Program

The XXII PVC main focus is on how technology helps in capturing, processing and analyzing voice and speech signals in health, disease and in training by means of optical visualizations, acoustics, electrophysiology, posturography and many newer clinical technologies such as OCT, NBI and HSDI. Hardware and software are discussed. Other applications include homeland security, phonetic processing, communication, man-machine communication, pedagogy and emotions. Special focus is also given to cochlear implants role in restoration of motor functions involved in voice and speech production. The XXII PVC is a coproduction of many leading institutions from the USA and RP.

Program is subject to change without notice.

Building D-17, where the conference rooms are located

Please prepare 14 minutes long presentation using Power Point or *.pdf file. Each room will be equipped with computer but you can use your PC as well.

krakow_agh_d-17.jpg

Day 1, Friday, April 11, 2014

Registration 8:00-8:55

Session 1. Joined rooms 1.19 & 1.20, 9:00-9:30

Opening and Welcome

9:00-9:05 Prof. dr hab. Tadeusz Pisarkiewicz, Head of the Department of Computer Science, Electronics and Telecommunications of the AGH University of Science and Technology.

9:05-9:10 Krzysztof Izdebski and Bartosz Ziółko: PVSF & AGH. Opening Remarks.

9:10-9:30 Major Invited Lecture
“Development of Voice Technology in Poland”
Introduction of Prof. Ryszard Tadeusiewicz
Former Chancellor of the AGH University of Science and Technology, Kraków
by Dr Krzysztof Izdebski (USA)

Session 2. Room 1.20, 9:40-10:55

Chair: Grażyna Demenko (Poland)

Sound Software and Hardware

9:40-9:55 Samuel Sonning, Thomas Mejtoft, Sten Ternström, Viveka Lyberg Åhlander (Sweden). Reliability of voice SPL estimations with an air-coupled microphone fastened to the neck.

9:55-10:10 Felix De Jong, H. Lycke, W. Decoster, A. Ivanova, M.M. Van Hulle (Belgium & The Netherlands). Mathematical analysis of different natural voice types.

10:10-10:25 Leszek Gajecki (Poland). Language modelling using SOM network.

10:25-10:40 Mariusz Mąsior, Mariusz Ziółko (Poland). Determination and selection of speaker dependent voice features for vocal tract normalization.

10:40-10:55 Łukasz Potępa, Ewa Niebudek-Bogusz, Wiesław Wszołek (Poland). Application of mel-cepstral coefficients to diagnostic of voice disorders.

Session 3. Room 1.19, 9:40-10:55

Chair: Jan Svec (The Czech Republic)

Physiological & Acoustical Signals Processing

9:40-9:55 Yuling Yan, Krzysztof Izdebski (USA). Simpler, faster and a more accurate data reduction protocol from HSDI.

9:55-10:10 Mariusz Ziółko (Poland). Fourier-wavelet speech analysis.

10:10-10:25 Jakub Gałka, Rafał Samborski (Poland). Fundamental frequency estimation employing wavelet parametrization.

10:25-10:40 Magdalena Igras, Marcin Witkowski, Joanna Grzybowska, Paweł Jaciów, Mariusz Ziółko (Poland). Caller identification by voice.

10:40-10:55 Marcin Just, Michal H. Tyc, (Poland). Computer analysis of vocal folds function with audio and video techniques.

Workshops 11:00 - 12:00:

Room 1.20 Joseph Quoidbach (Belgium). Advances in posturography and acoustic technology to correct singer’s vocal output.

Room 1.19 Bodo Maass (Germany). Measuring and controlling resonance of the mouth with VoceVista Video.

12:00 – 14:20 Lunch Break

Session 4. Room 1.20, 14:20-16:50

Chair: Raul M. Cruz (USA)

Clinical Technology (Acoustics)

14:20-14:35 Andrea Bandini, F. Giovannelli, S. Orlandi, S.D. Barbagallo, M. Cincotta, P. Vanni, R. Chiaramonti, A. Borgheresi, G. Zaccara, C. Manfredi (Italy). Acoustic and kinematic analysis of speech in idiopathic Parkinson's disease.

14:35-14:50 Joanna Ćwiklińska, Agnieszka Pankowska, Anna Geremek-Samsonowicz, Henryk Skarżyński, Karolina Samsonowicz (Poland). Sound perception changes in patients with partial deafness after cochlear implantation.

