Audio Segmentation Techniques and Applications Based on Deep Learning

Aggarwal, Shruti; Vasukidevi, G; Selvakanmani, S.; Pant, Bhaskar; Kaur, Kiranjeet; Binegde, Geleta Negasa

doi:10.1155/2022/7994191

Cited by 7 publications

(3 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning models have also been applied in music classification tasks, where models like CNNs and SVMs are utilized to categorize music into genres, moods, or other attributes based on audio features extracted from the music [11][12][13][14][15][16][17][18]. Furthermore, models such as Deep Belief Networks (DBNs) and Recurrent Neural Networks (RNNs) have been employed in music transcription, where the goal is to convert audio signals into musical notation [19][20][21][22][23][24].…”

Section: Descriptions Of Machine Learning In Musicmentioning

confidence: 99%

Analyzing principles and applications of machine learning in music: Emotion music generation, and style modeling

Lam

2024

ACE

View full text Add to dashboard Cite

The combination of machine learning with music composition and production is proving viable for innovative applications, enabling the creation of novel musical experiences that were once the exclusive domain of human composers. This paper explores the transformative role of machine learning in music, particularly focusing on emotion music generation and style modeling. Through the development and application of models including DNNs, GANs, and Autoencoders, this study delves into how machine learning is being harnessed to not only generate music that embodies specific emotional contexts but also to transfer distinct musical styles onto new compositions. This research discusses the principles of these models, their operational mechanisms, and evaluates their effectiveness through various metrics such as accuracy, precision, and creative authenticity. The outcomes illustrate that these technologies not only enhance the creative possibilities in music but also democratize music production, making it more accessible to non-experts. The implications of these advancements suggest a significant shift in the music industry, where machine learning could become a central component of creative processes. These results pave a path to the understanding of the potential and limitations of machine learning in music and forecasts future trends in this evolving landscape.

show abstract

Section: Descriptions Of Machine Learning In Musicmentioning

confidence: 99%

Analyzing principles and applications of machine learning in music: Emotion music generation, and style modeling

Lam

2024

ACE

View full text Add to dashboard Cite

show abstract

“…Audio segmentation is a technique that divides audio signals into a sequence of segments or frames, and each part contains audio information from a speech [36][37][38]. In this study, we present the voice activity detection (VAD) method for segmentation.…”

Section: Segmentationmentioning

confidence: 99%

Open-Source Pipeline for Noise-Resilient Voice Data Preparation

Alim,

Purnapatra,

Khondkar

et al. 2024

Preprint

View full text Add to dashboard Cite

A crucial component for developing an automated speaker or speech recognition system is voice preprocessing, which filters unwanted noise and detects the speech part. This study aimed to develop a computerized model to remove background noise and improve signal quality for future applications. This model was developed on a large longitudinal dataset containing varying real-world noise and validated on both a public dataset and a locally collected test dataset in different environments. An overall voice pre-processing pipeline is presented in this study, including denoising, segmentation, feature extraction, and ease of storage. The backbone of the denoising model is a Kalman filter, where the parameters were obtained from a grid search method; the signal-to-noise ratio (SNR) was used as the performance metric. Also, the segmentation was done to remove the pauses from the audio signal before the feature extraction. Finally, the data was stored as a template with the most common features. The SNR result suggested that the Kalman filter-based proposed method performed successfully across diverse datasets. Thus, this model provides a robust and adaptable solution for real-world scenarios and also ensures the data storing quality for future applications.

show abstract

“…Signal segmentation involves breaking down a continuous speech signal into smaller, more manageable frames. The following are the goals of segmentation: to maintain the speech as a wide-sense stationary (WSS) process for several feature extraction approaches [20], optimize feature extraction and machine learning procedures [27], and identify and isolate the individual speech sounds or words in a continuous stream of speech [28]. Stationarity implies that the statistical properties of the signal remain constant over time.…”

Section: Adaptive Segmentationmentioning

confidence: 99%

Non-Stationarity-Based Adaptive Segmentation Applied to Voice Disorder Discrimination

2023

View full text Add to dashboard Cite

Voice disorders can affect people in all age groups. Vocal health is especially important when voice is used as a work tool, as in the fields of education (teachers), music (singers) and multimedia (journalists). Several researches based on linear and nonlinear models of speech production have attempted to identify the intrinsic characteristics in voices affected by pathologies of organic or functional origin. However, there has been no consensus thus far on the best measure to distinguish a healthy voice from a pathological voice, whether in the diagnosis or treatment phase of a disorder. A common procedure in feature extraction uses a traditional voice segmentation, based on stationary frame sizes. On the other hand, no studies have attempted to analyze how laryngeal pathologies can introduce non-stationary acoustic variations in voice. In this study, the Index of Non-Stationarity (INS) is used to identify frame sizes that can be considered truly stationary for each signal. Healthy voice signals and voice signals affected by pathologies such as paralysis, Reinke's edema and nodules are analyzed, and a comparative analysis of the traditional and INS-based adaptive segmentation is performed. Linear predictive coding (LPC) coefficients, melfrequency cepstral coefficients (MFCC), gammatone-frequency cepstral coefficients (GFCC) and recurrence quantification measures (RQMs) are used as acoustic measures. Classification is carried out by performing a linear discriminant analysis (LDA). The results show that the proposed adaptive segmentation can increase pathology recognition (sensitivity) by up to 18%, for the linear model of speech production.

show abstract

Audio Segmentation Techniques and Applications Based on Deep Learning

Cited by 7 publications

References 49 publications

Analyzing principles and applications of machine learning in music: Emotion music generation, and style modeling

Analyzing principles and applications of machine learning in music: Emotion music generation, and style modeling

Open-Source Pipeline for Noise-Resilient Voice Data Preparation

Non-Stationarity-Based Adaptive Segmentation Applied to Voice Disorder Discrimination

Contact Info

Product

Resources

About