Fall 2023
We had oral presentations this year. Each team had 15 mintutes for presentation and Q&A. All teams did well. Many projects went beyond what we have covered in class! Final reports and slides can be found below.
| Author | Title | Slides |
| Max Morris & Alex Kim | Stealing Guitar Effects | Slides |
| McCormack Chew & Declan Parker | Guitar Tuning Detection | Slides |
| Huiran Yu | Chorale Music Transcription with Soft DTW Training Loss | Slides |
| Hanna Berger, Anna Boyd, & Izzy Hargrave | JingleBot: Short Form Music Generation with WaveNet | Slides |
| Qixin Deng, Tianyi Zhang, & Boning Wang | AutoMusicians: Polyphonic Music Composition via GPT-4-Powered Multi Agent System | Slides |
| Yuze Wang & Chengkai Kang | Pseudo Autoregressive Inference Using Diffusion Model for Piano Audio Synthesis | Slides |
| Yutong Wen | Audio Content Replication Detection | Slides |
| Anes Macić | Hearing Hearing Loss: Inverting the Auditory Nerve Model | Slides |
Fall 2022
We had oral presentations this year. All the teams did a great job. Their presentations were clear, engaging, and on time! After the presentation session, students had fun interacting with the Interactive Accompaniment System that Yiyang and Joseph developed, using keyboard, saxophone and violin! It's a pity that the group picture didn't size correctly, but everyone is more or less in there!
| Author | Title | Slides |
| Ben Kevelson & Tehgan Murray | Energy-Informed NMF for Polyphonic Piano MIDI Transcription | Slides |
| Seth Roberts | Tablature Estimation of Acoustic Guitar Recordings with a Convolutional Neural Network | Slides |
| William Bellows | Automatic Drum Transcription Using RNN Source Separation and Energy-Based Onset Detection | Slides |
| Cassius Close | GAN-Based Bandwidth Extension for Music | Slides |
| Miller Hickman & Alex Mancuso | Modal Shifting | Slides |
| Noah Miller & Joe Bumpus | Early Investigations Into Real-Time Beatbox Resynthesis Using Non-Negative Matrix Factorization | Slides |
| Yiyang Wang & Joseph Jaeger | An Interactive Computational System to Accompany Jazz Improvisation | Slides |
| Yongyi Zang | An Initial Investigation of the Attack-Specific Artifacts Overfitting Issue in Speech Antispoofing Model | Slides |
Fall 2019
Another year of interesting projects!
Fall 2018
This year the class size reached another new record, and we continued allowing students to work in groups. Here are the interesting projects!
Fall 2017
This year the class size reached a new record, and we allowed students to work with a partner on their final project. These projects were all interesting the presentation session went well!
| Author | Title | Poster | Reviewer 1 | Reviewer 2 | Reviewer 3 |
| Arvind Ramanathan | Beatboxing to Drums using Support Vector Machines | Poster | Jiyuan | Sattwik | Steve |
| Hilary Mogul | Offline Automatic Accompaniment Generation with External Rhythmic Signatures, and Experiments in Automatic Harmonization Algorithms | Poster | Haoyu | Arvind | Jing |
| Haoyu Li & Jiyuan Tian | Polyphonic Fundamental Frequency Estimation Using Score-Informed Source Separation and Probabilistic YIN Algorithm | Poster | Mingqing | Saarish | Jing |
| Isaac Mosebrook | Embedded Speech Recognition System | Poster | Wei | Ye | Arvind |
| Mingqing Yun & Jing Bi | Deep Learning for Musical Instrument Recognition | Poster | Greg | Sattwik | Yujia |
| Gregory Hunkins | Neural Network for Binaural Voice Localization | Poster | Yujia | Yufei | Steve |
| Saarish Kareer & Sattwik Basu | Musical Polyphony Estimation Using Convolutional Neural Networks | Poster | Ye | Wei | Hilary |
| Steve Philbert | Investigation of Source Localization and Beamforming with a Spherical Microphone Array | Poster | Yufei | Greg | Isaac |
| Wei Zhou & Yufei Zhang | Speech Separation in Multi-Channel by ICA and in Monaural by Deep Recurrent Neutral Networks | Poster | Jiyuan | Saarish | Hilary |
| Yujia Yan & Ye He | Speech Enhancement: An Investigation With Raw Waveform | Poster | Haoyu | Isaac | Mingqing |
Fall 2015
Each student worked on an individual course project. Some of the projects were quite interesting. The poster session went well too.
