Joaquín Ponferrada

I am a Sound Engineer with a strong educational background in acoustics, digital signal processing and extensive work experience in software development. I am highly skilled in Python (7+ years’ experience), I have experience with front- and back-end frameworks, web-development and cloud computing platforms. I am a responsible, self-motivated and detail-oriented person with a diligent attitude and excellent communication skills. I am excited about the prospect of applying my knowledge, skills and experience in both sound and programming towards creating innovative work.

Speech Analyst - Cognitive Neurosciences Center, UdeSA (2022 – present)

Research laboratory specialized in speech disorders associated with neurodegenerative diseases.

• Management, processing and analysis of audio signals from speech datasets.
• Development of algorithms for audio feature extraction pipelines.
• Application of denoising using Wiener filtering and Deep Learning techniques.
• Extraction of speech-related features for classification applications using Machine Learning models.

R&D Engineer - TELL Toolkit (2023 – present)

SaaS platform that grants patients agency on their brain health via validated automated speech analysis with AI. 

• Research and implementation of audio features into the platform.
• Code writing, unit testing and debugging. 
• API integration using Docker, AWS Lambda and S3.
• Assessment and integration of third-party APIs into the platform.
• Research, prototyping and end-to-end testing of audio preprocessing tools. 

Graduate Degree, Sound Engineering, Universidad Nacional de Tres de Febrero, Buenos Aires, Argentina (2015 – 2023)

Sound Engineering graduate program covering all disciplines relating to sound, including Acoustics, Psychoacoustics, Electronics, Audio Recording and Digital Signal Processing.

My graduate thesis consisted in developing and testing a Virtual Bass Synthesis algorithm with the objective of enhancing bass perception in audio signals exploiting the missing fundamental phenomenon. Towards this end, I studied the implementation of Morphological Component Analysis for separation of tonal and transient signals, which are better processed separately to achieve the enhancement effect.