We develop new inversion algorithms related to the production and perception of speech
These are the main goals of the project:
Non-invasive measurement of occupational voice loading.
Highly natural speech synthesis including affective factors.
Robust speech recognition in natural environments.
A description of the brain mechanisms of speech perception.
Three Centres of Excellence are involved in the project: CoE in Inverse Problems Research, CoE in Adaptive Informatics Research, and CoE in Computational Complex Systems Research.
Published journal articles:
Tuomo Raitio, Antti Suni, Junichi Yamagishi, Hannu Pulakka, Jani Nurminen, Martti Vainio, Paavo Alku: HMM-based speech synthesis utilizing glottal inverse filtering. IEEE Transactions on Audio, Speech, and Language Processing, Vol. 19, No. 1, pp. 153-165, 2010.
Ismo Miettinen, Hannu Tiitinen, Paavo Alku, Patrick May: Sensitivity of the human auditory cortex to acoustic degradation of speech and non-speech sounds. BMC Neuroscience 2010, 11:24.
Rahim Saeidi, Jouni Pohjalainen, Tomi Kinnunen, Paavo Alku: Temporally weighted linear prediction features for tackling additive noise in speaker verification. IEEE Signal Processing Letters, Vol. 17, No. 6, pp. 599-602, 2010.
Ismo Miettinen, Paavo Alku, Nelli Salminen, Patrick J May, Hannu Tiitinen: Responsiveness of the human auditory cortex to degraded speech sounds: reduction of amplitude resolution vs. additive noise. Brain Research, Vol. 1367, pp. 298-309, 2011.
Krupchyk K, Lassas M and Siltanen S, Determining electrical and heat transfer parameters using coupled boundary measurements. SIAM Journal on Mathematical Analysis 43(5), pp. 2096-2115.
Nakamura G, Ronkanen P, Siltanen S and Tanuma K 2011, Recovering conductivity at the boundary in three-dimensional electrical impedance tomography. Inverse Problems and Imaging 5(2), pp. 485-510.
Astala K, Mueller J L, Paivarinta L, Peramaki A and Siltanen S 2011, Direct electrical impedance tomography for nonsmooth conductivities. Inverse Problems and Imaging 5(3), pp. 531-549.
Nelli Salminen, Hannu Tiitinen, Ismo Miettinen, Paavo Alku, Patrick May: Asymmetrical representation of auditory space in human cortex. Brain Research, Vol. 1306, pp. 93-99, 2010.
Nelli H. Salminen, Patrick J.C. May, Paavo Alku, Hannu Tiitinen: A population rate code of auditory space in the human cortex. PLoS One 4(10), 2010.
Paavo Alku, Tom Bäckström, Carlo Magi: Generalization of linear prediction with the autocorrelation method. Electronics Letters, Vol. 47, Issue 2, pp. 145-147, 2011.
Laura E. Matilainen, Sanna S. Talvitie, Eero Pekkonen, Paavo Alku, Patrick J.C. May, Hannu Tiitinen: The effects of healthy aging on auditory processing in humans as indexed by transient brain responses. Clinical Neurophysiology, Vol. 121, pp. 902-911, 2010.
Sanna S. Talvitie, Laura E. Matilainen, Eero Pekkonen, Paavo Alku, Patrick J.C. May, Hannu Tiitinen: The effects of cortical ischemic stroke on auditory processing in humans as indexed by transient brain responses. Clinical Neurophysiology, Vol. 121, pp. 912-920, 2010.
Santeri Yrttiaho, Hannu Tiitinen, Paavo Alku, Ismo Miettinen, Patrick May: Temporal integration of vowel periodicity in the auditory cortex. Journal of the Acoustical Society of America, Vol. 128, No. 1, pp. 224-234, 2010.
Santeri Yrttiaho, Patrick J. C. May, Hannu Tiitinen, Paavo Alku: Cortical encoding of aperiodic and periodic speech sounds: evidence for distinct neural populations. NeuroImage, Vol. 55, Issue 3, pp. 1252-1259, 2011.
Hannu Pulakka, Paavo Alku: Bandwidth extension of telephone speech using a neural network and a filterbank implementation for highband mel spectrum. IEEE Transactions on Audio, Speech, and Language Processing, Vol. 19, No. 7, pp. 2170-2183, 2011.
Refereed conference papers:
Hannu Pulakka, Ulpu Remes, Kalle Palomäki, Mikko Kurimo, Paavo Alku: Speech bandwidth extension using Gaussian Mixture Model-based estimation of the highband Mel spectrum. In CD Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP'11), Prague, Czech Republic, May 22-27, 2011.
Tuomo Raitio, Antti Suni, Hannu Pulakka, Martti Vainio, Paavo Alku: Utilizing glottal source pulse library for generating improved excitation signal for HMM-based speech synthesis. In CD Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP'11), Prague, Czech Republic, May 22-27, 2011.
Sami Keronen, Ulpu Remes, Kalle J. Palomäki, Tuomas Virtanen, and Mikko Kurimo. Comparison of noise robust methods in large vocabulary speech recognition. In Proceedings of the 18th European Signal Processing Conference, EUSIPCO 2010, Aalborg, Denmark, August 2010.
Hannu Pulakka, Ville Myllylä, Laura Laaksonen, Paavo Alku: Bandwidth extension of telephone speech using a filter bank implementation for highband Mel spectrum. Proc. of the European Signal Processing Conference 2010 (EUSIPCO), Aalborg, Denmark, August 23-27, 2010.
