Markus Nußbaum-Thom — accepted AI-conference papers

2024

Towards A World-English Language Model for on-Device Virtual Assistants

Rricha Jalota, Lyan Verwimp, Markus Nußbaum-Thom, Amr El-Desoky Mousa, Arturo Argueta, Youssef Oualil

ICASSP 2024accepted

Neural Network Language Models (NNLMs) for Virtual Assistants (VAs) are generally language-, region-, and in some cases, device-dependent, which increases the effort to scale and maintain them. Combining NNLMs for one or more of the categories is one way to improve scalability. In this work, we comb…

Cited by 0 Source ↗Scholar ↗

2017

Knowledge distillation across ensembles of multilingual models for low-resource languages

Jia Cui, Brian Kingsbury, Bhuvana Ramabhadran, George Saon, Tom Sercu, Kartik Audhkhasi +3

ICASSP 2017accepted

This paper investigates the effectiveness of knowledge distillation in the context of multilingual models. We show that with knowledge distillation, Long Short-Term Memory(LSTM) models can be used to train standard feed-forward Deep Neural Network (DNN) models for a variety of low-resource languages…

Cited by 0 Source ↗Scholar ↗

2017

Noisy objective functions based on the f-divergence

Markus Nußbaum-Thom, Ralf Schlüter, Vaibhava Goel, Hermann Ney

ICASSP 2017accepted

Dropout, the random dropping out of activations according to a specified rate, is a very simple but effective method to avoid over-fitting of deep neural networks to the training data.

Cited by 0 Source ↗Scholar ↗