Audio Segmentation by Spoken Language

A fully funded PhD scholarship is available with the Human-in-the-Loop Analytics (HiLA) program at Monash University, Melbourne, Australia. https://www.monash.edu/graduate-research/partnerships/hila-grip

HiLA is a Graduate Research Industry Partnership (GRIP) that has been established to allow Monash University and its Industry partners to collaborate on common research objectives.
https://www.monash.edu/graduate-research/partnerships/grip
With the support of Monash’ partners, HiLA PhD scholarships are provided with significant benefits beyond other scholarships on offer. These benefits include:

A fully funded PhD scholarship with Monash University that is available for domestic (Australian) and international students. The 3 to 3.5 year award covers all course fees and a $30,000 AUD per year tax-free stipend;
An internship with the Industry partner - where PhD candidates will spend a portion of their candidature located on site and being supported by the partner;
Access to real world problems supported by real world data;
Where the industry partner is located overseas or interstate, travel and accommodation (when working on site with the partner);
Travel and incidental support for conferences;
Enrollment in the HiLA professional development program;

All HiLA PhD scholarships will commence in Semester 2, 2019.

SUPERVISION:
The successful candidate will be supervised by Professor Jon McCormack and Dr. Patrick Hutchings from the Faculty of Information Technology.

PROJECT DETAILS:
The specific project centers around the following research opportunity:

This is a Graduate Research Industry Partnership project run by Monash and Cyara that looks at the classification and segmentation of audio streams by spoken language content. Natural Language Recognition is a very active research area, with applications in telecommunications, robotics and portable computing.


An application of audio segmentation by spoken language will be explored with Cyara’s Interactive Voice Response (IVR) systems that test speech interfaces, which can feature a mixture of languages and require fast classification for interactive responsiveness. For example, an American IVR might present a menu that says “For service in English, press 1. Par español, oprima 2”, with the 2nd spoken phrase being in Spanish. The ability to segment and label audio from these systems by time offset, duration, language and confidence would assist automated testing and system improvement.

Machine learning techniques utilised in this area include support artificial neural networks, vector machines, multi-class logistic regression and Probabilistic Linear Discriminant Analysis and the candidate will be supported and encouraged to explore a range of techniques with an emphasis on responsiveness and accuracy for reduced language set classification ie. classifying the spoken language from a small pool of known language candidates.

As a Graduate Research Industry Partnership project, the candidate will have access to knowledge and resources from Monash University and Cyara, including state-of-the-art machine learning hardware (NVIDIA DGX-1) and access to large scale proprietary datasets. It also provides the opportunity for research to be tested and implemented in solving real-world problems during the project cycle.

This project would suit a candidate with a background in machine learning, especially in the area of speech processing. Experience with deep learning frameworks such as PyTorch, Tensorflow or Caffe is desirable, but not required.

APPLICATION PROCESS
Candidates must fill out the online to Request to Apply form, which can be found at:

https://docs.google.com/forms/d/e/1FAIpQLSdUiAswykQg43s8qIoLfq1eKfiGCZrgnkeoT7IQXOlhdJ8TIg/viewform

Please make sure you indicate that the PhD Topic is “Audio Segmentation by Spoken Language”;

In addition to filling out the form, a copy of your academic transcripts and CV should be emailed to [Email Address Removed].

Applicants must possess a Bachelor’s or equivalent degree with first-class Honours, and/or a distinction in a research Masters degree with relevant experience (e.g., data analysis, artificial intelligence, social informatics, psychology, human-computer interaction or data visualisation). Review of applications will begin immediately and short-listed candidates will be contacted for more information and invited to interview. The successful candidate will be invited to apply to Monash with the deadline for applications being the31st May 2018.

International students that can demonstrate English proficiency are encouraged to apply.