Lofty Consulting - Case studies

Some of our past and present projects :

Cochlear implants

> Developed several novel DSP algorithms running on the device for improving speech clarity, managing tinnitus, microphone diagnostics etc.

> Designed and trained an efficient machine learning classifier for audio scenes

> Performed acoustical measurements in anechoic chambers

> Performed various R&D tasks and technological improvements of the device

Dolby.io

> Researched and developed a deep learning audio content classifier for Dolby.io

> Provided general software development to the Dolby.io team (Python, Git, Docker, Gitlab, continuous integration testing etc.)

> Performed optimization and profiling of DSP code used in Dolby.io on AWS instances

Audio processing plug-in for Windows 10

> Contributed to the development of a Windows 10 audio processing plug-in (APO) that is used in call centers to protect workers from hearing injuries.

Conference phone system

> Created a real-time PC-based VOIP software to demonstrate and test a prototype conference phone apparatus.

> Implemented noise cancellation and acoustic echo cancellation algorithms.

> Performed acoustical validation of system.

Nurse call handset

> Designed an electro-acoustic solution to improve the audio performance of a nurse call handset used in hospitals.

> Performed acoustical measurements and acoustic software simulations

> Loudspeaker enclosure design

Skywalker sound

> Researched and developed a deep learning based system for automating and facilitating the sound mixing of movie and series at Skywalker sound (a Disney company) in Nicasio, California.

> Use of Tensorflow, Keras, Pytorch and other software libraries.

> Ingestion of very large datasets.

.

Dolby Atmos (headphone virtualizer)

> Performed software engineering (C language) for the Dolby Atmos headphone rendering engine.

> Worked with both the research and engineering teams at Dolby.

> Reconciled very complex code bases made of C, Matlab and Python.

> Our code now runs on thousand of consumer electronic devices as part of Dolby Atmos (Xbox game console, Samsung phones etc.)

> Created new system tests with Python (Pytest) running on a CI server (continuous integration)

Biointellisense : wearable health

> Performed core R&D and generated intellectual property for an FDA approved device

> Developed a cloud-based symptom classifier

> Devised a light-weight, highly robust step counting and gait analysis algorithm able to run on micro-controllers

Loneliness detector (wearable device)

> Designed a wearable device to monitor the loneliness / social isolation in older people by detecting conversations using machine learning

> Developed the prototype devices from zero: sourcing of components, 3D printing CAD design, embedding electronic programming (Arduino nano edge 33), dataset creation, machine learning model development and training

> Devised an encryption scheme to preserve user privacy

Irritable bowel syndrome detector

> Created an unsupervised machine learning framework for the analysis of intestinal sounds in order to better understand irritable bowel syndrome (IBS)

> Performed Exploratory data analysis on a large dataset of bowel sounds

Sound tuning for tablet

> Performed acoustical measurements of the Lumin tablet in anechoic chamber

> Devised inverse frequency response filters to improve the frequency response of the tablet

Smart urinary flow meter

> Performed core R&D for a connected medical device that measures urinary flow.

> Implemented a sensor and physics model and derived algorithms that measure liquid flow and volume from sensor data.

> Created stand alone executable programs for demonstration purpose.

Below are some of the clients that we have helped: