Signal processing/Machine Learning/Audio/Agents
Nanophonics is a signal processing and machine learning studio. We write the maths behind smart audio applications, algorithms and the systems that carry them, and we see it through from the first equation to the shipped product.
Four areas our team specializes in.
Speech recognition, sound event classification, music information retrieval and source separation are all practical uses of machine learning in audio.
If your problem needs a model trained on your own recordings, and that model has to run inside a latency budget, this is the right place to come.
We have an in-depth understanding of the maths and physics behind sound.
A voice pulled out of a noisy room, pitch and tempo estimated from a raw take, a filter that still behaves at the edge of its range. That is the work.
We specialize in everything from real-time audio processing to designing 2D and 3D audio solutions, and we take particular interest in custom VST plugins.
Our team has more than ten years of experience in the audio domain.
Chatbots, assistants, copilots and autonomous pipelines that plan, call tools and act on real systems instead of just answering questions.
Retrieval, tool use, memory, orchestration and evaluation, wired into the models and infrastructure your product already runs.
Media research, smart lighting, music collaboration, medical wearables, heavy industry and city sensing.
Mercury Analytics is a research technology firm in the Washington DC area. Its flagship is M2M dial testing: moment-to-moment response capture for video and audio content, producing frame-accurate sentiment curves.
Our part: audio synchronization algorithms that align respondent reactions to the media content inside their dial-testing and poll analysis platform.
Luke Roberts provides unique directional lighting technology powered by artificial intelligence, to give you the perfect light for any situation.
Our part: senior engineers from Nanophonics provide the machine learning solutions behind this state-of-the-art lamp.
Tyxit lets musicians play together over the internet with latency low enough to stay in time.
Our part: Nanophonics engineers helped develop novel audio codecs and real-time adaptive latency handling, so performance holds up through strong network interruptions and low bandwidth.
Muvr’s proprietary wearable sensors enable real-time joint motion tracking on a smartphone. More than 18,000 data points per minute and intelligent algorithms produce accurate, objective and actionable insight.
Our part: Nanophonics fine-tuned the signal processing algorithms in order to improve patient recovery rates.
FlowCommand is a full-service technology company providing software and hardware for oil & gas companies. Their mission is simple: reduce risk and cost with expertly architected, breakthrough technology.
Our part: we contributed the velocity tracking and prediction technology, through signal processing and algorithm work.
Senzoro is a Vienna-based company doing predictive maintenance with ultrasound and AI, detecting bearing damage, lubrication problems and cavitation on industrial machines.
Our part: machine learning algorithms that predict failures in CNC and similar machines from ultrasonic sensor data.
Leapcraft is a Copenhagen company doing sensing-as-a-service for smart cities and buildings, covering air quality, noise and thermal comfort.
Our part: noise detection and classification algorithms for environmental sensing in cities and buildings.
Small on purpose. The people you meet are the people who write the code.
Algorithms Engineer
Signal processing and algorithms engineer with interests and experience across several domains: biomedicine, acoustics, sensors and IoT.
Freelance consultant in several fields concerning audio applications and signal processing algorithms.
AI & Machine Learning Engineer
Specializing in audio AI, deep learning and generative models, with a strong background in audio signal processing and music technology.
Research interests include generative audio, neural audio codecs and multimodal learning.
AI & Machine Learning Engineer
AI/ML engineer with experience in machine learning, generative AI, and intelligent software systems.
Interests include large language models, audio AI, and applied artificial intelligence.
Mobile Engineer
Software Engineer specialized in iOS development.
Specializing in mobile and web applications, reactive programming, computer graphics and blockchain/crypto.
Tell us what you are trying to measure, hear or predict. We will tell you honestly whether we are the right people.