At this year’s IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Audio Analytic’s Head of Research, Dr Çağdaş Bilen, will be speaking alongside fellow experts from Amazon Lab 126, Meta, Sonos, IBM and others.

As one of the event’s Industry Expert sessions, Çağdaş will talk about the importance of decision post-processing in temporal ML problems.

In his synopsis, Çağdaş commented: “Models are often designed and optimized to estimate instantaneous probabilities and rely on ‘ad-hoc decision post-processing’ to determine the occurrence of events. Within the constraints of commercial deployment, the impact of post-processing on the final performance of the product can be significant, sometimes reducing errors by orders of magnitude.”

He continued, “However, these constraints are often ignored in academic challenges and publications. Therefore the focus is mainly on improving the performance of the ML models. Furthermore, both in academia and industry, the design and optimization of the ML models often disregards the effect of such decision post-processing, hence potentially leading to suboptimal performance and products.”

You can read more about Çağdaş’s presentation ‘Closing the Gap Between Probabilities and Decisions in Temporal Detection and Classification’ and the other speakers here on the ICASSP website.

ICASSP 2022 takes place virtually and in Singapore between May 7th and 27th. For more information and to register, visit