14:50-15:05 Mateusz Gasiński, Maciej Kłaczyński, Wiesław Wszołek, Maciej Modrzejewski (Poland). Human voice analysis as first step in early diagnostics of laryngeal pathology.

15:05-15:20 Georges Lawson (Belgium). Total laryngectomy using transoral robotic surgery (TORS). Techniques & results.

15:20-15:35 Georges Lawson (Belgium). How transoral total laryngectomy affects voice parameters and voice rehabilitation.

15:35-15:50 Artur Lorens, Malgorzata Zgoda, Anna Geremek, Henryk Skarżyński (Poland). Development of speech discrimination in implanted patients.

15:50-16:05 Maya Overbye Herulf (Denmark). Musical narratives in nonverbal human communication.

16:05-16:20 S. Orlandi, A. Bandini, S.D. Barbagallo, C. Manfredi (Italy). Automatic classification of newborn cry melody.

16:20-16:35 Elżbieta Włodarczyk, Agata Szkiełkowska, Henryk Skarżyński (Poland). Central auditory processing disorders and specific language impairments.

16:35-16:50 Khalid Daoudi, Safaa Mrad (France). A novel nonlinear approach to speech perturbation measure for pathological voice classification.

Session 5. Room 1.19, 14:20-16:35

Chair: Bożena Wiskirska-Woźnica (Poland)

Software analysis of acoustic and visual signals

14:20-14:35 Magdalena Igras, Bartosz Ziółko, Mariusz Ziółko (Poland). Is phoneme length and phoneme energy useful in automatic speaker recognition

14:35-14:50 Yizhar Lavner, Alex Frid (Israel). Spectral and textural features for automatic classification of fricatives.

14:50-15:05 Maciej Kłaczyński, Wiesław Wszołek (Poland). Electroacoustic methods of determining the parameters of speech sound generator.

15:05-15:20 Tomasz Mąka, Piotr Dziurzański (Poland). Analysis of the influence of acoustical adverse conditions on speaker gender identification.

15:20-15:35 Dima Ruinskiy, Yizhar Lavner (Israel). A multistage algorithm for fricative spotting.

15:35-15:50 Bartosz Zaborowski (Poland). Shallow parsing on word lattices.

15:50-16:05 Piotr Żelasko, Bartosz Ziółko, Dawid Skurzok (Poland). Statistics of diphones and triphones presence on the word boundaries in the Polish language. Applications to ASR.

16:05-16:20 Grażyna Demenko, Bożena Wiskirska-Woźnica (Poland). Acoustic protocol for disturbed speech signals.

16:20-16:35 Joanna Grzybowska, Maciej Kłaczyński (Poland). Computer-assisted HFCC-based learning system for patients with articulation disorders.

Workshops in joined rooms 1.19 & 1.20, 17:00 - 18:30:

Lilla Sadowski (Austria). Sensoliguistic Therapy Machine (STM).

Niksa Bareza (Austria). Traditional Chinese medicine for modern treatment of dysphonia. (TCM): An ancient technology.

18:30 END OF DAY 1

AGH D-17 Foyer 18:30 - 19:30 Reception

Day 2, Saturday, April 12, 2014

Session 6. Joined rooms 1.19 & 1.20, 9:00-10:15

Chair: Anna Barney (United Kingdom)

Voice and Emotions

9:00-9:30 Major Invited Lecture
Branka Zei-Pollermann (Switzerland)
“Why and how we encode emotions into our speech and voice patterns. Luxury or sheer necessity?”

9:30-9:45 S. Orlandi, Claudia Manfredi, A. Bandini and M.L. Scattoni (Italy). Automatic analysis of spontaneous infant cry for early diagnosis of autism spectrum disorders.

9:45-10:00 Rosario Signorello (USA). Acoustic characteristics of the charismatic voice.

10:00-10:15 Niksa Bareza (Austria). Traditional Chinese medicine, an ancient technology for modern voice therapy.

10:15-11:10 Mystery of human voice - film screening.

11:10 - 11:30 Coffee Break

Session 7. Room 1.20, 11:45-13:15

Chair: Mette F. Pedersen (Denmark)

Clinical Voice Issues & Technology

11:45-12:00 Łukasz Potępa, Joanna Szaleniec, Wiesław Wszołek, Andrzej Steczko, Jacek Składzień (Poland). Impact of tonsillectomy on selected speech parameters.

