An Efficient Hidden Markov Model with Periodic Recurrent Neural Network Observer for Music Beat Tracking
In music information retrieval (MIR), beat tracking is one of the most fundamental tasks. To obtain this critical component from rhythmic music signals, a previous beat tracking system of hidden Markov model (HMM) with a recurrent neural network (RNN) observer was developed. Although the frequency o...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/24/4186 |
| _version_ | 1797459973781848064 |
|---|---|
| author | Guangxiao Song Zhijie Wang |
| author_facet | Guangxiao Song Zhijie Wang |
| author_sort | Guangxiao Song |
| collection | DOAJ |
| description | In music information retrieval (MIR), beat tracking is one of the most fundamental tasks. To obtain this critical component from rhythmic music signals, a previous beat tracking system of hidden Markov model (HMM) with a recurrent neural network (RNN) observer was developed. Although the frequency of music beat is quite stable, existing HMM based methods do not take this feature into account. Accordingly, most of hidden states in these HMM-based methods are redundant, which is a disadvantage for time efficiency. In this paper, we proposed an efficient HMM using hidden states by exploiting the frequency contents of the neural network’s observation with Fourier transform, which extremely reduces the computational complexity. Observers that previous works used, such as bi-directional recurrent neural network (Bi-RNN) and temporal convolutional network (TCN), cannot perceive the frequency of music beat. To obtain more reliable frequencies from music, a periodic recurrent neural network (PRNN) based on attention mechanism is proposed as well, which is used as the observer in HMM. Experimental results on open source music datasets, such as GTZAN, Hainsworth, SMC, and Ballroom, show that our efficient HMM with PRNN is competitive to the state-of-the-art methods and has lower computational cost. |
| first_indexed | 2024-03-09T16:59:26Z |
| format | Article |
| id | doaj.art-62f40b42235848369da54082c94caed9 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T16:59:26Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-62f40b42235848369da54082c94caed92023-11-24T14:31:50ZengMDPI AGElectronics2079-92922022-12-011124418610.3390/electronics11244186An Efficient Hidden Markov Model with Periodic Recurrent Neural Network Observer for Music Beat TrackingGuangxiao Song0Zhijie Wang1College of Information Science and Technology, Donghua University, Shanghai 201620, ChinaCollege of Information Science and Technology, Donghua University, Shanghai 201620, ChinaIn music information retrieval (MIR), beat tracking is one of the most fundamental tasks. To obtain this critical component from rhythmic music signals, a previous beat tracking system of hidden Markov model (HMM) with a recurrent neural network (RNN) observer was developed. Although the frequency of music beat is quite stable, existing HMM based methods do not take this feature into account. Accordingly, most of hidden states in these HMM-based methods are redundant, which is a disadvantage for time efficiency. In this paper, we proposed an efficient HMM using hidden states by exploiting the frequency contents of the neural network’s observation with Fourier transform, which extremely reduces the computational complexity. Observers that previous works used, such as bi-directional recurrent neural network (Bi-RNN) and temporal convolutional network (TCN), cannot perceive the frequency of music beat. To obtain more reliable frequencies from music, a periodic recurrent neural network (PRNN) based on attention mechanism is proposed as well, which is used as the observer in HMM. Experimental results on open source music datasets, such as GTZAN, Hainsworth, SMC, and Ballroom, show that our efficient HMM with PRNN is competitive to the state-of-the-art methods and has lower computational cost.https://www.mdpi.com/2079-9292/11/24/4186hidden Markov modelperiodic recurrent neural networkbeat trackingattention mechanismdeep learning |
| spellingShingle | Guangxiao Song Zhijie Wang An Efficient Hidden Markov Model with Periodic Recurrent Neural Network Observer for Music Beat Tracking Electronics hidden Markov model periodic recurrent neural network beat tracking attention mechanism deep learning |
| title | An Efficient Hidden Markov Model with Periodic Recurrent Neural Network Observer for Music Beat Tracking |
| title_full | An Efficient Hidden Markov Model with Periodic Recurrent Neural Network Observer for Music Beat Tracking |
| title_fullStr | An Efficient Hidden Markov Model with Periodic Recurrent Neural Network Observer for Music Beat Tracking |
| title_full_unstemmed | An Efficient Hidden Markov Model with Periodic Recurrent Neural Network Observer for Music Beat Tracking |
| title_short | An Efficient Hidden Markov Model with Periodic Recurrent Neural Network Observer for Music Beat Tracking |
| title_sort | efficient hidden markov model with periodic recurrent neural network observer for music beat tracking |
| topic | hidden Markov model periodic recurrent neural network beat tracking attention mechanism deep learning |
| url | https://www.mdpi.com/2079-9292/11/24/4186 |
| work_keys_str_mv | AT guangxiaosong anefficienthiddenmarkovmodelwithperiodicrecurrentneuralnetworkobserverformusicbeattracking AT zhijiewang anefficienthiddenmarkovmodelwithperiodicrecurrentneuralnetworkobserverformusicbeattracking AT guangxiaosong efficienthiddenmarkovmodelwithperiodicrecurrentneuralnetworkobserverformusicbeattracking AT zhijiewang efficienthiddenmarkovmodelwithperiodicrecurrentneuralnetworkobserverformusicbeattracking |