In this paper, we propose a policy gradient-based semi-supervised speech recognition
acoustic model training. In practice, self-training and teacher/student learning are one of the …

We introduce the hyper autoencoder architecture where a secondary, hypernetwork is used
to generate the weights of the encoder and decoder layers of the primary, actual …

We propose two approaches to handle speech recognition for task domains with sparse
matched training data. One is an active learning method that selects training data for the …

Dementia can affect a person's speech, language and conversational interaction
capabilities. The early diagnosis of dementia is of great clinical importance. Recent studies …

Automatic speech recognition systems usually require large annotated speech corpus for
training. The manual annotation of a large corpus is very difficult. It can be very helpful to use …

Voice command recognition task commonly involves an Automatic Speech Recognition
(ASR) system with context-specific optimization. Automatic Speech Recognition system …

▶ Beginning of the integration of developed algorithms on multiple robotic platforms (eg IRL-
1, Baxter).▶ Study of the effects of grounding in multimodal neural machine translation.▶ …

Derin sinir ağı temelli üst özkodlayıcıların yapay öğrenme yöntemleriyle eğitilmesi Geçiş
Yönlendirmesi Türkçe English Türkçe Türkçe English Giriş Geçiş Yönlendirmesi Öğe Göster Ana …