Niklas Vanhaien

Since March of 2013, I am a PhD student at the Department of Speech, Music and Hearing in the Shcool of Computer Science and Communication. My supervisor is Giampiero Salvi.



Vanhainen, N., & Salvi, G. (2014). Free Acoustic and Language Models for Large Vocabulary Continuous Speech Recognition in Swedish. In Proceedings of LREC. Reykjavik, Iceland. [pdf]Vanhainen, N., & Salvi, G. (2014). Pattern Discovery in Continuous Speech Using Block Diagonal Infinite HMM. In Proceedings of ICASSP. Florence, Italy. [pdf]Salvi, G., & Vanhainen, N. (2014). The WaveSurfer Automatic Speech Recognition Plugin. In Proceedings of LREC. Reykjavik, Iceland. [pdf]


Vanhainen, N. (2012). Discovering words from continuous speech - Two factor analysis methods. Master's thesis, KTH, School of Computer Science and Communication, Dept for Speech, Music and Hearing. [pdf]Vanhainen, N., & Salvi, G. (2012). Word Discovery with Beta Process Factor Analysis. In Proceedings of Interspeech. Portland, Oregon. [abstract] [pdf]Abstract: We propose the application of a recently developed non-parametric Bayesian method for factor analysis to the problem of word discovery from continuous speech. The method, based on Beta Process priors, has a number of advantages compared to previously proposed methods, such as Non-negative Matrix Factorisation (NMF). Beta Process Factor Analysis (BPFA) is able to estimate the size of the basis, and therefore the num- ber of recurring patterns, or word candidates, found in the data. We compare the results obtained with BPFA and NMF on the TIDigits database, showing that our method is capable of not only finding the correct words, but also the correct number of words. We also show that the method can infer the approximate number of words for different vocabulary sizes by testing on randomly generated sequences of words.

This is a personal web page. More information.

Valid XHTML 1.1