12:00-12:15 Mette Pedersen, Sanila Mahmood, Anders Jønsson, Martin Eeg (Denmark). Applying acoustic and high-speed visual measures to study voice of patients with laryngopharyngeal reflux. A randomized controlled approach.

12:15-12:30 Krzysztof Izdebski and Rob Mickel (USA). Voice restoration in total esophageal stenosis post total laryngectomy and radiation therapy. A case for Tokyo larynx.

12:30-12:45 Raul M. Cruz and Krzysztof Izdebski (USA). Bevacizumb utility in RRP.

12:45-13:00 Maria A. Hortis-Dzierzbicka (Poland). The role of nasofiberscopic (NSF) visualization in the assessment and management of resonance disorders in cleft palate patients.

13.00-13.15 Mara Behlau, Glaucya Madazio, Paulo Pontes (Brazil). Positioning of the laryngeal endoscope on videokymography.

Session 8. Room 1.19, 11:30-13:15

Chair: Felix De Jong (Belgium & The Netherlands)

Pathological and Emotional Voice: Analysis

11:30-11:45 Branka Zei-Pollermann. (Switzerland). Extraction of the emotional signature of the human voice using Praat technology.

11:45-12:00 Lilla-Teresa Sadowski (Austria). Voice therapy for servere dysphonia.

12:00-12:15 Anna Barney, Dragana Nikolic, Manuela Bung, Peter Garrard (United Kingdom). Acoustic analysis of speech patterns. A marker for dementia.

12:15-12:30 Manuela Bung, Anna Barney (United Kingdom). Characterising speech patterns in frontotemporal dementia and Alzheimer’s disease according to the Levelt-model.

12:30-12:45 Krzysztof Szklanny, Ryszard Gubrynowicz, Krzysztof Marasek, Anna Tylki-Szymańska, Katarzyna Iwanicka-Pronicka (Poland). Pathological changes in speech of patients with Pompe’s disease.

12:45-13:00 Beata Miaśkiewicz, Agata Szkiełkowska, Henryk Skarżyński (Poland). Acoustic analysis of voice after injection laryngoplasty.

13:00-13:15 Martin Swanholm, Thomas Barslev (Sweden). Articulatory singing voice synthesis for music production.

13:15 - 14:30 Lunch Break

Session 9: Room 1.20, 14:30-16:15

Chair: Mara Behlau (Brazil)

Clinical Voice

14:30-14:45 Brian Wong (USA). OCT Application to the studies of human vocal folds in vivo

14:45-15:00 Beata Miaśkiewicz, Agata Szkiełkowska, Paulina Krasnodębska, Henryk Skarżyński (Poland). Videostrobokymography (VSK) in the assessment of voice disorders.

15:00-15:15 Bożena Wiskirska-Woźnica, Świdziński P., Malaczyńska B. (Poland). Research methodology of laryngeal pitch - clinical aspects.

15:15-15:30 Vít Hampala, Anne-Maria Laukkanen, Marco A. Guzman, Jaromir Horacek, Jan G. Svec (The Czech Republic, Finland, Chile). Changes in vocal fold adjustment caused by phonation into a tube investigated by computed tomography.

15:30-15:45 Ronald R. Ward (USA). Technology to examine sensory loss of the larynx.

15:45-16:00 Eric J. Hunter (USA). A budget voice dosimetry system for research. Benefits and limitations.

16:00-16:15 Felix De Jong, W. Decoster, S. Vandertwee, L. Decruy, Harm K Schutte (The Netherlands, Belgium). The vibratory pattern of the vocal folds in various registrations of the artistic voice. Evidence from Videokymography.

Session 10: Room 1.19, 14:30-16:30

Chair: Claudia Manfredi (Italy)

Voice - Clinical Analysis

14:30-14:45 Raul M. Cruz, Krzysztof Izdebski (USA). History, theory, utility & comparison to traditional LVS.

14:45-15:00 Sebastian Dippold, Christoph Becker, Wolfgang Maier, Bernhard Richter, Matthias Echternach. (Germany). NBI a tool for a better visualization of laryngeal papillomatosis.

15:00-15:15 Zhongping Chen, Joseph Jing, Anthony Chin Loy, Brian J.F. Wong (USA). Development of high-speed long-range Fourier domain OCT for in vivo imaging of pediatric upper airway.

