Communication sciences » Speech communication
Engineering » Sound engineering
Organisation/Company: University of Zurich
Department: Department of Computational Linguistics
Research Field: Communication sciences » Speech communication, Engineering » Sound engineering, Physics » Acoustics, Language sciences » Linguistics
Researcher Profile: First Stage Researcher (R1) Positions PhD Positions
Country: Switzerland
Application Deadline: 15 Mar 2025 - 23:59 (Europe/Zurich)
Type of Contract: Temporary
Job Status: Full-time
Hours Per Week: 42
Offer Starting Date: 1 Aug 2025
Is the job funded through the EU Research Framework Programme? Horizon Europe - MSCA Marie Curie Grant Agreement Number 101168998
Is the Job related to staff position within a Research Infrastructure? No
Offer Description Zurich University offers 1 Doctoral Candidate position as part of the EU-funded MSCA Doctoral Network project titled VoCS. The position is set to begin between August and October 2025, with a contract duration of 36 months .
The Voice Communication Sciences (VoCS) project is a groundbreaking initiative that aims to position Europe at the forefront of Voice Research. Its primary goal is to equip Doctoral Candidates with integrated knowledge spanning cognitive neuroscience, acoustics, phonetics, and computing science, via a unique combination of hands-on research training in labs, with cross-sectorial workshops in fundamental, technological, and clinical domains relevant to voice communication.
DC19 research topic: Temporal Voice Specific Properties for Forensic Speaker Comparison
Voice recognition technology to date has particularly exploited spectral information in the speech signal. However, individuals also exhibit distinctive temporal attributes within their speech, most likely as a result of individual movement behavior of the speech articulators. In this project, we will model temporal characteristics of the speech signal from varying frequency bands using a variety of techniques (e.g. modulation spectrum, discrete cosine transform). We will extract temporal coefficients which contain maximal speaker specific information from a variety of temporal properties like amplitude or harmonicity envelopes.
The project aims at understanding (a) the performance of temporal coefficients in automatic voice recognition and how they compare to/enhance MFCC-based acoustic models and (b) how the techniques can be used in forensic voice analysis environments where spectral information is often heavily reduced.
The DC will be hosted at the Department of Computational Linguistics of the University of Zurich, under the co-supervision of Volker Dellwo, Elisa Pellegrino and Srikanth Madikeri. The DC will spend 10 months of the doctorate at the University of Eastern Finland with co-supervisor Tomi Kinnunen and the National Institute of Informatics in Japan with co-supervisor Junichi Yamagichi to develop and set up a testing battery of temporal measures for voice recognition.
Research Field: Communication sciences » Speech communication
Education Level: Master Degree or equivalent
Skills/Qualifications Scientific enthusiasm, and a specific interest in the above research project.
Expertise in speech signal processing and technological applications of speech processing.
Background (e.g. MA, MSc) in Speech and/or Voice Sciences, Engineering (Audio, Electronics, etc.), Speech Signal Processing, Phonetics, or equivalent.
English language: Candidates must demonstrate their ability to understand and express themselves proficiently in both written and spoken English, in order to fully benefit from the network training.
Ability and motivation to collaborate within teams of researchers from various fields (e.g., psychology, neuroscience, communication science, computer science, auditory science).
Specific Requirements Desired: Experience with speech data analysis in forensic contexts.
Desired: Experience with temporal processing methods of speech signals.
Languages: ENGLISH Level Excellent
Years of Research Experience: 1 - 4
Additional Information Successful Doctoral Candidates will be part of an international and interdisciplinary network.
Recruited researchers will benefit from training modules, transferable skills courses, secondments, and participation in workshops and conferences.
An exciting job with creative leeway.
University healthcare promotion and a family-friendly environment with flexible working hours.
Financial package: (a) PhD funding for 36 months; (b-c) Living and Mobility Allowances: 57473 CHF (gross amount, country coefficient applies); (d) Family allowance: 7628 CHF (if applicable)
Eligibility criteria Degree: At the date of the recruitment, candidates must be in possession of a Master’s degree in a relevant field and should not have been already awarded a doctoral degree. Applicants must have submitted their master’s or equivalent thesis in relevant fields. The diploma/certificate must be forwarded as soon as it is received. Researchers who have successfully defended their doctoral thesis but who have not yet formally been awarded the doctoral degree will not be considered eligible.
Recruited researchers can be of any nationality but must not have resided or carried out their main activity (work, studies, etc.) in the country of their host organization for more than 12 months in the 3 years immediately prior to their recruitment. Short stays, such as holidays, are not taken into account.
Selection process The offer respects an equal opportunities policy. The required competencies, working conditions and career development prospects are presented to the applicants.
The call for Applications opens at the beginning of February 2025 and closes mid-March 2025.
Once the call has closed, the candidates will be pre-selected according to several eligibility criteria.
Pre-selected candidates will be interviewed in April 2025.
The selected Doctoral Candidates are recruited by the individual Beneficiaries of VoCS project, with starting date between August and October 2025. They will be enrolled in the VoCS Doctoral Network after signing their contract.
Additional comments Host supervisors and contacts at the Department of Computational Linguistics of the University of Zurich:
#J-18808-Ljbffr