25 citations · 32 across the 5 of their papers we have counts for
5 papers
Going Retro: Astonishingly Simple Yet Effective Rule-based Prosody Modelling for Speech Synthesis Simulating Emotion Dimensions
Felix Burkhardt, Uwe Reichel, Florian Eyben +1
We introduce two rule-based models to modify the prosody of speech synthesis in order to modulate the emotion to be expressed. The prosody modulation is based on speech synthesis m…
Speech-based Age and Gender Prediction with Transformers
Felix Burkhardt, Johannes Wagner, Hagen Wierstorf +2
We report on the curation of several publicly available datasets for age and gender prediction. Furthermore, we present experiments to predict age and gender with models based on a…
Happy or Evil Laughter? Analysing a Database of Natural Audio Samples
Aljoscha Düsterhöft, Felix Burkhardt, Björn W. Schuller
We conducted a data collection on the basis of the Google AudioSet database by selecting a subset of the samples annotated with \textit{laughter}. The selection criterion was to be…
audb -- Sharing and Versioning of Audio and Annotation Data in Python
Hagen Wierstorf, Johannes Wagner, Florian Eyben +2
Driven by the need for larger and more diverse datasets to pre-train and fine-tune increasingly complex machine learning models, the number of datasets is rapidly growing. audb is…
Probing Speech Emotion Recognition Transformers for Linguistic Knowledge
Andreas Triantafyllopoulos, Johannes Wagner, Hagen Wierstorf +5
Large, pre-trained neural networks consisting of self-attention layers (transformers) have recently achieved state-of-the-art results on several speech emotion recognition (SER) da…