The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
A sharp directional microphone array system was previously developed using a neural network. However, the system cannot distinguish two signals with different frequencies because it learns only the spatial pattern of the sound pressure distribution of the input signals. To overcome this problem, herein we propose a system that learns the temporal-spatial pattern of the input signals. The proposed...
A time-quefrency dereverberation method for reducing the minimum-phase component (MPC) of an unknown room impulse response (RIR) is presented. This paper shows that the vocal-tract and glottal components and the MPC of the RIR can be eliminated from observed signals convolving the unknown RIR with an unknown voiced speech signal. The liftered sequence is applied to direction-of-arrival (DOA) estimator...
These days Web technology is applied to various CE devices, e.g., smart TVs. However, ordinary GUI is not necessarily the best option for people in some situations even with touch panels. So the need for easier-to-use products is growing. To solve this issue, this paper describes the needs for (1) choosing additional modalities dynamically based on the users' demands and (2) standard library to handle...
Targeted at non-professional content creators, this paper presents an easy-to-use tool to create attractive animation for embodied agents just the same as professional directors. Unlike conventional methods that must manually synchronize gestures with speech in many key frames and design many facial textures for expression, our novel authoring system allows the user to semi-automatically create animation...
We propose a new speech intelligibility improvement method for bandlimited synthesized speech, which is based on superposing high-frequency component on lower frequency signal (i.e., baseband signal), where the high-frequency component is compressed in the frequency direction to be fitted on the superposing zone of the baseband signal. We applied the proposed method to Text to speech and conducted...
Howling control is a critical part of any public-address (PA) system. To detect a howling frequency of a PA system before having howling, the author has previously proposed an effective method based on spectral accumulation. This paper shows some results of the howling detection through a practical experiment. In this practical experiment, the proposed method was able to estimate the coloration frequency...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.