• The Journal of the Acoustical Society of Korea
• /
• v.36 no.4
• /
• pp.267-272
• /
• 2017

In this paper, we propose an effective method of applying multichannel-audio feature values to GRNNs (Gated Recurrent Neural Networks) in polyphonic sound event detection. Real life sounds are often overlapped with each other, so that it is difficult to distinguish them by using a mono-channel audio features. In the proposed method, we tried to improve the performance of polyphonic sound event detection by using multi-channel audio features. In addition, we also tried to improve the performance of polyphonic sound event detection by applying a gated recurrent neural network which is simpler than LSTM (Long Short Term Memory), which shows the highest performance among the current recurrent neural networks. The experimental results show that the proposed method achieves better sound event detection performance than other existing methods.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1990.10a
• /
• pp.251-256
• /
• 1990

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.5
• /
• pp.109-116
• /
• 2010

In this paper, we propose a method for extracting predominant melody of polyphonic music based on harmonic structure. Since polyphonic music contains multiple sound sources, the process of melody detection consists of extraction of multiple fundamental frequencies and determination of predominant melody using those fundamental frequencies. Harmonic structure is an important feature parameter of monophonic signal that has spectral peaks at the integer multiples of its fundamental frequency. We extract all fundamental frequency candidates contained in the polyphonic signal by verifying the required condition of harmonic structure. Then, we combine those harmonic peaks corresponding to each extracted fundamental frequency and assign a rank to each after calculating its harmonic average energy. We finally run pitch tracking based on the rank of extracted fundamental frequency and continuity of fundamental frequency, and determine the predominant melody. We measure the performance of proposed method using ADC 2004 DB and 100 Korean pop songs in terms of MIREX 2005 evaluation metrics, and pitch accuracy of 90.42% is obtained.

• ETRI Journal
• /
• v.39 no.6
• /
• pp.832-840
• /
• 2017

Recently, deep recurrent neural networks have achieved great success in various machine learning tasks, and have also been applied for sound event detection. The detection of temporally overlapping sound events in realistic environments is much more challenging than in monophonic detection problems. In this paper, we present an approach to improve the accuracy of polyphonic sound event detection in multichannel audio based on gated recurrent neural networks in combination with auditory spectral features. In the proposed method, human hearing perception-based spatial and spectral-domain noise-reduced harmonic features are extracted from multichannel audio and used as high-resolution spectral inputs to train gated recurrent neural networks. This provides a fast and stable convergence rate compared to long short-term memory recurrent neural networks. Our evaluation reveals that the proposed method outperforms the conventional approaches.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.769-771
• /
• 2005

In this paper we present a method of separating musical instrument sound sources from their monaural mixture, where we take the harmonic structure of music into account and use the sparseness and the overlapping NMF [1] to select representative spectral basis vectors which are used to reconstruct unmixed sound. A method of spectral basis selection is illustrated and experimental results with monaural mixture of voice/cello and trumpet/viola are shown to confirm the validity of our proposed method.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.8
• /
• pp.1-8
• /
• 2013

This paper proposes an effective parallel implementation of a physical modeling synthesis of guitar on the GPU environment. We used appropriate filter coefficients and adjusted the length of delay line for each open string to generate 44,100 six-polyphonic guitar sounds (E2, A2, D3, G4, B3, E4) by using physical modeling synthesis. In addition, we analyzed the physical modeling synthesis algorithm and observed that we can exploit parallelism inherent in the length of delay line. Thus, we assigned CUDA cores as many as the length of delay line and effectively implemented the physical modeling synthesis using GPU to achieve the highest performance. Experimental results indicated that synthetic guitar sounds using GPU were very similar to the original sounds when we compared their spectra. In addition, GPU achieved 68x and 3x better performance than high-performance TI DSP and CPU, respectively. Furthermore, this paper implemented and evaluated the performance of multi-GPU systems for the physical modeling algorithm.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.8
• /
• pp.697-705
• /
• 2009

An unsupervised (blind) method is proposed aiming at extracting rhythmic sources from commercial polyphonic music whose number of channels is limited to one. Commercial music signals are not usually provided with more than two channels while they often contain multiple instruments including singing voice. Therefore, instead of using conventional modeling of mixing environments or statistical characteristics, we should introduce other source-specific characteristics for separating or extracting sources in the under determined environments. In this paper, we concentrate on extracting rhythmic sources from the mixture with the other harmonic sources. An extension of nonnegative matrix factorization (NMF), which is called nonnegative matrix partial co-factorization (NMPCF), is used to analyze multiple relationships between spectral and temporal properties in the given input matrices. Moreover, temporal repeatability of the rhythmic sound sources is implicated as a common rhythmic property among segments of an input mixture signal. The proposed method shows acceptable, but not superior separation quality to referred prior knowledge-based drum source separation systems, but it has better applicability due to its blind manner in separation, for example, when there is no prior information or the target rhythmic source is irregular.