23 citations · 26 across the 7 of their papers we have counts for
8 papers
Biased Self-supervised learning for ASR
Florian L. Kreyssig, Yangyang Shi, Jinxi Guo +3
Self-supervised learning via masked prediction pre-training (MPPT) has shown impressive performance on a range of speech-processing tasks. This paper proposes a method to bias self…
Transferable Dialogue Systems and User Simulators
Bo-Hsiang Tseng, Yinpei Dai, Florian Kreyssig +1
One of the difficulties in training dialogue systems is the lack of training data. We explore the possibility of creating dialogue data through the interaction between a dialogue s…
A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training
Adnan Haider, Chao Zhang, Florian L. Kreyssig +1
This paper presents a novel natural gradient and Hessian-free (NGHF) optimisation framework for neural network training that can operate efficiently in a distributed manner. It rel…
Cosine-Distance Virtual Adversarial Training for Semi-Supervised Speaker-Discriminative Acoustic Embeddings
Florian L. Kreyssig, Philip C. Woodland
In this paper, we propose a semi-supervised learning (SSL) technique for training deep neural networks (DNNs) to generate speaker-discriminative acoustic embeddings (speaker embedd…
Discriminative Neural Clustering for Speaker Diarisation
Qiujia Li, Florian L. Kreyssig, Chao Zhang +1
In this paper, we propose Discriminative Neural Clustering (DNC) that formulates data clustering with a maximum number of clusters as a supervised sequence-to-sequence learning pro…
Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems
Bo-Hsiang Tseng, Florian Kreyssig, Pawel Budzianowski +4
Cross-domain natural language generation (NLG) is still a difficult task within spoken dialogue modelling. Given a semantic representation provided by the dialogue manager, the lan…
Neural User Simulation for Corpus-based Policy Optimisation for Spoken Dialogue Systems
Florian Kreyssig, Inigo Casanueva, Pawel Budzianowski +1
User Simulators are one of the major tools that enable offline training of task-oriented dialogue systems. For this task the Agenda-Based User Simulator (ABUS) is often used. The A…
Improved TDNNs using Deep Kernels and Frequency Dependent Grid-RNNs
Florian Kreyssig, Chao Zhang, Philip Woodland
Time delay neural networks (TDNNs) are an effective acoustic model for large vocabulary speech recognition. The strength of the model can be attributed to its ability to effectivel…