15:15-15:30 Ewelina Sielska-Badurek (Poland). Comparison of costs versus analysis of videostroboscopy systems.

15:30-15:45 Ronald R. Ward and Krzysztof Izdebski (USA). The role of Botox in the treatment of voice and speech problems.

15:45-16:00 Hana Šrámková, Efren Fernandéz-Grande, Jonas Brunskog, Jan G. Švec (The Czech Republic, Denmark) Near-field measurements of the human voice using a microphone array – preliminary study.

16:00-16:15 Allan Vurma, Kristel Kalling (Estonia). The voice problems of vocalists and the situations behind - A pilot study.

16:15-16:30 Ewelina Sielska-Badurek, Ewa Osuch-Wójcikiewicz (Poland). The value of the flexible fiber-optic endoscopic visualization in the examination of the different singing styles.

Evening in Wieliczka Salt Mine

Interesting social programme is planned as well, including a banquet in Wieliczka salt mine. Participants who are claustrophobic should be aware that the Gala Dinner will be held 125 m underground.

17:00 Depart to the Wieliczka Salt Mine for Tour and for Gala Dinner

17:30 Arrive at the Wieliczka Salt Mine

17:45-18:45 Tour of the Wieliczka Mine

“Weliczka Salt Mine is located in the town of Wieliczka in southern Poland, lies within the Kraków metropolitan area. The mine, built in the 13th century, produced table salt continuously until 2007, as one of the world's oldest salt mines still in operation. From its beginning and throughout its existence, the Royal mine was run by the Żupy krakowskie Salt Mines. Commercial mining was discontinued in 1996 due to low salt prices and mine flooding. The mine's attractions include dozens of statues, three chapels and an entire cathedral that has been carved out of the rock salt by the miners. The oldest sculptures are augmented by the new carvings by contemporary artists. About 1.2 million people visit the Wieliczka Salt Mine annually.” - Wikipedia

19:00-21:00 Gala Dinner at The Haluszka Chamber (125 meters underground)

21:30 Bus Departs to Hotel

Day 3, Sunday, April 13, 2014

Session 11. Room 1.20, 9:00-10:00

Chair: Beata Miaśkiewicz (Poland)

Clinical Voice Technology/Hearing

9:00-9:15 Raul M. Cruz, Krzysztof Izdebski (USA). Narrow Band Imaging (NBI) versus white light examinations of the glottis in some unusual mucosal vocal folds lesions.

9:15-9:30 Ronald R. Ward, Krzysztof Izdebski (USA). Advantages of using EMG technology in the treatment of voice and speech problems.

9:30-9:45 Marcin Just, Anna Sinkiewicz, Hanna Mackiewicz-Nartowicz, Michal H. Tyc (Poland). Vocal loading test with periodic measurement of diagnostic parameters.

9:45-10:00 Mara Behlau, Glaucya Madazio, Marina Englert, Jorge Lucero, Jean Schoentgen (Brazil & Belgium). A Vocal Fold Model for Disordered Voice Synthesis to Develop Auditory Perception in Speech Language Patologists.

Session 12. Room 1.19, 9:00-10:00

Chair: Erkki Bianco (France)

Clinical Voice Technology/ Hearing

9:00-9:15 Susanna Whitling, Viveka Lyberg Åhlander, Roland Rydell (Sweden). Tracking endurance of voice-healthy individuals in a vocal loading test including long time voice measurement.

9:15-9:30 Arkadiusz Wąsowski, Piotr H. Skarżyński, Artur Lorens, Anita Obrycka, Adam Walkowiak, Łukasz Bruski, Henryk Skarżyński (Poland). National Network of Teleaudiology in clinical practice for cochlear implant patients. A model of a national voice network.

9:30-9:45 Mara Behlau, Thays Vaiano (Brazil). The Development of a Specific Voice Approach Program for a Specific and Challenged Vocal Demand. A Pivotal Role Of Detailed Examination and Voice Load Test.

9:45-10:00 Ekaterina V. Osipenko et al. (Russia). Biofeedback game in the treatment of patients with voice disorders.

Coffee Break 10:00 - 10:30

Session 13. Room 1.20, 10:30-12:15

Chair: Ekaterina Osipenko (Russia)

Artistic Voice +

10:30-10:45 Erkki Bianco (France). The good voice, the bad voice. Examination of the professionnal voice in the office.

