An articulatory speech synthesizer comprising a three-dimensional vocal tract model and a gesture-based concept for control of articulatory movements is introduced and discussed in this paper. A modular learning concept based on speech perception is outlined for the creation of gestural control rules. The learning concept includes on sensory feedback information for articulatory states produced...

Hate speech in social media is a growing phenomenon, and detecting such toxic content has recently gained significant traction the research community. Existing studies have explored fine-tuning language models (LMs) to perform hate detection, these solutions yielded performance. However, most of are limited only English, neglecting bulk hateful that generated other languages, particularly low-r...

DIVA (Directions into Velocities of Articulators) is a mathematical model of the processes behind speech acquisition and production, supposed to achieve a functional representation of areas in the brain that are involved in speech production and speech perception. Introducing cerebellum control mechanism into the model plays a significant role in improving the mechanism of speech acquisition an...

Traditional automatic speech recognition (ASR) systems usually get a sharp performance drop when noise presents in speech. To make a robust ASR, we introduce a new model using the multi-task learning deep neural networks (MTL-DNN) to solve the speech denoising task in feature level. In this model, the networks are initialized by pre-training restricted Boltzmann machines (RBM) and fine-tuned by...

Our knowledge about the computational mechanisms underlying human learning and recognition of sound sequences, especially speech, is still very limited. One difficulty in deciphering the exact means by which humans recognize speech is that there are scarce experimental findings at a neuronal, microscopic level. Here, we show that our neuronal-computational understanding of speech learning and r...

BACKGROUND Detailed knowledge of the neurophysiology of speech acquisition is important for understanding the developmental aspects of speech perception and production and for understanding developmental disorders of speech perception and production. METHOD A computer implemented neural model of sensorimotor control of speech production was developed. The model is capable of demonstrating the...

Generalization is a common issue for automatic speech recognition. A successful method used to improve recognition results consists of training a single system to solve multiple related tasks in parallel. This overview investigates which auxiliary tasks are helpful for speech recognition when multi-task learning is applied on a deep learning based acoustic model. The impact of multi-task learni...

We explore multimodal recognition by combining visual lipreading with acoustic speech recognition. We show that combining the visual and acoustic clues of speech improves the recog­ nition performance significantly especially in noisy environment. We achieve this with a hybrid speech recognition architecture, consisting of a new visual learning and tracking mechanism, a channel robust acoustic ...