Iterative Thresholding-Based Spectral Subtraction Algorithm for Speech Enhancement

Kumar, R.; Tripathy, Manoj; Anand, R. S.

doi:10.1007/978-981-16-0443-0_18

Cited by 2 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e model uses a constrained mixture of Gaussian models to uniformly describe each set of harmonics and uses expectation maximization to estimate the fundamental frequency of the music. e iterative spectrum elimination approach was suggested and enhanced by [16][17][18]. e fundamental frequency and its harmonic energy are eliminated from the original spectrum after a fundamental frequency is found.…”

Section: Introductionmentioning

confidence: 99%

Mobile Music Recognition based on Deep Neural Network

Zhang

2022

Mobile Information Systems

View full text Add to dashboard Cite

The piano, as the king of playing instruments, is the most popular instrument for people to learn to play. Learning to play the piano, on the other hand, necessitates professional instruction and a lot of practice. People do not have enough time for systematic training because of the fast pace of life. At the same time, a lack of professional piano teachers and high tuition fees discourage piano students. If the computer can recognize and evaluate the learner’s piano music in real time, the learner will be able to identify and correct errors in real time. There are currently some music recognition technologies, but the majority of them have the following flaws: first and foremost, the recognition accuracy is poor. Second, the identification process is slow and not real-time. Based on the existing problems, this paper proposes a mobile-based music recognition method. The main work of this paper is as follows: (1) a deep neural network (DNN) is applied to the recognition of piano playing music. The use of deep learning models improves the accuracy of music recognition. (2) In order to make the identification of music easier to use, a mobile application is developed in this paper. The app can be installed on mobile phones and tablets. It can input songs in real-time or offline, outputting misplayed notes and scoring the entire composition. In order to evaluate the effect of this study on music recognition, the experimental part uses multiple models for comparison. The experimental results show that the research in this paper is feasible and effective.

show abstract

Section: Introductionmentioning

confidence: 99%