Estimating positions of multiple adjacent speakers based on MUSIC spectra correlation using a microphone array
نویسندگان
چکیده
In this paper, we propose an improved method of estimating the positions of two speakers using a microphone array. A well-known method, MUSIC, can be used to estimate speaker positions with high precision. However, in the special case that the speakers are closely located, the conventional MUSIC-based method sometimes fails to identify the existence of certain speakers, because close peaks in the MUSIC spectrum cannot be resolved. To overcome this di culty, we propose a new method utilizing a crosscorrelation between space-spectra calculated by MUSIC. Experimental results in a real environment have shown that the proposed method is e ective in resolving the approximate positions of adjacent speakers.
منابع مشابه
Localization of multiple environmental sound sources by MUSIC method with weighted histogram
This paper presents an estimation method of environmental sound sources localization based on MUSIC method by small-sized microphone array. MUSIC spectrum depends on array manifold vector calculated from microphone array configuration and eigenvectors provided an observed signal. By considering the relation between a microphone array and MUSIC spectrum, we examine the arrangement of microphones...
متن کاملMultimodal Speaker Segmentation and Identification in Presence of Overlapped Speech Segments
We propose a multimodal algorithm for speaker segmentation and identification with two main contributions: First, we suggest a hidden Markov model architecture that performs fusion of three modalities: a multi-camera system for participant localization, a microphone array for speaker localization, and a speaker identification system; Second, we present a novel likelihood model for the microphon...
متن کاملA real-time super-resolution robot audition system that improves the robustness of simultaneous speech recognition
This study addresses a framework for a robot audition system, including sound source localization (SSL) and sound source separation (SSS), that can robustly recognize simultaneous speeches in a real environment. Because SSL estimates not only the location of speakers but also the number of speakers, such a robust framework is essential for simultaneous speech recognition. Moreover, improvement ...
متن کاملSingle microphone speech separation by diffusion-based HMM estimation
We present a novel non-iterative and rigorously motivated approach for estimating hidden Markov models (HMMs) and factorial hidden Markov models (FHMMs) of high-dimensional signals. Our approach utilizes the asymptotic properties of a spectral, graph-based approach for dimensionality reduction and manifold learning, namely the diffusion framework. We exemplify our approach by applying it to the...
متن کاملAssembly and Employment of a Microphone Array with a Text-Independent Speaker Identification System
In this Master thesis, the combination of a 64 sensor microphone array named MarkIII/IRSTLight and a text-independent speaker identification system is investigated. The work is carried out within the EU-funded CHIL project (Computers in the Human Interaction Loop) for which the research of unobtrusive technology is a main focus. By exploiting the spatial correlation of the multiple signals prod...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2001