You can find a searchable list of my publications below. My Google Scholar profile contains an up-to-date overview of my citations. I also have a ResearchGate profile with most of my full-texts.
I am a strong proponent of Open Access, especially after having spent more than four years as a researcher at an institution with a very limited number of journal subscriptions. For each entry below where I am legally allowed to share a full-text, you can find it as the first link of the entry.
2018
Gelderblom, Femke B.; Tronstad, Tron V.; Viggen, Erlend Magnus
Subjective evaluation of a noise-reduced training target for deep neural network-based speech enhancement Journal Article
In: IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 27, no. 3, pp. 583–594, 2018, ISSN: 2329-9290.
Abstract | BibTeX | Tags: machine learning, speech enhancement | Links:
@article{gelderblom_subjective_2018,
title = {Subjective evaluation of a noise-reduced training target for deep neural network-based speech enhancement},
author = {Femke B. Gelderblom and Tron V. Tronstad and Erlend Magnus Viggen},
url = {https://erlend-viggen.no/wp-content/uploads/2018/11/gelderblom_subjective_2018_post-print.pdf, Full-text},
doi = {10.1109/TASLP.2018.2882738},
issn = {2329-9290},
year = {2018},
date = {2018-11-21},
journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
volume = {27},
number = {3},
pages = {583–594},
abstract = {Speech enhancement systems aim to improve the quality and intelligibility of noisy speech. In this study, we compare two speech enhancement systems based on deep neural networks. The speech intelligibility and quality of both systems was evaluated subjectively, by a Speech Recognition Test based on Hagerman sentences and a translation of the ITU-T P.835 recommendation, respectively. Results were compared with the objective measures STOI and POLQA. Neither STOI nor POLQA reliably predicted subjective results. While STOI anticipated improvement, subjective results for both models showed degradation of speech intelligibility. POLQA results were overall hardly affected, while the subjective results showed significant changes in overall quality, both positive and negative, in many of the tests. One of the systems was trained to remove all noise; a strategy that is common in speech enhancement systems found in the literature. The other system was trained to only reduce the noise such that the signal-to-noise ratio increased with 10 dB. The latter system subjectively outperformed the system that attempted to remove noise completely. From this, we conclude that objective evaluation cannot replace subjective evaluation until a measure that reliably predicts intelligibility and quality for deep neural network based systems has been identified. Results further indicate that it may be beneficial to move away from more aggressive noise removal strategies towards noise reduction strategies that cause less speech distortion.},
keywords = {machine learning, speech enhancement},
pubstate = {published},
tppubtype = {article}
}
2017
Gelderblom, Femke B.; Tronstad, Tron V.; Viggen, Erlend Magnus
Subjective Intelligibility of Deep Neural Network-Based Speech Enhancement Presentation
22.08.2017.
BibTeX | Tags: machine learning, speech enhancement | Links:
@misc{gelderblom_subjective_2017b,
title = {Subjective Intelligibility of Deep Neural Network-Based Speech Enhancement},
author = {Femke B. Gelderblom and Tron V. Tronstad and Erlend Magnus Viggen},
url = {https://www.researchgate.net/publication/319243091_Poster_Subjective_intelligibility_of_deep_neural_network-based_speech_enhancement, Poster on ResearchGate},
year = {2017},
date = {2017-08-22},
keywords = {machine learning, speech enhancement},
pubstate = {published},
tppubtype = {presentation}
}
Gelderblom, Femke B; Tronstad, Tron V; Viggen, Erlend Magnus
Subjective Intelligibility of Deep Neural Network-Based Speech Enhancement Proceedings Article
In: INTERSPEECH 2017, pp. 1968–1972, ISCA, 2017.
Abstract | BibTeX | Tags: machine learning, speech enhancement | Links:
@inproceedings{gelderblom_subjective_2017,
title = {Subjective Intelligibility of Deep Neural Network-Based Speech Enhancement},
author = {Femke B Gelderblom and Tron V Tronstad and Erlend Magnus Viggen},
url = {https://www.researchgate.net/publication/319184981_Subjective_Intelligibility_of_Deep_Neural_Network-Based_Speech_Enhancement, Full-text on ResearchGate},
doi = {10.21437/Interspeech.2017-1041},
year = {2017},
date = {2017-01-01},
urldate = {2017-01-01},
booktitle = {INTERSPEECH 2017},
pages = {1968--1972},
publisher = {ISCA},
abstract = {Recent literature indicates increasing interest in deep neural networks for use in speech enhancement systems. Currently, these systems are mostly evaluated through objective measures of speech quality and/or intelligibility. Subjective intelligibility evaluations of these systems have so far not been reported. In this paper we report the results of a speech recognition test with 15 participants, where the participants were asked to pick out words in background noise before and after enhancement using a common deep neural network approach. We found that, although the objective measure STOI predicts that intelligibility should improve or at the very least stay the same, the speech recognition threshold, which is a measure of intelligibility, deteriorated by 4 dB. These results indicate that STOI is not a good predictor for the subjective intelligibility of deep neural network-based speech enhancement systems. We also found that the postprocessing technique of global variance normalisation does not significantly affect subjective intelligibility.},
keywords = {machine learning, speech enhancement},
pubstate = {published},
tppubtype = {inproceedings}
}
This page is powered by the excellent TeachPress plugin for WordPress.