Speaker localization using excitation source information in speech

Raykar, Vikas C.; Yegnanarayana, B.; Prasanna, S. R. Mahadeva; Duraiswami, Ramani

doi:10.1109/tsa.2005.851907

Cited by 47 publications

(43 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Raykar et al [25] work on self-localisation formulates a maximum likelihood estimation for the unknown parameters (time offsets, microphone positions) and measurements (TDOA or TOF) by utilizing active emissions. Ono et al [26] present a TDOA based cost function approach, which does not required controlled calibration signal, for estimating selflocalisation, source localisation, and temporal offset estimation.…”

Section: Related Workmentioning

confidence: 99%

Real-time sound source localisation for target tracking applications using an asynchronous microphone array

Miró

Vidal-Calleja

2015

2015 IEEE 10th Conference on Industrial Electronics and Applications (ICIEA)

View full text Add to dashboard Cite

Abstract-This paper presents a strategy for sound source localisation using an asynchronous microphone array. The proposed method is suitable for target tracking applications, in which the sound source with a known frequency is attached to the target. Conventional microphone array technologies require a multichannel A/D converter for inter-microphone synchronization making the technology relatively expensive. In this work, the requirement of synchronization between channels is relaxed by adding an external reference audio signal. The only assumption is that the frequencies of the reference signal and the sound source attached to the target are fixed and known beforehand. By exploiting the information provided by the known reference signal, the Direction Of Arrival (DOA) of target sound source can be calculated in real-time. The key idea of the algorithm is to use the reference source to "pseudo-align" the audio signals from different channels. Once the channels are "pseudoaligned", a dedicated DOA estimation method based on Time Difference Of Arrival (TDOA) can be employed to find the relative bearing information between the target sound source and microphone array. Due to the narrow band of frequency of target sound source, the proposed approach is proven to be robust to low signals-to-noise ratios. Comprehensive simulations and experimental results are presented to show the validity of the algorithm.

show abstract

Section: Related Workmentioning

confidence: 99%

Real-time sound source localisation for target tracking applications using an asynchronous microphone array

Miró

Vidal-Calleja

2015

2015 IEEE 10th Conference on Industrial Electronics and Applications (ICIEA)

View full text Add to dashboard Cite

show abstract

“…This method has been used in localisation of an asynchronous source in [10]. Raykar et al's work [11] on self-localisation formulates a maximum likelihood estimation for unknown parameters of a microphone array (time offsets, microphone positions) and measurements (time difference of arrival (TDOA) or time of flight (TOF)) by utilising active emissions. Ono et al [12] presents a TDOA-based cost function approach, which does not require controlled calibration signal for estimating self-localisation, source localisation and temporal offset estimation.…”

Section: Introductionmentioning

confidence: 99%

Simultaneous asynchronous microphone array calibration and sound source localisation

Vidal-Calleja

Miró

2015

2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Abstract-In this paper, an approach for sound source localisation together with the calibration of an asynchronous microphone array is proposed to be solved simultaneously. A graph-based Simultaneous Localisation and Mapping (SLAM) method is used for this purpose. Traditional sound source localisation using a microphone array has two main requirements. Firstly, geometrical information of microphone array is needed. Secondly, a multichannel analog-to-digital converter is necessary to obtain synchronous readings of the audio signal. Recent works aim at releasing these two requirements by estimating the time offset between each pair of microphones. However, it was assumed that the clock timing in each microphone sound card is exactly the same, which requires the clocks in the sound cards to be identically manufactured. A methodology is hereby proposed to calibrate an asynchronous microphone array using a graph-based optimisation method borrowed from the SLAM literature, effectively estimating the array geometry, time offset and clock difference/drift rate of each microphone together with the sound source locations. Simulation and experimental results are presented, which prove the effectiveness of the proposed methodology in achieving accurate estimates of the microphone array characteristics needed to be used on realistic settings with asynchronous sound devices.

show abstract

“…Among various HRI components, we especially focus on audio-based HRI. Audio-based HRI technology includes speech recognition, speaker recognition [3] [4], sound source localization [5], sound source separation, speech emotional recognition, speech enhancement, gender and age group recognition. Among various audio-based HRI components, we focus on gender and age group recognition.…”

Section: Introductionmentioning

confidence: 99%

Performance Comparison of Gender and Age Group Recognition for Human-Robot Interaction

Lee¹,

Kwak²

2012

IJACSA

View full text Add to dashboard Cite

Abstract-In this paper, we focus on performance comparison of gender and age group recognition to perform robot's application services for Human-Robot Interaction (HRI). HRI is a core technology that can naturally interact between human and robot. Among various HRI components, we concentrate audio-based techniques such as gender and age group recognition from multichannel microphones and sound board equipped with robots. For comparative purposes, we perform the performance comparison of Mel-Frequency Cepstral Coefficients (MFCC) and Linear Prediction Coding Coefficients (LPCC) in the feature extraction step, Support Vector Machine (SVM) and C4.5 Decision Tree (DT) in the classification step. Finally, we deal with the usefulness of gender and age group recognition for humanrobot interaction in home service robot environments.

show abstract

Speaker localization using excitation source information in speech

Cited by 47 publications

References 24 publications

Real-time sound source localisation for target tracking applications using an asynchronous microphone array

Real-time sound source localisation for target tracking applications using an asynchronous microphone array

Simultaneous asynchronous microphone array calibration and sound source localisation

Performance Comparison of Gender and Age Group Recognition for Human-Robot Interaction

Contact Info

Product

Resources

About