Proceedings Article10.1109/ICASSP.2011.5947041
Feature selection based on Multiple Kernel Learning for single-channel sound source localization using the acoustic transfer function
Ryoichi Takashima,Tetsuya Takiguchi,Yasuo Ariki +2 more
- 22 May 2011
- pp 2696-2699
TL;DR: A feature selection method for the cepstral parameter using Multiple Kernel Learning (MKL) to define the base kernels for each cEPstral dimension (scalar) of the acoustic transfer function.
read more
Abstract: This paper presents a sound source (talker) localization method using only a single microphone. In our previous work [1], we discussed the single-channel sound source localization method, where the acoustic transfer function from a user's position is estimated by using a Hidden Markov Model (HMM) of clean speech in the cepstral domain. In this paper, each cepstral dimension of the acoustic transfer function is newly selected in order to select the cepstral dimensions having information that is useful for classifying the user's position. Then, we propose a feature selection method for the cepstral parameter using Multiple Kernel Learning (MKL) to define the base kernels for each cepstral dimension (scalar) of the acoustic transfer function. The user's position is trained and classified by Support Vector Machine (SVM). The effectiveness of this method has been confirmed by sound source (talker) localization experiments performed in a room environment.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Array signal processing
TL;DR: This book is very referred for you because it gives not only the experience but also lesson, that's not about who are reading this array signal processing book but about this book that will give wellness for all people from many societies.
733
Geological feature selection in reservoir modelling and history matching with Multiple Kernel Learning
TL;DR: The paper proposes a novel data driven approach - Multiple Kernel Learning (MKL) - for modelling porous property distributions in sub-surface reservoirs and demonstrates an MKL application to a problem of history matching based on a diverse prior information embedded into a range of possible geological scenarios.
16
A new multiple-kernel-learning weighting method for localizing human brain magnetic activity
Tetsuya Takiguchi,Toshiaki Imada,Ryoichi Takashima,Yasuo Ariki,Jo-Fu Lotus Lin,Patricia K. Kuhl,Masaki Kawakatsu,Makoto Kotani +7 more
- 25 Mar 2012
TL;DR: A new weighting method using a multiple kernel learning (MKL) algorithm to localize the brain area contributing to the accurate vowel discrimination is proposed, showing both the large-weight MEG sensors mainly in a language area of the brain and the high classification accuracy in the 100 ~ 200 ms latency range.
•Dissertation
Kernel methods for gene regulatory network inference
Arnaud Fouchet
- 10 Jan 2014
TL;DR: Two approaches are developed to obtain interpretable kernel methods that are shown to consistently estimate a transition function and its partial derivatives from a learning dataset and allow to better infer the gene regulatory network than previous methods on realistic gene regulatory networks.
3
References
Array signal processing
TL;DR: This book is very referred for you because it gives not only the experience but also lesson, that's not about who are reading this array signal processing book but about this book that will give wellness for all people from many societies.
733
Acoustic source location in noisy and reverberant environment using CSP analysis
Maurizio Omologo,Piergiorgio Svaizer +1 more
- 07 May 1996
TL;DR: A linear four microphone array can be employed for acoustic event location in a real environment using an accurate time delay estimation using a specific technique, based on crosspower spectrum phase (CSP) analysis, that yielded accurate location performance.
170
Single microphone source separation using high resolution signal reconstruction
Trausti Kristjansson,Hagai Attias,John R. Hershey +2 more
- 17 May 2004
TL;DR: A method for separating two speakers from a single microphone channel that exploits the fine structure of male and female speech and relies on a strong high frequency resolution model for the source signals.
A New Method for Binaural 3-D Localization Based on Hrtfs
Fakheredine Keyrouz,Y. Naous,Klaus Diepold +2 more
- 14 May 2006
TL;DR: A modern technique for robotic sound source detection using a dataset head-related transfer functions (HRTFs) is presented and provides estimates of azimuth and elevation angles in free space by using only two microphones.
64
Latent Dirichlet Decomposition for Single Channel Speaker Separation
Bhiksha Raj,Madhusudana Shashanka,Paris Smaragdis +2 more
- 14 May 2006
TL;DR: An algorithm for the separation of multiple speakers from mixed single-channel recordings by latent variable decomposition of the speech spectrogram using a Dirichlet distribution.
39