User profiles for Okko Johannes Räsänen
Okko RäsänenAssociate Professor, Tampere University, Finland Verified email at tuni.fi Cited by 2413 |
[PDF][PDF] An improved speech segmentation quality measure: the r-value
OJ Räsänen, UK Laine, T Altosaar - Tenth Annual Conference of the …, 2009 - Citeseer
Phone segmentation in ASR is usually performed indirectly by Viterbi decoding of HMM
output. Direct approaches also exist, eg, blind speech segmentation algorithms. In either case, …
output. Direct approaches also exist, eg, blind speech segmentation algorithms. In either case, …
[PDF][PDF] Generating Hyperdimensional Distributed Representations from Continuous-Valued Multivariate Sensory Input.
OJ Räsänen - CogSci, 2015 - researchgate.net
Hyperdimensional computing (HDC) refers to the representation and manipulation of data
in a very high dimensional space using random vectors. Due to the high dimensionality, …
in a very high dimensional space using random vectors. Due to the high dimensionality, …
[PDF][PDF] Self-learning vector quantization for pattern discovery from speech.
OJ Räsänen, UK Laine, T Altosaar - Interspeech, 2009 - isca-archive.org
A novel and computationally straightforward clustering algorithm was developed for vector
quantization (VQ) of speech signals for a task of unsupervised pattern discovery (PD) from …
quantization (VQ) of speech signals for a task of unsupervised pattern discovery (PD) from …
[PDF][PDF] Computational language acquisition by statistical bottom-up processing.
OJ Räsänen, UK Laine, T Altosaar - INTERSPEECH, 2008 - lands.let.ru.nl
Statistical learning of patterns from perceptual input is an increasingly central topic in
cognitive processing including human language acquisition. We present an unsupervised …
cognitive processing including human language acquisition. We present an unsupervised …
[PDF][PDF] A noise robust method for pattern discovery in quantized time series: the concept matrix approach
OJ Räsänen, UK Laine, T Altosaar - Tenth Annual Conference of the …, 2009 - Citeseer
An efficient method for pattern discovery from discrete time series is introduced in this paper.
The method utilizes two parallel streams of data, a discrete unit time-series and a set of …
The method utilizes two parallel streams of data, a discrete unit time-series and a set of …
[PDF][PDF] Analyzing the Predictability of Lexeme-specific Prosodic Features as a Cue to Sentence Prominence.
S Kakouros, OJ Räsänen - CogSci, 2015 - researchgate.net
This study investigates the relationship between sentence prominence and the predictability
of word-specific statistical descriptors of prosody. We extend from an earlier wordinvariant …
of word-specific statistical descriptors of prosody. We extend from an earlier wordinvariant …
[PDF][PDF] Computational evidence for effects of memory decay, familiarity preference and mutual exclusivity in cross-situational learning.
H Rasilo, OJ Räsänen - CogSci, 2015 - researchgate.net
Human infants learn meanings for words in interaction with their environment. Individual
learning scenarios can be ambiguous due to the presence of several words and possible …
learning scenarios can be ambiguous due to the presence of several words and possible …
[PDF][PDF] Method for Speech Inversion with Large Scale Statistical Evaluation.
H Rasilo, UK Laine, OJ Räsänen, T Altosaar - INTERSPEECH, 2011 - researchgate.net
An articulatory model of speech production is created for the purpose of studying the links
between speech production and perception. A computationally effective method for speech …
between speech production and perception. A computationally effective method for speech …
[PDF][PDF] Estimation studies of vocal tract shape trajectory using a variable length and lossy kelly-lochbaum model.
H Rasilo, UK Laine, OJ Räsänen - INTERSPEECH, 2010 - isca-archive.org
This work demonstrates the use of a modified Kelly-Lochbaum (KL) vocal tract (VT) model in
dynamic mapping from speech signals to articulatory configurations. The sixteen section KL …
dynamic mapping from speech signals to articulatory configurations. The sixteen section KL …
[PDF][PDF] Fully unsupervised word learning from continuous speech using transitional probabilities of atomic acoustic events.
OJ Räsänen - Interspeech, 2010 - isca-archive.org
This work presents a learning algorithm based on transitional probabilities of atomic acoustic
events (vector quantized spectral features). The algorithm learns models for word-like units …
events (vector quantized spectral features). The algorithm learns models for word-like units …