Optimal local rejection for classifiers

L Fischer, B Hammer, H Wersing - Neurocomputing, 2016 - Elsevier
We analyse optimal rejection strategies for classifiers with input space partitioning, eg
prototype-based classifiers, support vector machines or decision trees using certainty …

Feature-space SVM adaptation for speaker adapted word prominence detection

A Schnall, M Heckmann - Computer Speech & Language, 2019 - Elsevier
Prosodic cues such as the word prominence play a fundamental role in human
communication, eg, to express important information. Since different speakers use a wide …

[PDF][PDF] Integrating sequence information in the audio-visual detection of word prominence in a human-machine interaction scenario

A Schnall, M Heckmann - Fifteenth Annual Conference of the …, 2014 - researchgate.net
Modifying the articulatory parameters to raise the prominence of a segment of an utterance
(hyperarticulating) is usually accompanied by a reduction of these parameters …

Audio-visual word prominence detection from clean and noisy speech

M Heckmann - Computer Speech & Language, 2018 - Elsevier
In this paper we investigate the audio-visual processing of linguistic prosody, more precisely
the detection of word prominence, and examine how the additional visual information can be …

Steps towards more natural human-machine interaction via audio-visual word prominence detection

M Heckmann - … Workshop on Multimodal Analyses Enabling Artificial …, 2014 - Springer
We investigate how word prominence can be detected from the acoustic signal and
movements of the speaker's head and mouth. Our research is based on a corpus with 12 …

[PDF][PDF] Inter-speaker variability in audio-visual classification of word prominence.

M Heckmann - INTERSPEECH, 2013 - isca-archive.org
In this paper we present results for the audio-visual discrimination of prominent from non-
prominent words on a dataset with 16 speakers and more than 5000 utterances. We …

[PDF][PDF] Speaker adaptation for word prominence detection with support vector machines

A Schnall, M Heckmann - Speech Prosody, accepted, 2016 - honda-ri.de
In this paper we propose a new speaker adaptation method to improve the detection of
prominent words in speech. Prosodic cues are difficult to extract, due to the different features …

Comparing speaker independent and speaker adapted classification for word prominence detection

A Schnall, M Heckmann - 2016 IEEE Spoken Language …, 2016 - ieeexplore.ieee.org
Prosodic cues are an important part of human communication. One of these cues is the word
prominence which is used to eg highlight important information. Since individual speakers …

Balancing Gaussianity and sparseness in feature-space speaker adaptation for word prominence detection

A Schnall, M Heckmann - Speech Communication; 12. ITG …, 2016 - ieeexplore.ieee.org
Word prominence is an essential part of communication, eg to express important
information. But due to speaker variations, it is difficult to extract these cues. A common …

The impact of word alignment accuracy on audio-visual word prominence detection

M Heckmann, P Mikias… - … Communication; 11. ITG …, 2014 - ieeexplore.ieee.org
To automatically detect prominent syllables or words, most approaches require a
segmentation of the speech signal and a subsequent extraction of prosodic features in these …