Spatial Cepstrum as a Spatial Feature Using a Distributed Microphone Array for Acoustic Scene Analysis

Imoto, Keisuke; Ono, Nobutaka

doi:10.1109/taslp.2017.2690559

Cited by 33 publications

(33 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For extracting spatial information using an unsynchronized and distributed microphone array, Kürby et al [41] and Phan et al [48] devised scene classification methods based on late fusion of scene classification results in each microphone. Imoto et al [49][50][51] proposed a spatial cepstrum that can extract spatial information robustly when microphones are not synchronized.…”

Section: Acoustic Event and Scene Analysis Utilizingmentioning

confidence: 99%

Introduction to acoustic event and scene analysis

Imoto

2018

Acoust. Sci. & Tech.

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Acoustic Event and Scene Analysis Utilizingmentioning

confidence: 99%

Introduction to acoustic event and scene analysis

Imoto

2018

Acoust. Sci. & Tech.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Figure 3 shows the acoustic scene classification process using the spatial-feature-based BoW representation and the generative model of acoustic spatial words. To extract the spatial features, we utilized the spatial cepstrum (SC) proposed in [20]. Similarly, the generalized-frequency spatial cepstrum (GFSC) is used for the integrated feature including spatial and spectral information [20].…”

Section: A Environmental Sound Recordingsmentioning

confidence: 99%

“…To extract the spatial features, we utilized the spatial cepstrum (SC) proposed in [20]. Similarly, the generalized-frequency spatial cepstrum (GFSC) is used for the integrated feature including spatial and spectral information [20]. The SC and GFSC can extract the spatial information efficiently and robustly without using locations of the microphones.…”

Section: A Environmental Sound Recordingsmentioning

confidence: 99%

“…However, to apply these methods, the position information of microphones is needed and the microphones require synchronizing, and therefore, it is not easy to use them for a distributed microphone array. To address this problem, we previously proposed a method for extracting spatial information that does not need the position information of the microphone array and does not need precisely synchronized microphones if the microphones are positionally fixed [20].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Acoustic scene classification based on generative model of acoustic spatial words for distributed microphone array

Imoto

2017

2017 25th European Signal Processing Conference (EUSIPCO)

Self Cite

View full text Add to dashboard Cite

Abstract-In this paper, we propose an acoustic scene classification method for a distributed microphone array based on a combination of spatial information of multiple sound events. In the proposed method, each acoustic scene is characterized by a spatial information representation based on a bag-ofwords called the bag of acoustic spatial words. To calculate the bag-of-acoustic spatial words, spatial features extracted from multichannel observations are quantized and then aggregated over a sound clip, that is, each sound clip is regarded as a unit of a"document." Moreover, a supervised generative model relating acoustic scenes and bag-of-acoustic spatial words is also adapted, which enables robust acoustic scene classification. Experimental results using actual environmental sounds show that the proposed approach achieves more effective performance than the conventional acoustic scene classification approach not utilizing a combination of the spatial information of multiple sound events.

show abstract

“…It is worth to note that an operation to remove a reverberation from an audio signal is called blind dereverberation. This problem was investigated in many papers [8], [9], [10], [11], [12], [13] and others. But the goal of such signal transform was to make the audio signal free from additional reverberation interference that may occur in a natural manner.…”

Section: Attack On a Wm System That Is Based On The Embedding Witmentioning

confidence: 99%

Design of Audio Digital Watermarking System Resistant to Removal Attack

Korzhik

Алексеев

Morales‐Luna

2017

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Abstract-We consider a digital watermarking system intended for an embedding of additional information into audio (typically musical) files that should be resistant against a removal attack. The proposed embedding procedure is based on a reverberation and extraction procedure executing a cepstral transform. A removal attack based on blind dereverberation is investigated both theoretically and experimentally. In order to prevent such an attack, a slight modification of the embedding procedure is also proposed. Further experiments show that the proposed watermarking system provides both a good quality of the cover audio-signal and a sufficiently large embedding rate.

show abstract

Spatial Cepstrum as a Spatial Feature Using a Distributed Microphone Array for Acoustic Scene Analysis

Cited by 33 publications

References 28 publications

Introduction to acoustic event and scene analysis

Introduction to acoustic event and scene analysis

Acoustic scene classification based on generative model of acoustic spatial words for distributed microphone array

Design of Audio Digital Watermarking System Resistant to Removal Attack

Contact Info

Product

Resources

About