Hanna Silen
Hanna Silen
Verified email at google.com
TitleCited byYear
Voice conversion using dynamic kernel partial least squares regression
E Helander, H Silén, T Virtanen, M Gabbouj
IEEE transactions on audio, speech, and language processing 20 (3), 806-817, 2011
1162011
Parameterization of vocal fry in HMM-based speech synthesis
H Silén, E Helander, J Nurminen, M Gabbouj
Tenth Annual Conference of the International Speech Communication Association, 2009
352009
Ways to implement global variance in statistical speech synthesis
H Silén, E Helander, J Nurminen, M Gabbouj
Thirteenth Annual Conference of the International Speech Communication …, 2012
282012
On the impact of alignment on voice conversion performance
E Helander, J Schwarz, J Nurminen, H Silen, M Gabbouj
Ninth Annual Conference of the International Speech Communication Association, 2008
272008
Recent advances in Google real-time HMM-driven unit selection synthesizer
X Gonzalvo, S Tazari, C Chan, M Becker, A Gutkin, H Silen
262016
Local linear transformation for voice conversion
V Popa, H Silen, J Nurminen, M Gabbouj
2012 IEEE International Conference on Acoustics, Speech and Signal …, 2012
222012
Google's Next-Generation Real-Time Unit-Selection Synthesizer Using Sequence-to-Sequence LSTM-Based Autoencoders.
V Wan, Y Agiomyrgiannakis, H Silen, J Vit
INTERSPEECH, 1143-1147, 2017
162017
Hierarchical modeling of F0 contours for voice conversion
G Sanchez, H Silen, J Nurminen, M Gabbouj
Fifteenth Annual Conference of the International Speech Communication …, 2014
122014
Voice conversion for non-parallel datasets using dynamic kernel partial least squares regression
H Silén, J Nurminen, E Helander, M Gabbouj
Convergence 1, 2, 2013
122013
Analysis of duration prediction accuracy in HMM-based speech synthesis
H Silén, E Helander, J Nurminen, M Gabbouj
Speech Prosody 2010-Fifth International Conference, 2010
92010
Evaluation of detailed modeling of the LP residual in statistical speech synthesis
J Nurminen, H Silén, E Helander, M Gabbouj
2013 IEEE International Symposium on Circuits and Systems (ISCAS2013), 313-316, 2013
82013
Prediction of voice aperiodicity based on spectral representations in HMM speech synthesis
H Silen, E Helander, M Gabbouj
Twelfth Annual Conference of the International Speech Communication Association, 2011
82011
Maximum a posteriori voice conversion using sequential Monte Carlo methods
E Helander, H Silén, J Míguez, M Gabbouj
Eleventh Annual Conference of the International Speech Communication Association, 2010
82010
Using robust Viterbi algorithm and HMM-modeling in unit selection TTS to replace units of poor quality
H Silén, E Helander, J Nurminen, K Koppinen, M Gabbouj
Eleventh Annual Conference of the International Speech Communication Association, 2010
72010
Building a Finnish unit selection TTS system.
H Silen, E Helander, K Koppinen, M Gabbouj
SSW, 310-315, 2007
62007
Speaker-specific retraining for enhanced compression of unit selection text-to-speech databases.
J Nurminen, H Silén, M Gabbouj
INTERSPEECH, 388-391, 2013
52013
Voice conversion
J Nurminen, H Silén, V Popa, E Helander, M Gabbouj
Speech enhancement, modeling and recognition-algorithms and applications, 2012
52012
Evaluation of Finnish unit selection and HMM-based speech synthesis
H Silen, E Helander, J Nurminen, M Gabbouj
Ninth Annual Conference of the International Speech Communication Association, 2008
52008
Methods and apparatuses for facilitating speech synthesis
JK Nurminen, HM Silen, E Helander
US Patent 8,781,835, 2014
42014
Voice conversion using dynamic kernel partial least squares regression
H Silen
IEEE Trans. Audio, Speech, and Language Processing 20, 806-817, 2012
32012
The system can't perform the operation now. Try again later.
Articles 1–20