I am super content to have completed another chapter of my professional life as I have recently received my Phd degree after a 4 year-long journey. A journey that thought me many things that I wouldn’t have even imagined to reach from the very beginning. It is a journey that necessitates a strong motivation first, and then the right people and resources to guide you. I am thankful for the many talented people I met, be it researchers, developers or artists in UPF and nearby universities, in Barcelona and the conferences that I visited. I am also glad to have ended this journey with great motivation to keep searching and making things that will benefit others.

I finalized my work supervised by Mireia Farrús and Antonio Bonafonte on the last quarter of 2018. On December 14th, I submitted my thesis titled Incorporating Prosody into Neural Speech Processing Pipelines to the board of doctoral studies of Universitat Pompeu Fabra.

Alp Öktem's thesis submission

Short description of the thesis

In the current era where humans build more and more interaction with machines, prosody still is a less-focused phenomena in systems with natural language understanding. Automatic speech recognition systems give focus on “what is said?” and disregard “how it is said?”, which is many times vital element of human communication. In my thesis, I focused on the recovery of the prosodic information which deals with the “how” an utterance is delivered in speech processing pipelines. I developed my methodologies on two principal use-cases, automatic transcription and spoken language machine translation, and used state-of-the-art neural methods as baselines. My experiments showed the enhancing effect of representing spoken language together with its prosodic features.

Access

The thesis can be accessed through the following repositories:

Defense

My thesis defense took place on 25th of February in UPF with the attendance of the tribunal consisting of David Escudero (Univ. de Valladolid), Francesc Alías (La Salle - URL) and Jordi Adell (Verbio Technologies). You can watch the defense on YouTube as well: