Martin E. Malandro
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Martin E. Malandro has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Aaron M. Broussard1 shared publication
- Abagayle Serreyn1 shared publication
- Daniel Rockmore
Dartmouth College
1 shared publication - Douglas Shadle
Vanderbilt University
1 shared publication - Ken Smith
University of Richmond VA now at Google
1 shared publication - Ken W. Smith
Department of Mathematics and Statistics, Sam Houston State University, Huntsville, USA
1 shared publication
Latest Publications
- Open Access
Barwise Section Boundary Detection in Symbolic Music Using Convolutional Neural Networks
Current methods for Music Structure Analysis (MSA) focus primarily on audio data. While symbolic music can be synthesized into audio and analyzed using existing MSA techniques, such an approach does not exploit symbolic music's rich explicit representation of pitch, timing, and instrumentation. A key subproblem of MSA is section boundary detection-determining whether a given point in time marks the transition between musical sections. In this paper, we study automatic section boundary detection for symbolic music. First, we introduce a human-annotated MIDI dataset for section boundary detection, consisting of metadata from 6134 MIDI files that we manually curated from the Lakh MIDI dataset. Second, we train a deep learning model to classify the presence of section boundaries within a fixed-length musical window. Our data representation involves a novel encoding scheme based on synthesized overtones to encode arbitrary MIDI instrumentations into 3-channel piano rolls. Our model achieves an F1 score of 0.77, improving over the analogous audio-based supervised learning approach and the unsupervised block-matching segmentation (CBM) audio approach by 0.22 and 0.31, respectively. We release our dataset, code, and models.
Open AccessBarwise Section Boundary Detection in Symbolic Music Using Convolutional Neural Networks
Current methods for Music Structure Analysis (MSA) focus primarily on audio data. While symbolic music can be synthesized into audio and analyzed using existing MSA techniques, such an approach does not exploit symbolic music's rich explicit representation of pitch, timing, and instrumentation. A key subproblem of MSA is section boundary detection-determining whether a given point in time marks the transition between musical sections. In this paper, we study automatic section boundary detection for symbolic music. First, we introduce a human-annotated MIDI dataset for section boundary detection, consisting of metadata from 6134 MIDI files that we manually curated from the Lakh MIDI dataset. Second, we train a deep learning model to classify the presence of section boundaries within a fixed-length musical window. Our data representation involves a novel encoding scheme based on synthesized overtones to encode arbitrary MIDI instrumentations into 3-channel piano rolls. Our model achieves an F1 score of 0.77, improving over the analogous audio-based supervised learning approach and the unsupervised block-matching segmentation (CBM) audio approach by 0.22 and 0.31, respectively. We release our dataset, code, and models.
- Open Access
The Florence Price Art Song Dataset and Piano Accompaniment Generator
Florence B. Price was a composer in the early 20th century whose music reflects her upbringing in the American South, her African heritage, and her Western classical training. She is noted as the first African-American woman to have a symphony performed by a major orchestra. Her music has recently received renewed attention from both the public and the research community, decades after her death. In addition to other genres, Price was a prolific composer for solo voice and piano. Music historians have documented the existence of 134 art songs and piano/voice arrangements for spirituals and folk songs written by Price. We release a digital catalog of 112 of these works in MuseScore, MusicXML, MIDI, and PDF format. We also use this dataset to fine-tune a symbolic music generation model to generate accompaniments to melodies, and we conduct a blind listening experiment that shows that accompaniments generated by our model are perceived as being reflective of Florence Price's style more frequently than accompaniments generated by a baseline model. We release our model as the Florence Price Piano Accompaniment Generator alongside our dataset.
Open AccessThe Florence Price Art Song Dataset and Piano Accompaniment Generator
Florence B. Price was a composer in the early 20th century whose music reflects her upbringing in the American South, her African heritage, and her Western classical training. She is noted as the first African-American woman to have a symphony performed by a major orchestra. Her music has recently received renewed attention from both the public and the research community, decades after her death. In addition to other genres, Price was a prolific composer for solo voice and piano. Music historians have documented the existence of 134 art songs and piano/voice arrangements for spirituals and folk songs written by Price. We release a digital catalog of 112 of these works in MuseScore, MusicXML, MIDI, and PDF format. We also use this dataset to fine-tune a symbolic music generation model to generate accompaniments to melodies, and we conduct a blind listening experiment that shows that accompaniments generated by our model are perceived as being reflective of Florence Price's style more frequently than accompaniments generated by a baseline model. We release our model as the Florence Price Piano Accompaniment Generator alongside our dataset.
