-
Research Article
Features, Models, and Applications of Deep Learning in Music Composition
Issue:
Volume 9, Issue 3, September 2025
Pages:
155-162
Received:
20 April 2025
Accepted:
12 June 2025
Published:
15 July 2025
Abstract: Due to the swift advancement of artificial intelligence and deep learning technologies, computers are assuming an increasingly prominent role in the realm of music composition, thereby fueling innovations in techniques for music generation. Deep learning models such as RNNs, LSTMs, Transformers, and diffusion models have demonstrated outstanding performance in the music generation process, effectively handling temporal relationships, long-term dependencies, and complex structural issues in music. Transformers, with their self-attention mechanism, excel at capturing long-term dependencies and generating intricate melodies, while diffusion models exhibit significant advantages in audio quality, producing higher-fidelity and more natural audio. Despite these breakthroughs in generation quality and performance, challenges remain in areas such as efficiency, originality, and structural coherence. This research undertakes a comprehensive examination of the utilization of diverse and prevalent deep learning frameworks in music generation, emphasizing their respective advantages and constraints in managing temporal correlations, prolonged dependencies, and intricate structures. It aims to provide insights to address current challenges in efficiency and control capabilities. Additionally, the research explores the potential applications of these technologies in fields such as music education, therapy, and entertainment, offering theoretical and practical guidance for future music creation and applications. Furthermore, this study highlights the importance of addressing the limitations of current models, such as the computational intensity of Transformers and the slow generation speed of diffusion models, to pave the way for more efficient and creative music generation systems. Future work may focus on combining the strengths of different models to overcome these challenges and to foster greater originality and diversity in AI-generated music. By doing so, we aim to push the boundaries of what is possible in music creation, leveraging the power of AI to inspire new forms of artistic expression and enhance the creative process for musicians and composers alike.
Abstract: Due to the swift advancement of artificial intelligence and deep learning technologies, computers are assuming an increasingly prominent role in the realm of music composition, thereby fueling innovations in techniques for music generation. Deep learning models such as RNNs, LSTMs, Transformers, and diffusion models have demonstrated outstanding pe...
Show More
-
Research Article
Resolving Technological Barriers: Development Strategies for Technological Competitive Intelligence of Technology Based Enterprises
Issue:
Volume 9, Issue 3, September 2025
Pages:
163-170
Received:
3 June 2025
Accepted:
16 June 2025
Published:
16 July 2025
Abstract: In the face of unprecedented global changes, some countries are moving against the trend of globalization, relying on their own technological strength to continuously create technological barriers and disrupt the order of technology enterprises' industrial and supply chains, and have had a serious adverse impact on the recovery of the world economy and the development of high-tech industries. In response to this situation, this article proposes the problems brought about by this situation through literature research, including the need for technology-based enterprises to further strengthen the development of technology competitive intelligence, solve the problems of insufficient technology competitive intelligence institutions, lack of high-level professional talents, and low comprehensive development capabilities of technology competitive intelligence in enterprises. At the same time, this article proposes a practical path to solve the existing problems - by improving the technology competitive intelligence network, establishing technology competitive intelligence agencies, and leveraging the technology competitive intelligence development role of high-tech industrial development zones, the adverse effects of technological barriers on enterprises can be effectively eliminated, and the technological accumulation, research and development, and innovation capabilities of enterprises can be improved. These measures can to some extent alleviate the negative impact of technological barriers and stabilize the industrial and supply chains of high-tech enterprises.
Abstract: In the face of unprecedented global changes, some countries are moving against the trend of globalization, relying on their own technological strength to continuously create technological barriers and disrupt the order of technology enterprises' industrial and supply chains, and have had a serious adverse impact on the recovery of the world economy...
Show More
-
Research Article
A Comprehensive Test Plan for Natural Language Processing Preprocessing Functions
Partha Majumdar*
Issue:
Volume 9, Issue 3, September 2025
Pages:
171-193
Received:
29 July 2025
Accepted:
8 August 2025
Published:
26 August 2025
Abstract: This paper outlines a comprehensive testing strategy for validating key natural language processing (NLP) preprocessing functions, specifically preprocess() and get_tokens(). These functions are vital for ensuring high-quality input data in NLP workflows. Recognising the influence of preprocessing on subsequent model performance, the plan employs a layered testing approach that includes functional, edge-case, negative, and property-based tests. It emphasises goals such as ensuring functional correctness, robustness, semantic integrity, and idempotency, supported by thorough test cases and automation with pytest and hypothesis. By systematically tackling pipeline fragility, this framework aims to ensure the reliability and reproducibility of NLP preprocessing, laying the groundwork for dependable, production-ready language models.
Abstract: This paper outlines a comprehensive testing strategy for validating key natural language processing (NLP) preprocessing functions, specifically preprocess() and get_tokens(). These functions are vital for ensuring high-quality input data in NLP workflows. Recognising the influence of preprocessing on subsequent model performance, the plan employs a...
Show More
