Music information Retrieval (MIR) is an essential part of what I am and what I do. Here are some of my MIR papers.
KL Walls, IR Roman, B Steers, E Georgieva. Total variation in popular rap vocals from 2009-2023: extension of the analysis by Georgieva, Ripollés & McFee. In Extended Abstracts for the Late-Breaking Demo Session of the 24th International Society for Music Information Retrieval Conference. 2023. Pitch variability in rap vocals is overlooked in favor of the genre’s uniquely dynamic rhythmic properties. We present an analysis of fundamental frequency (F0) variation in rap vocals over the past 14 years, focusing on song examples that represent the state of modern rap music.
Roman IR, Faronbi D, Burger-Weiser I, Adu-Gilmore L. F0 analysis of Ghanaian pop singing reveals progressive alignment with equal temperament over the past three decades: a case study. In20th Sound and Music Computing Conference, SMC 2023 2023 (pp. 27-33). Contemporary Ghanaian popular singing combines European and traditional Ghanaian influences. We hypothesize that access to technology embedded with equal temperament catalyzed a progressive alignment of Ghanaian singing with equal-tempered scales over time. To test this, we study the Ghanaian singer Daddy Lumba, whose work spans from the earliest Ghanaian electronic style in the late 1980s to the present.
Faronbi D, Roman I, Bello JP. Exploring Approaches to Multi-Task Automatic Synthesizer Programming. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023 Jun 4 (pp. 1-5). IEEE. Automatic Synthesizer Programming is the task of transforming an audio signal that was generated from a virtual instrument, into the parameters of a sound synthesizer that would generate this signal. In the past, this could only be done for one virtual instrument. In this paper, we expand the current literature by exploring approaches to automatic synthesizer programming for multiple virtual instruments.
Pedroza HE, Meza G, Roman IR. EGFxSet: Electric Guitar Tones Processed Through Real Effects of Distortion, Modulation, Delay and Reverb. In Extended Abstracts for the Late-Breaking Demo Session of the 23rd International Society for Music Information Retrieval Conference. 2022. EGFxSet contains recordings of all clean tones in a Stratocaster guitar, with augmentations by processing through twelve electric guitar effects. Similar datasets apply effects using software, EGFxSet in contrast uses real guitar effects hardware.
O’Brien T, Roman IR. A Recurrent Neural Network for Musical Structure Processing and Expectation. 2016. Research in cognitive neuroscience has identified neural activity correlated with subjects hearing an unexpected event in a musical sequence. Using an augmented data set consisting of music from the western tradition (originally 371 Bach chorales), we trained a Long Short-Term Memory (LSTM) and two Recurrent Neural Network (RNN) architectures to ask: will a neural network show a larger perplexity when presented with an unexpected event in a musical sequence?
Kermit-Canfield E, Roman I. Dance Type Classification in Irish and Scandinavian Folk Music. 2015. For centuries, western cultures have written folk songs down. In the 21st century, this has resulted in large databases of music from all around the world. We have built, trained, and tested classi- fiers on Irish and Scandinavian dance music using songs encoded in symbolic representation (ABC format), downloaded from John Chamber’s online folk-song database.
© 2024 Iran R. Roman