voices
- 1 July 2019
- Published by Elsevier in Journal of Voice
- Vol. 33 (4) , 453-464
A Perceptual Method to Rate Dysphonic Voices
- 2 February 2019
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 53 (3) , 419-447
Emilia: a speech corpus for Argentine Spanish text to speech synthesis
- 2 February 2019
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 53 (3) , 419-447
Emilia: a speech corpus for Argentine Spanish text to speech synthesis
- Open Access
- 15 December 2016
- Published by Universidad de Alicante Servicio de Publicaciones in Estudios de Lingüística. Universidad de Alicante
- No. 30,p. 129
La relación entre foco y prosodia: análisis de la percepción de las prominencias acentuales en un corpus del español de Buenos Aires
- 15 December 2016
- Published by Universidad de Alicante Servicio de Publicaciones in Estudios de Lingüística. Universidad de Alicante
- No. 30,p. 129
Open AccessLa relación entre foco y prosodia: análisis de la percepción de las prominencias acentuales en un corpus del español de Buenos Aires
- 20 June 2015
- Published by Elsevier in Journal of Voice
- Vol. 30 (4) , 506.e1-506.e8
Comparison of Two Perceptual Methods for the Evaluation of Vowel Perturbation Produced by Jitter
- 20 June 2015
- Published by Elsevier in Journal of Voice
- Vol. 30 (4) , 506.e1-506.e8
Comparison of Two Perceptual Methods for the Evaluation of Vowel Perturbation Produced by Jitter
- 13 May 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Latin America Transactions
- Vol. 13 (4) , 1098-1111
Data Mining applied to Forensic Speaker Identification
In this paper we analyze the advantages of using data mining techniques and tools for data fusion in forensic speaker recognition. Segmental and suprasegmental features were employed in 28 different classifiers, in order to compare their performances. The selected classifiers have different learning techniques: lazy or instance-based, eager and ensemble. Two approaches were employed on the classification task: the use of all features and the use of a feature subset, selected with a gain ratio methodology. The best performances, with all features, were obtained by three classifiers: Logistic Model Tree (eager), LogitBoost (ensemble) and Multilayer Perceptron (eager). Support Vector Machine (eager) proved to be a good classifier if a Pearson VII function-based universal kernel was used. When low dimensional features were selected, ensemble classifiers exceeded the performance of all others classifiers. Segmental and tone features demonstrated the best speaker discrimination capabilities, followed by duration and quality voice features. Evaluation was performed on Argentine-Spanish voice samples from the Speech_Dat database recorded on a fixed telephone environment. Different recording sessions and channels for the test segments were added and the Z-norm procedure was applied for channel compensation.
- 13 May 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Latin America Transactions
- Vol. 13 (4) , 1098-1111
Data Mining applied to Forensic Speaker Identification
In this paper we analyze the advantages of using data mining techniques and tools for data fusion in forensic speaker recognition. Segmental and suprasegmental features were employed in 28 different classifiers, in order to compare their performances. The selected classifiers have different learning techniques: lazy or instance-based, eager and ensemble. Two approaches were employed on the classification task: the use of all features and the use of a feature subset, selected with a gain ratio methodology. The best performances, with all features, were obtained by three classifiers: Logistic Model Tree (eager), LogitBoost (ensemble) and Multilayer Perceptron (eager). Support Vector Machine (eager) proved to be a good classifier if a Pearson VII function-based universal kernel was used. When low dimensional features were selected, ensemble classifiers exceeded the performance of all others classifiers. Segmental and tone features demonstrated the best speaker discrimination capabilities, followed by duration and quality voice features. Evaluation was performed on Argentine-Spanish voice samples from the Speech_Dat database recorded on a fixed telephone environment. Different recording sessions and channels for the test segments were added and the Z-norm procedure was applied for channel compensation.
- Open Access
- 10 May 2010
- Published by International Speech Communication Association
- p. paper 131
Alignment of F0 model parameters with final and non-final accents in Argentinean Spanish
The goal of this study is to explore the association between tonal accents and fundamental frequency parameters obtained from the Fujisaki model in Buenos Aires Spanish. Results indicate that three-syllable words in final position which are stressed on the third syllable are associated with early peaks. In non-final word accents, late peaks are found for words stressed in the first and second syllables. Alignments were calculated for accent commands relative to the onset of both the accented syllable and its nucleus. Similarly to an earlier study on German, anchoring is supported in favor of tonal transitions than of F0 peaks, considering that alignment of onset and offset times of accent commands appear earlier for final than for non-final accents.
- 10 May 2010
- Published by International Speech Communication Association
- p. paper 131
Open AccessAlignment of F0 model parameters with final and non-final accents in Argentinean Spanish
The goal of this study is to explore the association between tonal accents and fundamental frequency parameters obtained from the Fujisaki model in Buenos Aires Spanish. Results indicate that three-syllable words in final position which are stressed on the third syllable are associated with early peaks. In non-final word accents, late peaks are found for words stressed in the first and second syllables. Alignments were calculated for accent commands relative to the onset of both the accented syllable and its nucleus. Similarly to an earlier study on German, anchoring is supported in favor of tonal transitions than of F0 peaks, considering that alignment of onset and offset times of accent commands appear earlier for final than for non-final accents.
- 1 April 2008
- Published by Elsevier in Computer Speech & Language
- Vol. 22 (2) , 196-206
Acoustic speech unit segmentation for concatenative synthesis
- 1 April 2008
- Published by Elsevier in Computer Speech & Language
- Vol. 22 (2) , 196-206
Acoustic speech unit segmentation for concatenative synthesis