The field of Music Information Retrieval (MIR) is witnessing significant developments, particularly in the areas of audio-to-tab guitar transcription, notational error detection, and music emotion recognition. Researchers are proposing innovative frameworks and models to overcome long-standing challenges, such as accurately detecting expressive techniques in guitar recordings and improving the quality of digital music scores. The use of machine learning and deep learning techniques is becoming increasingly prevalent, enabling the development of more accurate and efficient MIR systems. Noteworthy papers include:

• TART, a comprehensive tool for technique-aware audio-to-tab guitar transcription, which generates detailed tablature with accurate fingerings and expressive labels from guitar audio.
• BACHI, a boundary-aware symbolic chord recognition model that achieves state-of-the-art performance on both classical and pop music benchmarks.