Description

A distant-speech recognition system is fundamental for voice-operated ambient assisted living facilities. A common purpose of such a system is to capture the wave field, locate a speaker (in a crowded room), set a focus (a virtual beam) on it, and enhance its speech.

The system consists of several modules, whereas one module is about locating speakers acoustically. We would like to additionally estimate a speaker’s fundamental frequency during voiced utterances. This enables us to to estimate the location more precisely and to separate speakers in a multi-speaker environment more accurately.

We are currently working on distant-speech recognition applications, where joint estimation of a speaker’s position and its fundamental frequency is an indispensable tool. By now, we have introduced several algorithms to jointly locate a speaker and estimate its fundamental frequency. We need to implement other algorithms to do more comprehensive performance evaluations (benchmarks) and to be able to apply more suitable algorithms to specific problems

Tasks

• Literature review of joint direction and fundamental frequency estimators (see reference).
• Implementation in MATLAB.
• Evaluation of its performance (speech database and speech recognizer provided).
• Report about estimator, experiments, and findings (in English).

Your Profile / Requirements

The candidate should be interested in literature reviews (papers), spatial filtering (acoustic beamforming and target localization), digital non-/linear and statistical signal processing, and MATLAB programming.

References

Jensen, J. R., Christensen, M. G., Jensen, S. H.„ “Joint DOA and Fundamental Frequency Estimation Method based on 2-D Filtering,” in Proc. of 18th European Signal Processing Conference (EUSIPCO- 2010), pp.2091-2095, Aalborg, Denmark, August 23-27, 2010.

Jensen, J. R., Christensen, M. G., Benesty, J., and Jensen, S. H.,, ``Joint Spatio-Temporal Filtering Methods for DOA and Fundamental Frequency Estimation,’’ IEEE Transactions on Audio, Speech, and Language Processing, vol. 23, no. 1, pp.174-185, Aalborg, Jan. 2015.

Gabbrielli, M., ``Nonlinear Least Squares Methods for Joint DOA and Pitch Estimation,’’ Master-Project, Signal Processing and Speech Communication Laboratory, Graz University of Technology, Austria, 2015.

Jensen, J. R., Christensen, M. G., and Jensen, S. H.,, ``Nonlinear Least Squares Methods for Joint DOA and Pitch Estimation,’’ IEEE Transactions on Audio, Speech, and Language Processing, vol. 21, no. 5, pp.923-933, Aalborg, Jan. 2013.

Info

If you would like to write a master thesis about this topic, please contact Hannes Pessentheiner.