Martti Vainio, Matti Airas, Juhani Järvikivi, Paavo Alku: Laryngeal voice quality in the expression of focus. Proc. of Interspeech’10, Makuhari, Japan, Sept. 26-30, 2010.
Tuomo Raitio, Antti Suni, Hannu Pulakka, Martti Vainio, Paavo Alku: Comparison of formant enhancement methods for HMM-based speech synthesis. Proc. of the 7th ISCA Speech Synthesis Workshop, Kyoto, Japan, Sept. 22-24, 2010.
Antti Suni, Tuomo Raitio, Martti Vainio, Paavo Alku: The GlottHMM speech synthesis entry for Blizzard Challenge 2010. Proc. of the Blizzard Challenge 2010 Workshop, Kyoto, Japan, Sept. 25, 2010.
George Kafentzis, Yannis Stylianou, Paavo Alku: Glottal inverse filtering using Stablilised Weighted Linear Prediction. Proc. of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP’11), Prague, Czech Republic, May 22-27, 2011.
Hannu Pulakka, Ulpu Remes, Santeri Yrttiaho, Kalle Palomäki, Mikko Kurimo, Paavo Alku: Low-frequency bandwidth extension of telephone speech using sinusoidal synthesis and gaussian mixture model. Proc. of Interspeech’11, Florence, Italy, Aug. 28-31, 2011.
Sami Keronen, Jouni Pohjalainen, Paavo Alku, Mikko Kurimo: Noise robust feature extraction based on Extended Weighted Linear Prediction in LVCSR. Proc. of Interspeech’11, Florence, Italy, Aug. 28-31, 2011.
Jouni Pohjalainen, Tuomo Raitio, Paavo Alku: Detection of shouted speech in the presence of ambient noise. Proc. of Interspeech’11, Florence, Italy, Aug. 28-31, 2011.
Tuomo Raitio, Antti Suni, Martti Vainio, Paavo Alku: Analysis of HMM-based Lombard speech synthesis. Proc. of Interspeech’11, Florence, Italy, Aug. 28-31, 2011.
Antti Suni, Tuomo Raitio, Martti Vainio, Paavo Alku: The GlottHMM entry for Blizzard Challenge 2011: Utilizing source unit selection in HMM-based speech synthesis for improved excitation generation. Proc. of the ISCA Blizzard Challenge 2011 Workshop, Turin, Italy, Sept. 2, 2011.
Seppanen A, Nissinen A, Kolehmainen V, Siltanen S and Laukkanen A-M 2011, Electrical impedance tomography imaging of larynx. Models and analysis of vocal emissions for biomedical applications, 7th International Workshop, August 25-27, 2011, Firenze, Italy.
Forthcoming publications:
Paavo Alku: Glottal inverse filtering analysis of human voice production, A review of estimation and parameterization methods of the glottal excitation and their applications. (Invited article). Sadhana. In press.
M. Gehre, T. Kluth A. Lipponen, B. Jin, A. Seppänen, J.P. Kaipio, P. Maass: Sparsity Reconstruction in Electrical Impedance Tomography: An Experimental Evaluation, Journal of Computational and Applied Mathematics, In press.
Conference presentations:
Seppänen A, Nissinen A, Kolehmainen V, Siltanen S, Laukkanen A-M, "Electrical Impedance Tomography imaging of larynx",
Finnish-Japanese-Korean Workshop on Inverse Problems. 14.12.2011, Helsinki, Finland.
Laukkanen A-M.: "Phonation related vocal fold loading as a challenge for imaging and quantification",
Finnish-Japanese-Korean Workshop on Inverse Problems. 14.12.2011, Helsinki, Finland.
Samuli Siltanen: Plenary talk: "Electrical Impedance Tomography", Fields-MITACS Conference on Mathematics of Medical Imaging, University of Toronto, Canada, June 23, 2011.
Samuli Siltanen: "Feasibility of electrical impedance tomography for the imaging of the larynx - preliminary results", Advanced Voice Function Assessment (AVFA) Workshop, Goethe-University of Frankfurt am Main, Germany, May 15, 2011.
Samuli Siltanen: "Fake tooth, artificial voice, and inverse calculus" (in Finnish), Kumpula Colloquium, University of Helsinki, Finland. This presentation was aimed at a general audience.
Samuli Siltanen: "Industrial Mathematics" (In Finnish), The Science Forum, University of Helsinki, Finland, January 13, 2011. This presentation was aimed at a general audience.A. Seppänen, V. Kolehmainen, S. Siltanen, A-M. Laukkanen: "Electrical impedance tomography for non-invasive measurement of occupational voice loading", Annual seminar of Academy of Finland Computational Science Research Programme (Lastu), Tuusula, April 6-8, 2011.
Invited lectures:
A. Seppänen: "Statistical inversion in electrical impedance tomography", School of Mathematical Sciences, Fudan University, Shanghai, China, September 15th, 2010.
A. Seppänen: Three lectures: 1. "Electrical impedance tomography", 2. "Non-stationary inverse problems with application to industrial process tomography", 3. "Localization of internal electrodes in electrical impedance tomography", School of Mathematics and Statistics, Lanzhou University, Lanzhou, China, September 19th - 20th, 2010.
A. Seppänen: "Bayesian inversion in electrical impedance tomography", University of Rome, "La Sapienza", Italy, March 28th, 2011.
Visibility in mainstream media:
The Finnish science TV show "Prisma Studio" reported this project's results on March 6, 2012.
