Montevideo, Uruguay · Audio AI · Machine Listening · MIR
Audio AI Research Engineer
HERO BIO PLACEHOLDER — Gabriel will provide final copy.
Projects
Peer-reviewed work first, followed by independent systems and personal technical projects.
Audio AI · VAD · Model evaluation
2025-2026This research evaluates how audio-language models detect speech when the audio is short, noisy, reverberant, or filtered. The project compares Qwen2-Audio-7B, Qwen2-Audio-7B with LoRA, Qwen3-Omni-30B, and Silero VAD on the same degraded test bank. The best result came from Qwen2-Audio-7B with LoRA and OPRO-Template: 93.3% balanced accuracy on 21,340 degraded clips.
Privacy-preserving dataset · Domestic audio
2024Sounds of Home is a residential audio dataset for sound event detection. It contains 1,344 one-hour recordings from 8 homes in Belgium, captured with AudioMoth recorders placed in living rooms and kitchens. Speech was removed before release, and PANNs predictions were provided for the audio frames.
Privacy · Speech removal · WASPAA
2025A framework for removing speech from audio recordings before they are shared or published. The system supports privacy-preserving release workflows for audio datasets while retaining non-speech acoustic information for downstream sound event detection research.
MIR · Harmonic mixing · MSc thesis
2021-2022This music analysis system estimates how well two EDM tracks mix harmonically. It analyzes tracks, computes chroma features, converts them into Tonal Interval Vectors, compares harmonic compatibility, and suggests pitch shifts that can improve a mix. The work began as an MSc thesis and later became an ICWE 2022 publication.
Speech enhancement · Backend platform
2026The ASR Enhancement Platform compares two speech recognition paths on the same audio: raw transcription and enhance-and-transcribe. The backend stores jobs, audio files, transcripts, and provider payloads so each result can be inspected later. It uses FastAPI, Celery, PostgreSQL, Redis, MinIO, Docker Compose, metrics, tracing, Grafana, and CI.
MIR · DJ library organization
2026Traktor ML turns a local Techno and Tech House library into Traktor-ready playlists. The pipeline extracts MERT embeddings, separates stems with Demucs, reads BPM and key metadata with Essentia, clusters similar tracks, orders them for smoother transitions, and exports M3U playlists. The current V4 run processed 239 tracks and exported 14 playlists. The private audio collection is not included in the repo.
Python-based algorithmic trading platform with market data ingestion, risk controls, backtesting, and real-time monitoring.
Raspberry Pi demo for real-time sound event recognition. The system runs pre-trained neural networks on a low-cost edge device, exposes a web interface, and can send email notifications when selected AudioSet events are detected.
Mechanical tool designed during the pandemic to avoid touching shared surfaces directly. It is a physical prototyping project, not an AI project.
IoT handwashing device for industrial environments. The device used stainless steel, WiFi, cloud connectivity, IR/RFID sensors, and a 3-litre tank.
Mobile app project for booking appointments and reducing crowding during the pandemic. My role is shown as Project Manager.
Research / Publications
Thomas Deacon; Jennifer Williams; Jason R. C. Nurse; Christopher Hicks; Gabriel Bibbó; Arshdeep Singh; Mark D. Plumbley
2025 AES International Conference on Artificial Intelligence and Machine Learning for Audio
Gabriel Bibbó; Arshdeep Singh; Mark D. Plumbley
2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), Tahoe City, CA, October 2025
Gabriel Bibbó; Craig Cieciura; Mark D. Plumbley
Proceedings of the 54th International Congress and Exposition on Noise Control Engineering, São Paulo, Brazil, August 2025
Rhys Burchett-Vass; Arshdeep Singh; Gabriel Bibbó; Mark D. Plumbley
2025 AES International Conference on Artificial Intelligence and Machine Learning for Audio
Thomas Deacon; Gabriel Bibbó; Arshdeep Singh; Mark D. Plumbley
Forum Acusticum / Euronoise 2025, Málaga, Spain, June 2025
Arshdeep Singh; Gabriel Bibbó; Thomas Deacon; Haohe Liu; Mark D. Plumbley
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2025), Hyderabad, India, April 2025
Gabriel Bibbó; Arshdeep Singh; Mark D. Plumbley
INTER-NOISE and NOISE-CON Congress and Conference Proceedings, Nantes, France, August 2024
Gabriel Bibbó; Thomas Deacon; Arshdeep Singh; Mark D. Plumbley
8th International Workshop on Speech Processing in Everyday Environments (CHiME 2024), Kos Island, Greece, September 2024
Thomas Deacon; Gabriel Bibbó; Arshdeep Singh; Mark D. Plumbley
International Conference on Sound and Music Computing (SMC 2024), Porto, Portugal, July 2024
Gabriel Bibbó
International Conference on Web Engineering (ICWE 2022), Bari, Italy, July 2022
Gabriel Bibbó
Master thesis, Universitat Pompeu Fabra, Barcelona, Spain, 2021
Gabriel Bibbó
Bachelor thesis, Universidad de la República, Montevideo, Uruguay, 2017
Experience
University of Surrey, Remote
University of Surrey, Guildford, UK
Webhelp, Barcelona, Spain
KPMG, Barcelona, Spain
Ikatu, Montevideo, Uruguay
Formal Education
2020-2021
Universitat Pompeu Fabra, Barcelona, Spain
Master thesis on harmonic compatibility for EDM mixing. Final thesis grade: 9/10.
2010-2017
Universidad de la República, Montevideo, Uruguay
Bachelor thesis on autonomous mobile robots communicated by software-defined radio.
Technical Stack
Additional Information