- Open Access
Composer's Assistant 2: Interactive Multi-Track MIDI Infilling with Fine-Grained User Control
We introduce Composer's Assistant 2, a system for interactive human-computer composition in the REAPER digital audio workstation. Our work upgrades the Composer's Assistant system (which performs multi-track infilling of symbolic music at the track-measure level) with a wide range of new controls to give users fine-grained control over the system's outputs. Controls introduced in this work include two types of rhythmic conditioning controls, horizontal and vertical note onset density controls, several types of pitch controls, and a rhythmic interest control. We train a T5-like transformer model to implement these controls and to serve as the backbone of our system. With these controls, we achieve a dramatic improvement in objective metrics over the original system. We also study how well our model understands the meaning of our controls, and we conduct a listening study that does not find a significant difference between real music and music composed in a co-creative fashion with our system. We release our complete system, consisting of source code, pretrained models, and REAPER scripts.
Open AccessComposer's Assistant 2: Interactive Multi-Track MIDI Infilling with Fine-Grained User Control
We introduce Composer's Assistant 2, a system for interactive human-computer composition in the REAPER digital audio workstation. Our work upgrades the Composer's Assistant system (which performs multi-track infilling of symbolic music at the track-measure level) with a wide range of new controls to give users fine-grained control over the system's outputs. Controls introduced in this work include two types of rhythmic conditioning controls, horizontal and vertical note onset density controls, several types of pitch controls, and a rhythmic interest control. We train a T5-like transformer model to implement these controls and to serve as the backbone of our system. With these controls, we achieve a dramatic improvement in objective metrics over the original system. We also study how well our model understands the meaning of our controls, and we conduct a listening study that does not find a significant difference between real music and music composed in a co-creative fashion with our system. We release our complete system, consisting of source code, pretrained models, and REAPER scripts.
- Open Access
Composer's Assistant: An Interactive Transformer for Multi-Track MIDI Infilling
We introduce Composer's Assistant, a system for interactive human-computer composition in the REAPER digital audio workstation. We consider the task of multi-track MIDI infilling when arbitrary track-measures have been deleted from a contiguous slice of measures from a MIDI file, and we train a T5-like model to accomplish this task. Composer's Assistant consists of this model together with scripts that enable interaction with the model in REAPER. We conduct objective and subjective tests of our model. We release our complete system, consisting of source code, pretrained models, and REAPER scripts. Our models were trained only on permissively-licensed MIDI files.
Open AccessComposer's Assistant: An Interactive Transformer for Multi-Track MIDI Infilling
We introduce Composer's Assistant, a system for interactive human-computer composition in the REAPER digital audio workstation. We consider the task of multi-track MIDI infilling when arbitrary track-measures have been deleted from a contiguous slice of measures from a MIDI file, and we train a T5-like model to accomplish this task. Composer's Assistant consists of this model together with scripts that enable interaction with the model in REAPER. We conduct objective and subjective tests of our model. We release our complete system, consisting of source code, pretrained models, and REAPER scripts. Our models were trained only on permissively-licensed MIDI files.
- 27 April 2023
- Published by Taylor & Francis in PRIMUS
- Vol. 33 (8) , 916-937
Ask Your Students Research-Like Questions: Examples from Calculus II
I introduce a teaching method which involves asking students to answer investigative, research-like questions, and I detail my experience with this method in Calculus II in Fall 2019 and Fall 2020. This method is applicable to a range of undergraduate courses, and can be used in both face-to-face and online settings. I give several examples of research-like questions and student responses, I detail some of the benefits and potential pitfalls with this method, and I include in the appendix a complete list of research-like questions asked during the Fall 2020 semester.
- 27 April 2023
- Published by Taylor & Francis in PRIMUS
- Vol. 33 (8) , 916-937
Ask Your Students Research-Like Questions: Examples from Calculus II
I introduce a teaching method which involves asking students to answer investigative, research-like questions, and I detail my experience with this method in Calculus II in Fall 2019 and Fall 2020. This method is applicable to a range of undergraduate courses, and can be used in both face-to-face and online settings. I give several examples of research-like questions and student responses, I detail some of the benefits and potential pitfalls with this method, and I include in the appendix a complete list of research-like questions asked during the Fall 2020 semester.
