Separating Multi Speeches in Intelligent Humanoid Robot using FastICA

Abstract

The main objective of our research is to develop an intelligent humanoid robot for teaching children by listening and answering the questions. In our previous research, we have designed a humanoid robot that can detect human face and receive commands by using speech recognition. Our robot is based on Bioloid GP robot and Raspberry Pi2 as control system. In this study, we would like to expand the capability of the robot system in order to isolate the speech of one speaker from all the other sounds. The problem for separating multi speeches from stereo audio record is called as Blind Speech Separation (BSS). We propose FastICA algorithm to solve the BSS problem. FastICA is an efficient algorithm to separate several signals based on Independent Component Analysis (ICA) algorithm. Some assumption must be met to use FastICA, that is the number of mixtures are equal to the number of sources and the sources are linearly independent from each other. To evaluate the algorithm, we use several simulations based on two speech sources and its mixing matrix. Our simulation shows FastICA algorithm can solve BSS problem by separating two sound signals, but its linearly independent assumption makes it difficult to implement in our humanoid robot.

Hybrid In-Vehicle Background Noise Reduction for Robust Speech Recognition: The Possibilities of Next Generation 5G Data Networks

“…To resolve an issue with an unknown parameter A mix , Eq. ( 5) is used to estimate independent components from mixed speech signals, where W is the inverse matrix from the A mix matrix [21][22][23].…”

“…There is a significant number of ICA based algorithms. Among them are FastICA, JADE, SOBI, Infomax, FlexiICA, kICA, RADICAL ICA, AMUSE etc [22,[24][25][26]. All these algorithms require performing ICA preprocessing in form of centering (creation of zero mean vector) and whitening (creation of vector with unit scattering).…”

“…First, maximum number of iterations k and criterium of convergence δ must be selected. FastICA algorithm is then based on following steps [21][22][23]: 1) Random normalized vector w + is created.…”

Pengembangan Sistem Kendali Robot Humanoid untuk Edukasi berdasarkan Robosapien dan Raspberry Pi Zero

“…Dalam penelitian sebelumnya (Tarunajaya, et al, 2016), kami mengembangkan robot humanoid yang dapat berinteraksi dengan mengenali wajah seseorang dan menjawab pertanyaan sederhana. Dilanjutkan lagi (Ngarianto, et al, 2018), robot humanoid telah ditanamkan metode untuk memisahkan dua sinyal suara yang berbeda yaitu laki-laki dan perempuan. Namun gerakan robot tersebut hanya dibagian tangan saja yang bergerak.…”