Comparison of techniques for environmental sound recognition

Cowling, Michael; Sitte, Renate

doi:10.1016/s0167-8655(03)00147-8

Cited by 196 publications

(125 citation statements)

References 5 publications

Supporting

Mentioning

124

Contrasting

Order By: Relevance

“…The Hellinger (Bhattacharya) kernel is effective for measuring the similarity between probability distributions [12]. Such kernel can be embedded in a (linear) dot product of the feature vectors normalized by the following L 2 -Hellinger normalization [13];x = x x 1 . Note that the proposed features are non-negative and the normalized feature vectorx has a unit L 2 norm ( x 2 = 1); linear SVM effectively works on the features that have a unit L 2 norm [14].…”

Section: -Hellinger Normalizationmentioning

confidence: 99%

“…While the methods for classifying speech and music have been intensively developed for decades, those for the environmental sounds are studied with keen attention in recent years [1,2,3,4]. The environmental sounds are different from the speech and music in that the acoustic signals are not stationary nor well-structured; characteristics in these types of sounds are discussed in [5].…”

Section: Introductionmentioning

confidence: 99%

“…The environmental sounds are different from the speech and music in that the acoustic signals are not stationary nor well-structured; characteristics in these types of sounds are discussed in [5]. Therefore, the conventional speech recognition methods might not be suitable for the environmental sounds [1,2,6], and much research effort has been made especially on the feature extraction that effectively characterize them.…”

Section: Introductionmentioning

confidence: 99%

“…Cowling et al [1] extensively investigated various types of acoustic features as well as classification methods, concluding that the continuous wavelet transform with dynamic time warping produces the promising performance. Wavelet packet analysis is applied to extract acoustic feature in generalized sound classification [7].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Acoustic feature extraction by statistics based local binary pattern for environmental sound classification

Kobayashi

2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Classification of environmental sounds is a fundamental procedure for a wide range of real-world applications. In this paper, we propose a novel acoustic feature extraction method for classifying the environmental sounds. The proposed method is motivated from the image processing technique, local binary pattern (LBP), and works on a spectrogram which forms two-dimensional (time-frequency) data like an image. Since the spectrogram contains noisy pixel values, for improving classification performance, it is crucial to extract the features which are robust to the fluctuations in pixel values. We effectively incorporate the local statistics, mean and standard deviation on local pixels, to establish robust LBP. In addition, we provide the technique of L 2 -Hellinger normalization which is efficiently applied to the proposed features so as to further enhance the discriminative power while increasing the robustness. In the experiments on environmental sound classification using RWCP dataset that contains 105 sound categories, the proposed method produces the superior performance (98.62%) compared to the other methods, exhibiting significant improvements over the standard LBP method as well as robustness to noise and low computation time.

show abstract

Section: -Hellinger Normalizationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Acoustic feature extraction by statistics based local binary pattern for environmental sound classification

Kobayashi

2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…Sound recognition is a challenge that has been explored for many years using machine learning methods with different techniques (e.g., neural networks, learning vector quantization, ...) and with different features extracted depending on the technique (Cowling & Sitte, 2003). It can be used for many applications inside the home, such as the quantification of water use (Ibarz, Bauer, Casas, Marco, & Lukowicz, 2008) but it is mostly used for the detection of distress situations.…”

Section: Sound Recognitionmentioning

confidence: 99%

Development of Audio Sensing Technology for Ambient Assisted Living

Fleury

Vacher

Noury

et al. 2011

International Journal of E-Health and Medical Communications

View full text Add to dashboard Cite

One of the greatest challenges in Ambient Assisted Living is to design health smart homes that anticipate the needs of its inhabitant while maintaining their safety and comfort. It is thus essential to ease the interaction with the smart home through systems that naturally react to voice command using microphones rather than tactile interfaces. However, efficient audio analysis in such noisy environment is a challenging task. In this paper, a real-time audio analysis system, the AuditHIS system, devoted to audio analysis in smart home environment is presented. AuditHIS has been tested thought three experiments carried out in a smart home that are detailed. The results show the difficulty of the task and serve as basis to discuss the stakes and the challenges of this promising technology in the domain of AAL.

show abstract