Signal Processing Commons^™

Transformer-Based Symbolic Music Generation, Ben Buentello

Master’s Theses

This thesis investigates the capacity of transformer-based architectures to learn generalized musical patterns through symbolic generation. To support this exploration, a complete music generation pipeline was developed, beginning with the construction and classification of a large-scale dataset of over 170,000 MIDI files. The dataset was processed using rule-based heuristics and custom neural classifiers to separate tracks by musical function and contour. A novel tokenization scheme, MINTii, was introduced to encode musical information compactly through interval-based representations, reducing redundancy and promoting generalization. Using this infrastructure, a transformer model was trained to generate single-track melodic sequences. Its performance was evaluated through both …

4-Band Personal Eq Device, Carson Kellerman

Electrical Engineering

The device is a 4-band EQ with 3.5mm audio input and output jacks. The device has 4 adjustable EQ bands. Each of the 4 bands are adjustable via knob potentiometers, and are able to boost or cut their respective center frequencies of 150Hz, 400Hz, 2500Hz, and 10kHz from -15dB to +15dB. The device is battery powered off of 1 9V battery and is able to function for 10 hours before needing to replace the batteries. The device has a Total Harmonic Distortion of less than 1% and a Signal to Noise Ratio greater than 60dB. Overall, this device allows music …

Cyberinet: Integrated Semi-Modular Sensors For The Computer-Augmented Clarinet, Matthew Bardin

LSU Doctoral Dissertations

The Cyberinet is a new Augmented instrument designed to easily and intuitively provide a method of computer-enhanced performance to the Clarinetist to allow for greater control and expressiveness in a performance. A performer utilizing the Cyberinet is able to seamlessly switch between a traditional performance setting and an augmented one. Towards this, the Cyberinet is a hardware replacement for a portion of a Clarinet containing a variety of sensors embedded within the unit. These sensors collect various real time data motion data of the performer and air fow within the instrument. Additional sensors can be connected to the Cyberinet to …

Standalone Wireless Humming Music Synthesizer, Elizaveta Viktorovna Koush, Conrad Kinsey, Alberto Munoz

Electrical Engineering

This project, called a standalone wireless humming music synthesizer, aimed to provide a tool for musicians to make creating music easier. It did this by removing learning barriers and adding an assistive functionality element that current synthesizers fail to address.

Existing methods for synthesizers typically include a keyboard or some collection of buttons to play melodies on. This requires the knowledge of music theory and a learning curve for the instrument, and this device aims to tackle this barrier. A device that can synthesize your voice into high-quality audio removes this musical knowledge barrier and allows anyone to easily convert …

Hum Synthesizer, Daniel Keith Mcfall, Jason Chang

Electrical Engineering

Most modern music, especially the popular and rising genres such as pop music and rap music are more reliant on music synthesizers than ever before. While other instruments are readily used to sample background noises, the main form of sound generation is becoming more digital rather than using acoustic instruments. However, many people that want to make music aren’t familiarized with traditional music theory and would have difficulty using a traditional synthesizer. The Hum Synthesizer aims to allow a wider audience to access the functions of a traditional synthesizer by using voice controls rather than keyboard controls. If the user …

Music Synthesizer Senior Project: Individual Report, Bryan Bellin

Electrical Engineering

No abstract provided.

Music Synthesizer Senior Project: Danalog, Vikrant A. Marathe

Electrical Engineering

The Danalog is a 25 key portable digital music synthesizer that uses multiple synthesis methods and effects to generate sounds. Sound varieties included three synthesis methods including FM, subtractive, and sample-based, with up to eight adjustable parameters, at least four effects, including reverb, chorus, and flange, with five adjustable parameters, and at least two note polyphony, and a five band equalizer. The user would be able to adjust these effects using digital encoders and potentiometers and view the settings on two LCD screens. The finals project was unable to meet the original design requirements. The FM synthesis method was primarily …

Danalog: Digital Music Synthesizer, Evan R. Lew

Electrical Engineering

The Danalog is a 25 key portable digital music synthesizer that uses multiple synthesis methods and effects to generate sounds. Sound varieties included three synthesis methods including FM, subtractive, and sample-based, with up to eight adjustable parameters, at least four effects, including reverb, chorus, and flange, with five adjustable parameters, and at least two note polyphony, and a five band equalizer. The user would be able to adjust these effects using digital encoders and potentiometers and view the settings on two LCD screens.