10:45-11:00 Enrico Di Lorenzo, Krzysztof Izdebski, Yuling Yan (Italy, USA). What we have learned about Heavy-Metal production form HSDP.

11:00-11:15 Krzysztof Izdebski, Lydia Hyde, Ronald Ward, Joel C. Ross (USA). Usage of flexible fiberoptics to observe glottic activity in a didgeridoo player and singer.

11:15-11:30 Bodo Maass (Germany). VoceVista Video - a new generation of visual feedback software for vocal pedagogy.

11:30-11:45 Mara Behlau, Ana Celiane Ugolino (Brazil). Self-assessment of the Communicative Behavior on Public Speaking of Diverse Professionals using Two Different Instruments.

11:45-12:00 Sebastian Dziadzio (Poland). Unit selection speech synthesizer for the Polish language. Student paper.

12:00-12:15 Magdalena Majdak, Magdalena Igras, Anna Domeracka-Kołodziej (Poland). Looking for natural voice - the effectiveness of the program of Postgraduate Studies of Voice and Speech Training at the University of Social Sciences and Humanities in Warsaw.

Session 14. Room 1.19, 10:30-12:30

Chair: Mariusz Ziółko (Poland)

Normative Voice – Hearing - Future

10:30-10:45 Jan G. Švec, Michael Döllinger, Jörg Lohscheller (The Czech Republic, Germany). Normative data from in vivo kymographic imaging in humans. Vocal fold vibration amplitude, open quotient and speed quotient.

10:45-11:00 Enrico di Lorenzo, Krzysztof Izdebski, Yuling Yan (USA, Italy). Physiologic correlates of vocal emotions based on HSDP.

11:00-11:15 Mateusz Rusiniak, Monika Lewandowska, Tomasz Wolak, Agnieszka Pluta, Katarzyna Cieśla, Henryk Skarżyński (Poland). Temporal aspects and neural correlates of auditory perception in children with dyslexia. An EEG-fMRI study.

11:15-11:30 Krzysztof Izdebski (USA). Phonetotopic organization of phonation based of EMG, Ps, Air Flow and sensory stimuli.

11:30-11:45 Mette Pedersen, Sanila Mahmood (Denmark). Genomics & genetics of the human voice.

11:45-12:00 Henrik Kjelin, Cathrine Sadolin (Denmark). The advantages of a common accepted terminology among voice teachers.

12:00-12:15 Mathew Blanco, Xin Chen, Yuling Yan (USA). A restricted, adaptive threshold segmentation approach for processing High-speed image sequences of the glottis.

12:15-12:30 Jerzy Wolf (Poland). How to create an emotional and/or altered voice quality. An acoustic comparison between habitual and altered voice of the same natural speaker. Student paper.

Workshop in joined rooms 1.19 & 1.20, 12:45 - 13:45

13:45 The Official End of the XXII PVC (East)

Prof. Izdebski talk and short concerts of:

Ewelina Sielska-Badurek (Poland)
Monia Grassa (Italy)

Exhibits

Olympus - NBI is a patented technology of Olympus.

Diagnova Technologies is a manufacturer of dedicated software for medical diagnostics, data analysis and visualization, and dedicated measurement equipment and software. Our key product is DiagnoScope Specjalista, a computer program for versatile acoustic voice analysis in phoniatric diagnostics and image acquisition with advanced kymographic analysis in laryngological endoscopy, containing also special modules for audiometry and professional singers’ voice assessment. Our services include comparative voice analysis for forensic purposes. We also design and manufacture tailored electronic devices, particularly for impedance measurements in medicine and chemistry, as well as accompanying software.

Multilanguage speech database being build at AGH University of Science and Technology with support of PVSF. Demonstration of existing data and recording new. The main objectives of the project are:

  • development of new methods of phonemes extraction and determining of their characteristics,
  • investigation of the differences among the phonemes of 300 languages all over the world,
  • investigation of the origin and expansion of modern languages,
  • creation of a natural languages taxonomy on the basis of the multi-linguistic phoneme analysis and methods used in evolutionary genetics,
  • improving of Polish speech phonemes identification.

Techmo sp. z o.o. Exhibit of AGH spin-off developing speech and speaker recognition system.

Copyright © XXII PVC Organizing Committee 2013. All Rights Reserved.