Share This Author
Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection
- Emre Çakir, Giambattista Parascandolo, T. Heittola, H. Huttunen, T. Virtanen
- Computer ScienceIEEE/ACM Transactions on Audio, Speech, and…
- 9 December 2015
This work combines these two approaches in a convolutional recurrent neural network (CRNN) and applies it on a polyphonic sound event detection task and observes a considerable improvement for four different datasets consisting of everyday sound events.
Recurrent neural networks for polyphonic sound event detection in real life recordings
- Giambattista Parascandolo, H. Huttunen, T. Virtanen
- Computer ScienceIEEE International Conference on Acoustics…
- 20 March 2016
In this paper we present an approach to polyphonic sound event detection in real life recordings based on bi-directional long short term memory (BLSTM) recurrent neural networks (RNNs). A single…
Machine learning framework for early MRI-based Alzheimer's conversion prediction in MCI subjects
Robust detection of periodic time series measured from biological systems
- Miika Ahdesmäki, H. Lähdesmäki, Ronald K. Pearson, H. Huttunen, O. Yli-Harja
- Computer ScienceBMC Bioinformatics
- 13 May 2005
This work proposes a general-purpose robust testing procedure for finding periodic sequences in multiple time series data based on a robust spectral estimator which is incorporated into the hypothesis testing framework using a so-called g-statistic together with correction for multiple testing.
Computational Framework for Simulating Fluorescence Microscope Images With Cell Populations
- A. Lehmussola, P. Ruusuvuori, J. Selinummi, H. Huttunen, O. Yli-Harja
- BiologyIEEE Transactions on Medical Imaging
- 2 July 2007
A simulation platform for generating synthetic images of fluorescence-stained cell populations with realistic properties that enable the validation of analysis methods for automated image cytometry and comparison of their performance is presented.
Polyphonic sound event detection using multi label deep neural networks
- Emre Çakir, T. Heittola, H. Huttunen, T. Virtanen
- Computer ScienceInternational Joint Conference on Neural Networks…
- 12 July 2015
Frame-wise spectral-domain features are used as inputs to train a deep neural network for multi label classification in this work and the proposed method improves the accuracy by 19% percentage points overall.
Car type recognition with Deep Neural Networks
- H. Huttunen, Fatemeh Shokrollahi Yancheshmeh, Ke Chen
- Computer ScienceIEEE Intelligent Vehicles Symposium (IV)
- 23 February 2016
Two data driven frameworks are considered: a deep neural network and a support vector machine using SIFT features for automatic recognition of cars of four types: Bus, Truck, Van and Small car.
Recognition of acoustic events using deep neural networks
- O. Gencoglu, T. Virtanen, H. Huttunen
- Computer Science22nd European Signal Processing Conference…
- 13 November 2014
For an acoustic event classification task containing 61 distinct classes, classification accuracy of the neural network classifier excels that of the conventional Gaussian mixture model based hidden Markov model classifier.
Clustering benefits in mobile-centric WiFi positioning in multi-floor buildings
- Andrei Cramariuc, H. Huttunen, E. Lohan
- Computer ScienceInternational Conference on Localization and GNSS…
- 28 June 2016
A comparative analysis between different clustering methods, together with a novel metric, called the Penalized Logarithmic Gaussian Distance metric which can boost the performance of the clustering.
Taming the waves: sine as activation function in deep neural networks
This paper formally characterize why deep neural networks can indeed often be difficult to train even in very simple scenarios, and describes how the presence of infinitely many and shallow local minima emerges from the architecture.