- 13 September 2019
- Published by Springer Nature in Semigroup Forum
- Vol. 99 (3) , 679-723
Enumeration of finite inverse semigroups
- 13 September 2019
- Published by Springer Nature in Semigroup Forum
- Vol. 99 (3) , 679-723
Enumeration of finite inverse semigroups
- Open AccessPartial Difference Sets in $C_{2^n} \times C_{2^n}$We give an algorithm for enumerating the regular nontrivial partial difference sets (PDS) in the group $G_n = C_{2^n}\times C_{2^n}$. We use our algorithm to obtain all of these PDS in $G_n$ for $2\leq n\leq 9$, and we obtain partial results for $n=10$ and $n=11$. Most of these PDS are new. For $n\le 4$ we also identify group-inequivalent PDS. Our approach involves constructing tree diagrams and canonical colorings of these diagrams. Both the total number and the number of group-inequivalent PDS in $G_n$ appear to grow super-exponentially in $n$. For $n=9$, a typical canonical coloring represents in excess of $10^{146}$ group-inequivalent PDS, and there are precisely $2^{520}$ reversible Hadamard difference sets.Open AccessPartial Difference Sets in $C_{2^n} \times C_{2^n}$We give an algorithm for enumerating the regular nontrivial partial difference sets (PDS) in the group $G_n = C_{2^n}\times C_{2^n}$. We use our algorithm to obtain all of these PDS in $G_n$ for $2\leq n\leq 9$, and we obtain partial results for $n=10$ and $n=11$. Most of these PDS are new. For $n\le 4$ we also identify group-inequivalent PDS. Our approach involves constructing tree diagrams and canonical colorings of these diagrams. Both the total number and the number of group-inequivalent PDS in $G_n$ appear to grow super-exponentially in $n$. For $n=9$, a typical canonical coloring represents in excess of $10^{146}$ group-inequivalent PDS, and there are precisely $2^{520}$ reversible Hadamard difference sets.
- 1 January 2016
- Published by Taylor & Francis in The American Mathematical Monthly
- Vol. 123 (10)
Optimizing the Video Game Multi-Jump: Player Strategy, AI, and Level Design
This article initiates the mathematical study of multi-jumping in video games. We begin by proving a necessary, and frequently sufficient, condition for a multi-jump to be optimal, i.e., achieve th...
- 1 January 2016
- Published by Taylor & Francis in The American Mathematical Monthly
- Vol. 123 (10)
Optimizing the Video Game Multi-Jump: Player Strategy, AI, and Level Design
This article initiates the mathematical study of multi-jumping in video games. We begin by proving a necessary, and frequently sufficient, condition for a multi-jump to be optimal, i.e., achieve th...
- Open Access
Enumeration of finite inverse semigroups
We give an efficient algorithm for the enumeration up to isomorphism of the inverse semigroups of order n, and we count the number S(n) of inverse semigroups of order n<=15. This improves considerably on the previous highest-known value S(9). We also give a related algorithm for the enumeration up to isomorphism of the finite inverse semigroups S with a given underlying semilattice of idempotents E, a given restriction of Green's D-relation on S to E, and a given list of maximal subgroups of S associated to the elements of E.
Open AccessEnumeration of finite inverse semigroups
We give an efficient algorithm for the enumeration up to isomorphism of the inverse semigroups of order n, and we count the number S(n) of inverse semigroups of order n<=15. This improves considerably on the previous highest-known value S(9). We also give a related algorithm for the enumeration up to isomorphism of the finite inverse semigroups S with a given underlying semilattice of idempotents E, a given restriction of Green's D-relation on S to E, and a given list of maximal subgroups of S associated to the elements of E.
- Open Access
Fourier inversion for finite inverse semigroups
This paper continues the study of Fourier transforms on finite inverse semigroups, with a focus on Fourier inversion theorems and FFTs for new classes of inverse semigroups. We begin by introducing four inverse semigroup generalizations of the Fourier inversion theorem for finite groups. Next, we describe a general approach to the construction of fast inverse Fourier transforms for finite inverse semigroups complementary to an approach to FFTs given in previous work. Finally, we give fast inverse Fourier transforms for the symmetric inverse monoid and its wreath product by arbitrary finite groups, as well as fast Fourier and inverse Fourier transforms for the planar rook monoid, the partial cyclic shift monoid, and the partial rotation monoid.
Open AccessFourier inversion for finite inverse semigroups
This paper continues the study of Fourier transforms on finite inverse semigroups, with a focus on Fourier inversion theorems and FFTs for new classes of inverse semigroups. We begin by introducing four inverse semigroup generalizations of the Fourier inversion theorem for finite groups. Next, we describe a general approach to the construction of fast inverse Fourier transforms for finite inverse semigroups complementary to an approach to FFTs given in previous work. Finally, we give fast inverse Fourier transforms for the symmetric inverse monoid and its wreath product by arbitrary finite groups, as well as fast Fourier and inverse Fourier transforms for the planar rook monoid, the partial cyclic shift monoid, and the partial rotation monoid.