| Author | Title | Poster | Reviewer 1 | Reviewer 2 | Reviewer 3 |
| Iris Ren | Comparing Artificial Intelligence Music and Human Music: A Case Study of Prof. David Cope’s Emmy System | Poster | Steven | Shan | Junzhi |
| Jay Biernat | Instrument Recognition in Polyphonic Mixtures Using Spectral Envelopes | Poster | Jon | Marko | Qiaozhan |
| Jon Downing | Non-Negative Matrix Factorization for Drum Source Separation and Transcription | Poster | Steven | Jay | Shan |
| Junzhi Du | A Method of Query-by-Humming System for Polyphonic Audio | Poster | Qiaozhan | Marko | Jay |
| Marko Stamenovic | Identifying Cover Songs Using Deep Neural Networks | Poster | Iris | Shan | Jon |
| Qiaozhan Gao | Pitch Detection Based Monophonic Piano Transcription | Poster | Jon | Iris | Junzhi |
| Shan Anis | Exploring Automatic Chord Recognition Algorithms | Poster | Junzhi | Jay | Steven |
| Steven Crawford | What Sounds So Good? Maybe, Time Will Tell. | Poster | Marko | Iris | Qiaozhan |
Fall 2014
Each student worked on an individual course project within the field of computer audition. This project turned out to be a great way for students to apply what they learned from the class on the problems that they are interested in. Students' course project reports and posters are posted below. Some of them are quite interesting!
| Author | Title | Poster | Reviewer 1 | Reviewer 2 | Reviewer 3 |
| Bochen Li | Improvement of An Online Music Alignment based on Onset Information | Poster | Mingfeng | Emre | Yuanzhong |
| Hanqing Wen | Onset Detection for Piano Music Transcription based on Neural Networks | Poster | Mingfeng | Bochen | Yuanzhong |
| Mingfeng Zhang | Parametric Analysis of Musical Vibrato in Voice and Instrument Performance | Poster | Emre | Yichi | Hanqing |
| Minhao Zhang | A Real-time Karaoke Scoring System based on Pitch Detection | Poster | Yichi | Bochen | Hanqing |
| Sefik Emre Eskimez | Feature Analysis for Music Genre Classification Task | Poster | Yuanzhong | Hanqing | Minhao |
| Yuanzhong Zheng | Text-Independent Speaker Recognition System | Poster | Yichi | Minhao | Mingfeng |
Fall 2013
The final project in this semester was writing a literature review by summerizing about 20 papers on a topic that the student was interested in. The reviews were supposed to not only summarize the main ideas of the papers, but also present the student's own opinion. The preliminary version of these reviews were commented by three peer students (and the instructor). The comments were addressed in the final version of the reviews, which were written in the ISMIR2013 paper template and are posted here. Some of the reviews are great!
| Author | Title | Reviewer 1 | Reviewer 2 | Reviewer 3 |
| Andrea Cogliati | Melody Perception and Extraction from Audio | Kedar | Sarah | Yi |
| Andrew Trahan | Musical Instrument Recognition in Polytimbral Polyphonic Music Audio Signals | Andrea | Ishaan | Luyang |
| Ishaan Rao | Harmonic Single Channel Source Separation | Kedar | Andrew | Luyang |
| Kedar Patki | Review of Single Channel Source Separation Techniques | Sarah | Yi | Andrea |
| Luyang Li | A Survey of Content-based Music Similarity | Yi | Sarah | Andrew |
| Sarah Smith | Methods and Applications for Segmentation and Description of Musical Transients | Luyang | Ishaan | Andrew |
| Yi Gao | Multi-pitch Streaming: Based on Clustering Algorithms | Kedar | Ishaan | Andrea |