ESR9 : Acoustic-phonetic alignment in synthetic speech

PhD fellowship

Objectives:

To discover whether there is a benefit from employing acoustic-phonetic alignment in synthetic speech. Here, alignment refers to changes in pronunciation (e.g., vowel space) or prosody (e.g., pitch range, speaking rate). It is already possible to control these and related factors such as vocal tract length in Hidden Markov Model (HMM) speech synthesis, using machine learning methods previously developed by UEDIN and its collaborators. Possible applications are human-machine dialogue and human-human interaction where one of the humans is using a voice-output communication aid. Changing vocal tract length and pitch range gives control over perceived gender.


Expected results:

Extension of control techniques from HMM to the latest Deep Neural Network synthesis, providing controllable high-quality synthetic speech for use in experiments; control of this system using vocal tract length, vowel space and prosody measured (using already-available signal processing methods) from the human interlocutor’s speech; initial results regarding the effects on listeners of controlling the above factors, in a non-interactive situation; final results regarding the effectiveness of acoustic-phonetic alignment on interlocutor behaviour and overall task success / user satisfaction in both simulated human-machine and real human-human interaction scenarios.

Based in Edinburgh, UK

Full-time three-year contract, starting September 2020

PhD enrolment at: University of Edinburgh

Main supervisor’s institution: University of Edinburgh

Main supervisor: Prof Simon King

Secondments:

  • ReadSpeaker, Uppsala: to apply the developed methods to commercial-quality synthetic speech (6 months);
  • University of Helsinki: application to user-adaptive systems for the improvement of second-language pronunciation, in which the teacher (i.e., machine) aligns with particular aspects of the student’s speech: first matching gender, then prosody, then more subtle effects (5 months).

Co-supervisors’ institutions:

  • ReadSpeaker, Uppsala, Sweden
  • University of Helsinki, Finland

Benefits

The ESR will be contractually employed for 36 months by the main institution, and will be covered under the social security scheme of the enrolling country. She/he will monthly receive a Living Allowance, a Mobility Allowance and a Family Allowance (if applicable) compliant with the applicable EC Marie Skłodowska-Curie Actions-ITN general conditions.

The net salary for ESR1 will be about €2.300-2.700 according to her/his situation.

Eligibility criteria:

Experience eligibility requirement: Eligible applicants must be in the first 4 years of their research careers (full-time equivalent research experience) at the signature of the contract (measured from the time the Master’s degree has been obtained).

Eligible applicants must not hold a Doctoral Degree yet.

Mobility eligibility requirement

The fellow must not have resided in the main institution’s country for more than 12 months in the 3 years immediately prior to the recruitment date, and not have carried out their main activity (work, studies, etc.) in that country.

Selection process

February-March 2020: Opening of the call

Applications must be sent to administrative support and contain the following:

  1. An up-to-date CV, without gaps, in order for the selection committee to easily check the mobility and experience requirements. CVs that either do not clearly show the applicant’s past experience, or have gaps, will be considered ineligible;
  2. A letter exposing her/his motivation for a COBRA PhD fellowship, and her preference for two of the fifteen PhD projects proposed in COBRA;
  3. At least 1 reference letter (in English) from one former supervisor and/or lecturer;
  4. The scan of the degree (usually the master’s degree) which would formally entitles her/him to embark on a doctorate, either in the country in which the degree was obtained, or in the country in which the researcher will be recruited. If the degree has not been obtained yet, the applicant will have to provide a declaration of her/his university stating that the degree will be obtained before the expected starting date;
  5. Transcripts of records (document indicating the applicant’s ranking and marks within her/his master’s degree as well as the courses/modules she/he has followed).

Admissions time-line

  • April 2020: Selection & ranking of pre-selected candidates
  • May 2020: pre-selected candidates’ interviews
  • June 2020: Notification of the selected candidates
  • September-October 2020: beginning of contracts

Additional comments

REQUIRED EDUCATION LEVEL: Master’s degree or equivalent
REQUIRED LANGUAGES: ENGLISH (Good)

Specific Requirements:

Applications must be in English and will be evaluated against the following criteria:

  • Educational record;
  • Scientific quality of the applicant’s CV;
  • Expected impact and benefit to the fellow and to the project;
  • Previous experiences in the area of the COBRA research programme.

COBRA supports equal opportunity and encourages female researchers to apply for positions.

In the event that the ESR recruited has a disability such that her/his participation in the project is not possible without extra financial support, the host institution will apply for a dedicated Special Needs Lump Sum allowance (SNLS) to the European Commission.

Scroll to top