Ulpu Remes

Publication Activity (10 Years)

Years Active: 2007-2023
Publications (10 Years): 9

Top Topics

Evaluation Method

Speech Recognition

Top Venues

IEEE ACM Trans. Audio Speech Lang. Process.

Publications

Daolang Huang, Manuel Haussmann, Ulpu Remes, ST John, Grégoire Clarté, Kevin Sebastian Luck, Samuel Kaski, Luigi Acerbi
Practical Equivariances via Relational Conditional Neural Processes. CoRR (2023)
Daolang Huang, Manuel Haussmann, Ulpu Remes, ST John, Grégoire Clarté, Kevin Sebastian Luck, Samuel Kaski, Luigi Acerbi
Practical Equivariances via Relational Conditional Neural Processes. NeurIPS (2023)
Jukka Corander, Ulpu Remes, Timo Koski
Likelihood-free Model Choice for Simulator-based Models with the Jensen-Shannon Divergence. CoRR (2022)
Jukka Corander, Ulpu Remes, Ida Holopainen, Timo Koski
Nonparametric likelihood-free inference with Jensen-Shannon divergence for simulator-based models with categorical output. CoRR (2022)
Shreyas Seshadri, Ulpu Remes, Okko Räsänen
Dirichlet process mixture models for clustering i-vector data. ICASSP (2017)
Shreyas Seshadri, Ulpu Remes, Okko Räsänen
Comparison of Non-Parametric Bayesian Mixture Models for Syllable Clustering and Zero-Resource Speech Processing. INTERSPEECH (2017)
Emma Jokinen, Ulpu Remes, Paavo Alku
Intelligibility Enhancement of Telephone Speech Using Gaussian Process Regression for Normal-to-Lombard Spectral Tilt Conversion. IEEE ACM Trans. Audio Speech Lang. Process. 25 (10) (2017)
Emma Jokinen, Ulpu Remes, Paavo Alku
The Use of Read versus Conversational Lombard Speech in Spectral Tilt Modeling for Intelligibility Enhancement in Near-End Noise Conditions. INTERSPEECH (2016)
Ulpu Remes, Ana Ramírez López, Lauri Juvela, Kalle J. Palomäki, Guy J. Brown, Paavo Alku, Mikko Kurimo
Comparing human and automatic speech recognition in a perceptual restoration experiment. Comput. Speech Lang. 35 (2016)
Emma Jokinen, Ulpu Remes, Paavo Alku
Comparison of Gaussian process regression and Gaussian mixture models in spectral tilt modelling for intelligibility enhancement of telephone speech. INTERSPEECH (2015)
Ulpu Remes, Ana Ramírez López, Kalle J. Palomäki, Mikko Kurimo
Bounded Conditional Mean Imputation with Observation Uncertainties and Acoustic Model Adaptation. IEEE ACM Trans. Audio Speech Lang. Process. 23 (7) (2015)
Ana Ramírez López, Nobutaka Ono, Ulpu Remes, Kalle J. Palomäki, Mikko Kurimo
Designing multichannel source separation based on single-channel source separation. ICASSP (2015)
Reima Karhila, Ulpu Remes, Mikko Kurimo
Noise in HMM-Based Speech Synthesis Adaptation: Analysis, Evaluation Methods and Experiments. IEEE J. Sel. Top. Signal Process. 8 (2) (2014)
Emma Jokinen, Ulpu Remes, Marko Takanen, Kalle J. Palomäki, Mikko Kurimo, Paavo Alku
Spectral tilt modelling with extrapolated GMMs for intelligibility enhancement of narrowband telephone speech. IWAENC (2014)
Emma Jokinen, Ulpu Remes, Marko Takanen, Kalle J. Palomäki, Mikko Kurimo, Paavo Alku
Spectral tilt modelling with GMMs for intelligibility enhancement of narrowband telephone speech. INTERSPEECH (2014)
Ulpu Remes, Reima Karhila, Mikko Kurimo
Objective evaluation measures for speaker-adaptive HMM-TTS systems. SSW (2013)
Sami Keronen, Heikki Kallasjoki, Ulpu Remes, Guy J. Brown, Jort F. Gemmeke, Kalle J. Palomäki
Mask estimation and imputation methods for missing data speech recognition in a multisource reverberant environment. Comput. Speech Lang. 27 (3) (2013)
Reima Karhila, Ulpu Remes, Mikko Kurimo
HMM-based speech synthesis adaptation using noisy data: Analysis and evaluation methods. ICASSP (2013)
Ulpu Remes
Bounded conditional mean imputation with an approximate posterior. INTERSPEECH (2013)
Hannu Pulakka, Ulpu Remes, Santeri Yrttiaho, Kalle J. Palomäki, Mikko Kurimo, Paavo Alku
Bandwidth Extension of Telephone Speech to Low Frequencies Using Sinusoidal Synthesis and a Gaussian Mixture Model. IEEE Trans. Speech Audio Process. 20 (8) (2012)
Hannu Pulakka, Ulpu Remes, Kalle J. Palomäki, Mikko Kurimo, Paavo Alku
Speech bandwidth extension using Gaussian mixture model-based estimation of the highband mel spectrum. ICASSP (2011)
Jort F. Gemmeke, Bert Cranen, Ulpu Remes
Sparse imputation for large vocabulary noise robust ASR. Comput. Speech Lang. 25 (2) (2011)
Heikki Kallasjoki, Ulpu Remes, Jort F. Gemmeke, Tuomas Virtanen, Kalle J. Palomäki
Uncertainty Measures for Improving Exemplar-Based Source Separation. INTERSPEECH (2011)
Ulpu Remes, Yoshihiko Nankaku, Keiichi Tokuda
GMM-Based Missing-Feature Reconstruction on Multi-Frame Windows. INTERSPEECH (2011)
Ulpu Remes, Kalle J. Palomäki, Tapani Raiko, Antti Honkela, Mikko Kurimo
Missing-Feature Reconstruction With a Bounded Nonlinear State-Space Model. IEEE Signal Process. Lett. 18 (10) (2011)
Hannu Pulakka, Ulpu Remes, Santeri Yrttiaho, Kalle J. Palomäki, Mikko Kurimo, Paavo Alku
Low-Frequency Bandwidth Extension of Telephone Speech Using Sinusoidal Synthesis and Gaussian Mixture Model. INTERSPEECH (2011)
Jort F. Gemmeke, Ulpu Remes, Kalle J. Palomäki
Observation uncertainty measures for sparse imputation. INTERSPEECH (2010)
Sami Keronen, Ulpu Remes, Kalle J. Palomäki, Tuomas Virtanen, Mikko Kurimo
Comparison of noise robust methods in large vocabulary speech recognition. EUSIPCO (2010)
Ulpu Remes, Kalle J. Palomäki, Mikko Kurimo
Robust automatic speech recognition using acoustic model adaptation prior to missing feature reconstruction. EUSIPCO (2009)
Ulpu Remes, Kalle J. Palomäki, Mikko Kurimo
Missing feature reconstruction and acoustic model adaptation combined for large vocabulary continuous speech recognition. EUSIPCO (2008)
Ulpu Remes, Janne Pylkkönen, Mikko Kurimo
Segregation of Speakers for Speaker Adaptation in TV News Audio. ICASSP (4) (2007)