Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Adaptive compressive onset-enhancement for improved speech intelligibility in noise and reverberation

: Bederna, F.; Schepker, H.; Rollwage, C.; Doclo, S.; Pusch, A.; Bitzer, J.; Rennies, J.


Meng, H. ; International Speech Communication Association -ISCA-:
Cognitive intelligence for speech processing. 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 : held online due to Covid-19; Shanghai, China, 25-29 October 2020
Red Hook/NY: Curran Associates, 2020
ISBN: 978-1-71382-069-7
DOI: 10.21437/Interspeech.2020
International Speech Communication Association (INTERSPEECH Annual Conference) <21, 2020, Online>
Conference Paper
Fraunhofer IDMT ()

Near-end listening enhancement (NELE) algorithms aim to pre-process speech prior to playback via loudspeakers so as to maintain high speech intelligibility even when listening conditions are not optimal, e.g., due to noise or reverberation. Often NELE algorithms are designed for scenarios considering either only the detrimental effect of noise or only reverberation, but not both disturbances. In many typical applications scenarios, however, both factors are present. In this paper, we evaluate a new combination of a noise-dependent and a reverberation-dependent algorithm implemented in a common framework. Specifically, we use instrumental measures as well as subjective ratings of listening effort for acoustic scenarios with different reverberation times and realistic signal-to-noise ratios. The results show that the noise-dependent algorithm also performs well in reverberation, and that the combination of both algorithms can yield slightly better performance than the individual algorithms alone. This benefit appears to depend strongly on the specific acoustic condition, indicating that further work is required to optimize the adaptive algorithm behavior.