About the Lab

Background

The Speech and Music Information Retrieval (shMIR) Lab is a research and innovation group dedicated to advancing knowledge in Speech Processing, Audio Signal Processing, Music Information Retrieval (MIR), Bioacoustics, and Artificial Intelligence. The lab serves as a collaborative platform where students and researchers explore contemporary challenges in audio intelligence through research, experimentation, software development, and interdisciplinary collaboration.

Beyond research publications, the lab emphasizes experiential learning, critical thinking, reproducible research, and the development of practical solutions that benefit academia, industry, and society. By integrating research with education and outreach, the shMIR Lab aims to nurture future researchers and innovators while contributing to the broader scientific community.

Vision

To build a vibrant ecosystem where students learn, create, innovate, and contribute to the advancement of Speech, Music, Audio, and Bioacoustic Intelligence through research, laboratory development, education, and community engagement.

Mission

The shMIR Lab is committed to nurturing a culture of curiosity, innovation, and lifelong learning by providing students with opportunities to engage in meaningful research, develop laboratory experiments and educational resources, contribute to open-source software and datasets, organize workshops and outreach activities, and collaborate on interdisciplinary projects in speech, music, audio, and bioacoustic intelligence. The lab strives to cultivate strong technical competence, critical thinking, ethical research practices, teamwork, leadership, and effective scientific communication, enabling students to grow into confident professionals and independent researchers while creating solutions that benefit academia, industry, and society. The lab believes that meaningful innovation begins with deep understanding, sustained effort, and responsible collaboration. 

What we do?

The shMIR Lab actively engages in:

• Research in Speech Processing, Music Information Retrieval, Audio Intelligence, Bioacoustics, and Artificial Intelligence.

• Development of algorithms, software tools, and intelligent systems for audio analysis.

• Preparation of high-quality journal and conference publications.

• Development of educational laboratory experiments, demonstrations, and learning resources.

• Organization of workshops, tutorials, expert talks, and technical training programmes.

• Participation in national and international research challenges and competitions.

• Development of open-source software, datasets, and reproducible research resources.

• Mentoring undergraduate, postgraduate, and doctoral students through collaborative research.

• Promoting interdisciplinary collaboration with academia, industry, and research organizations.