The finals project was unable to meet the original design requirements. The FM synthesis method was primarily …

Multiplicative Feedback Audio Distortion Circuit, Colton Parsons

Electrical Engineering

This circuit aims to distort an audio signal input in a novel and aesthetically pleasing manner. When it comes to the timbre of a note, even harmonics generally sound better than odd harmonics. Most forms of audio signal distortion (usually for electric guitar) primarily add odd harmonics to a signal, as this is easily accomplished by clipping the waveform. This project instead utilizes a signal multiplier in a feedback loop, with one multiplier input coming from the circuit’s input, and the other from the multiplier’s own output. This process creates even harmonics. A delay line is placed in the loop, …

Locating Tune Changes And Providing A Semantic Labelling Of Sets Of Irish Traditional Tunes, Cillian Kelly, Mikel Gainza, David Dorran, Eugene Coyle

Conference papers

An approach is presented which provides the tune change loactions within a set of Irish traditional turnes. Also provided are semantic labels for each part of each tune within the set. A set in Irish traditional music is a number of individual tunes played segue. Each of the tunes in the set are made up of structural segments called parts. Musical variation is a prominent characteristic of this genre. However, a certain set of notes known as "set accented tones" are considered impervious to musical variation. Chroma information is extracted at "set accented tone" locations within the music. The resulting …

Audio Thumbnail Generation Of Irish Traditional Music, Cillian Kelly, Mikel Gainza, David Dorran, Eugene Coyle

Conference papers

An approach is presented which generates an audio thumbnail of Irish traditional music. An audio thumbnail is consered to be the most representative segment of the music. For popular music, the chorus is considered to be an ideal audio thumbnail, however in Irish Traditional Music there is no chorus. An Irish Traditional tune consists of tow or mor short structural segments called parts. Parts are repeated to extend the tuen, and the tune itself is also repeated once or more in its entirety. To further extend a performance, tunes are concatenated to form a set of tuens. As a result, …

Towards A Method To Determine The Glottal Formant Parameters Of Voiced Speech Without Time-Domain Reference, Alan O'Cinneide, David Dorran, Mikel Gainza, Eugene Coyle

Conference papers

This paper presents an approach to estimate the glottal formant parameters of the voicing source in the frequency-domain. The method is based on a simplified pole-zero interpretion of the prevalent Liljencrants-Fant (LF) model of glottal flow, and gives approximations for a broad range of pulses shapes. An advantage of the method is that, unlike other methods, it does not rely on time-domain references.

Automatic Musical Meter Detection, Mikel Gainza

Conference papers

A method that automatically estimates the metrical structure of a piece of music is presented. The approach is based on the generation of a beat similarity matrix, which provided information about the similarity between any two beats of a piece of music. The repetitive structure of most music is exploited by processing the beat similarity matrix in order to identify similar patterns of beats in different parts of a piece. This principles proves to be equally effective for the detection of both duple and triple meters as awll as complex meters. The use of beat positions and dynamic programming techniques …

The Annotation Of Traditional Irish Dance Music Using Matt2 And Tansey, Bryan Duggan, Brendan O'Shea, Mikel Gainza, Padraig Cunningham

Conference papers

Current estimates put the canon of traditional Irish dance tunes at least 7,000 compositions. Given this diversity, a common problem faced by musicians and ethnomusicologists is identifying tunes from recordings. This is evident even in the number of commercial recordings whose title is gan aimn (without name). This work attempts to solve this problem by developing a Content Based Music Information Retrieval (CBMIR) System adapted to the characteristics of traditional Irish music. A system is presented called MATT2 (Machine Annotation of Traditional Tunes) whose primary goal is to annotate recordings of traditional Irish dance music with useful meta-data including tune …

Blind Source Separation And Automatic Transcription Of Music Using Tensor Decompositions, Derry Fitzgerald

Conference papers

Recent advances in the use of tensor decompositions for the analysis of music are described. In particular, the use of such decompositions for sound source separation and the automatic transcription of music are explored.