• B. M. Van Doren, V. Lostanlen, A. Cramer, J. Salamon, A. Dokter, S. Kelling, J. P. Bello, and A. Farnsworth, "Automated acoustic monitoring captures timing and intensity of bird migration," Journal of Applied Ecology, 2022.


• A. Cramer, M. Cartwright, F. Pishdadian, and J. P. Bello, "Weakly Supervised Source-Specific Sound Level Estimation in Noisy Soundscapes," WASPAA 2021 - 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), (New Paltz, New York, USA), 2021.


• M. Cartwright, A. Cramer, A. Mendez, Y. Wang, H. Wu, V. Lostanlen, M. Fuentes, G. Dove, C. Mydlarz, J. Salamon, O. Nov, and J. P. Bello, "SONYC-UST-V2: An Urban Sound Tagging Dataset with Spatiotemporal Context," Detection and Classification of Acoustic Scenes and Events 2020, 2020.


• A. Cramer, V. Lostanlen, A. Farnsworth, J. Salamon, O. Nov, and J. P. Bello, "Chirping up the right tree: incorporating biological taxonomies into deep bioacoustic classifiers," ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020.


• M. Cartwright, A. Mendez, A. Cramer, V. Lostanlen, G. Dove, H. Wu, J. Salamon, O. Nov, and J. P. Bello, "SONYC Urban Sound Tagging (SONYC-UST): a multilabel dataset from an urban acoustic sensor network," Detection and Classification of Acoustic Scenes and Events 2019, 2019.


• V. Lostanlen, K. Palmer, E. Knight, C. Clark, H. Klinck, A. Farnsworth, T. Wong, A. Cramer, and J. Bello, "Long-distance detection of bioacoustic events with per-channel energy normalization," Detection and Classification of Acoustic Scenes and Events 2019, 2019.


• M. Cartwright, A. Cramer, J. Salamon and J. P. Bello, "TriCycle: audio representation learning from sensor network data using self-supervision," WASPAA 2019 - 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), (New Paltz, New York, USA), 2019.


• A. Cramer, H. Wu, J. Salamon and J. P. Bello, "Look, Listen, and Learn More: Design Choices for Deep Audio Embeddings," ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, United Kingdom, 2019, pp. 3852-3856.


• C. Summers, G. Tronel, A. Cramer, A. Vartakavi, and P. Popp, "GNMID14: A Collection of 110 Million Global Music Identification Matches," in Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’16, (New York, NY, USA), pp. 693–696, ACM, 2016.


• O. Oreifej, A. Cramer, and A. Zakhor, "Automatic Generation of 3D Thermal Maps of Building Interiors," in ASHRAE, 2014.

• Weakly Supervised Source-Specific Sound Level Estimation: An implementation of source level estimation models trained using weak supervision with clip-level source class presence.


• BirdVoxClassify: Open source library for classifying bird species from audio recordings of bird flight calls.


• SONYC-UST: Urban sound classification dataset, released as part of the DCASE 2019 Challenge Task 5: Urban Sound Tagging.


• openl3: Open source library providing implementation and pretrained models of the Look, Listen, Learn embedding models.


• TideGAN: Audio timbre transfer using CycleGAN with WaveGAN-style generators and discriminators.


• PyTorch WaveGAN implementation: An implementation of WaveGAN using PyTorch.


• Identifying and reducing gender bias in word-level language models: Code for analyzing gender bias in text corpora and training word-level RNN language models with a regularizer that penalizes gender bias in the embedding layer.


• Deep beat tracking and tempo estimation: Beat tracking and tempo estimation using deep learning, using raw audio as the input to the network. Based off of methods from Sebastian Böck et al.


• audiosetdl: Scripts for downloading the AudioSet dataset from Google.


• L3 Embedding: Implementation of the Look, Listen, Learn model and models for the down-stream task of urban sound classification. Part of the SONYC project.


• Stream instrument source separation: PLCA-based source separation of musical instruments on streamed audio.

• A. Vartakavi, C.Y.R. Gil, A. Gopakumar, J. Cramer, "Methods and apparatus to generate recommendations based on attribute vectors." May 27 2021. US Patent App. 16/695,169.


• M. Cremer, J. Cramer, P. Popp, and C. Summers, "Responding to remote media classification queries using classifier models and context parameters," July 6 2017. US Patent App. 15/185,616.


• J. Cramer, M. Cremer, P. Popp, and C. Summers, "Model-based media classification service using sensed media noise characteristics," July 6 2017. US Patent App. 15/185,654

• ambientMIDI: Render a song from a MIDI file using environmental sound events.


• personal bash scripts: bash scripts I use on Ubuntu for convenience; mostly for audio and keyboard control


• MarkovMixer: Real-time Markov chain mashup program, with transition probabilites based on cross-correlation similarity. Made as a starter template for EE 126 class projects.


• fortissimo: Simple programming language for music composition, implemented in Python and with Overtone as the synthesis backend.


• PandaPhone: Ambient generative instrument using a Leap Motion controller and Max MSP. Hand gestures modify note and velocity transition probabilities learned from MIDI data.


• Augmented reality digital audio workstation: Hackathon proof-of-concept for synthesizers controlled by augmented reality knobs.