Search Results for author: Birger Kollmeier

Found 4 papers, 0 papers with code

Lombard Effect for Bilingual Speakers in Cantonese and English: importance of spectro-temporal features

no code implementations14 Apr 2022 Maximilian Karl Scharf, Sabine Hochmuth, Lena L. N. Wong, Birger Kollmeier, Anna Warzybok

While Cantonese is a tonal language that encodes information in spectro-temporal features, the Lombard effect is known to be associated with spectral changes in the speech signal.

Automatic Speech Recognition speech-recognition

Prediction of speech intelligibility with DNN-based performance measures

no code implementations17 Mar 2022 Angel Mario Castro Martinez, Constantin Spille, Jana Roßbach, Birger Kollmeier, Bernd T. Meyer

This paper presents a speech intelligibility model based on automatic speech recognition (ASR), combining phoneme probabilities from deep neural networks (DNN) and a performance measure that estimates the word error rate from these probabilities.

Automatic Speech Recognition speech-recognition

Individualized sound pressure equalization in hearing devices exploiting an electro-acoustic model

no code implementations4 Oct 2021 Henning Schepker, Reinhild Rohden, Florian Denk, Birger Kollmeier, Matthias Blau, Simon Doclo

To achieve optimal individualized equalization typically requires knowledge of all transfer functions between the source, the hearing device, and the individual eardrum.

Robust single- and multi-loudspeaker least-squares-based equalization for hearing devices

no code implementations9 Sep 2021 Henning Schepker, Florian Denk, Birger Kollmeier, Simon Doclo

To improve the sound quality of hearing devices, equalization filters can be used that aim at achieving acoustic transparency, i. e., listening with the device in the ear is perceptually similar to the open ear.


Cannot find the paper you are looking for? You can Submit a new open access paper.