Discriminative multiple sound source localization based on deep neural networks using independent location model

Takeda, Ryo; Komatani, Kazunori

doi:10.1109/slt.2016.7846325

Cited by 74 publications

(66 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Localization of two sources is addressed in [11], which encodes the output as two marginal posterior probability vectors. However, an ad-hoc location-based ordering is introduced to decide the source-to-vector assignment, rendering the posteriors dependent on each other and the encoding somewhat ambiguous.…”

Section: B Existing Neural Network-based Ssl Methodsmentioning

confidence: 99%

Deep Neural Networks for Multiple Speaker Detection and Localization

Motlíček

Odobez

2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

140

167

View full text Add to dashboard Cite

We propose to use neural networks for simultaneous detection and localization of multiple sound sources in human-robot interaction. In contrast to conventional signal processing techniques, neural network-based sound source localization methods require fewer strong assumptions about the environment. Previous neural network-based methods have been focusing on localizing a single sound source, which do not extend to multiple sources in terms of detection and localization.In this paper, we thus propose a likelihood-based encoding of the network output, which naturally allows the detection of an arbitrary number of sources. In addition, we investigate the use of sub-band cross-correlation information as features for better localization in sound mixtures, as well as three different network architectures based on different motivations. Experiments on real data recorded from a robot show that our proposed methods significantly outperform the popular spatial spectrum-based approaches.

show abstract

Section: B Existing Neural Network-based Ssl Methodsmentioning

confidence: 99%

Deep Neural Networks for Multiple Speaker Detection and Localization

Motlíček

Odobez

2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

140

167

View full text Add to dashboard Cite

show abstract

“…Compared to signal processing based approaches to this task, supervised learning approaches have the advantage that they can be adapted to different acoustic conditions via training. With the recent success of deep neural network based supervised learning methods for different signal processing related tasks, they have also become an attractive solution for DOA estimation [1][2][3][4][5][6][7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

“…Existing approaches mainly vary in terms of the input features that are utilized for the task of DOA estimation. Most of the earlier methods [1][2][3][4][5] involved a feature extraction step, where features similar to those used in classical signal processing based approaches, were given as an input to a deep neural network to learn the mapping from the features to the DOA of the sound sources.…”

Section: Introductionmentioning

confidence: 99%

Multi-scale Aggregation of Phase Information for Complexity Reduction of CNN Based DOA Estimation

Chakrabarty

Habets

2019

2019 27th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

In a recent work on direction-of-arrival (DOA) estimation of multiple speakers with convolutional neural networks (CNNs), the phase component of short-time Fourier transform (STFT) coefficients of the microphone signal is given as input and small filters are used to learn the phase relations between neighboring microphones. Due to this chosen filter size, M − 1 convolution layers are required to achieve the best performance for a microphone array with M microphones. For arrays with large number of microphones, this requirement leads to a high computational cost making the method practically infeasible. In this work, we propose to use systematic dilations of the convolution filters in each of the convolution layers of the previously proposed CNN for expansion of the receptive field of the filters to reduce the computational cost of the method. Different strategies for expansion of the receptive field of the filters for a specific microphone array are explored. With experimental analysis of the different strategies, it is shown that an aggressive expansion strategy results in a considerable reduction in computational cost while a relatively gradual expansion of the receptive field exhibits the best DOA estimation performance along with reduction in the computational cost.

show abstract

“…To improve the robustness of DOA estimation, deep neural networks (DNNs) have been proposed to learn a mapping between signal features and a discretized DOA space [17][18][19][20][21]. Various features such as phasemaps [17,18] and GCC-PHAT [21] have been used as inputs.…”

Section: Introductionmentioning

confidence: 99%

“…This property has motivated clustering-based localization algorithms, which iteratively identify the time-frequency bins dominated by each speaker and reestimate the corresponding DOAs [24][25][26]. It has also recently been exploited to design training data for multi-speaker DNN-based localization [18,19].…”

Section: Introductionmentioning

confidence: 99%

Keyword Based Speaker Localization: Localizing a Target Speaker in a Multi-speaker Environment

Sivasankaran¹,

Fohr²

2018

Interspeech 2018

View full text Add to dashboard Cite

To cite this version:Sunit Sivasankaran, Emmanuel Vincent, Dominique Fohr. Keyword-based speaker localization: Localizing a target speaker in a multi-speaker environment. Interspeech 2018 -19th AbstractSpeaker localization is a hard task, especially in adverse environmental conditions involving reverberation and noise. In this work we introduce the new task of localizing the speaker who uttered a given keyword, e.g., the wake-up word of a distantmicrophone voice command system, in the presence of overlapping speech. We employ a convolutional neural network based localization system and investigate multiple identifiers as additional inputs to the system in order to characterize this speaker.We conduct experiments using ground truth identifiers which are obtained assuming the availability of clean speech and also in realistic conditions where the identifiers are computed from the corrupted speech. We find that the identifier consisting of the ground truth time-frequency mask corresponding to the target speaker provides the best localization performance and we propose methods to estimate such a mask in adverse reverberant and noisy conditions using the considered keyword.

show abstract

Discriminative multiple sound source localization based on deep neural networks using independent location model

Cited by 74 publications

References 21 publications

Deep Neural Networks for Multiple Speaker Detection and Localization

Deep Neural Networks for Multiple Speaker Detection and Localization

Multi-scale Aggregation of Phase Information for Complexity Reduction of CNN Based DOA Estimation

Keyword Based Speaker Localization: Localizing a Target Speaker in a Multi-speaker Environment

Contact Info

Product

Resources

About