Picture for Pawel Swietojanski

Pawel Swietojanski

Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition

Apr 18, 2023
Maurits Bleeker, Pawel Swietojanski, Stefan Braun, Xiaodan Zhuang

Figure 1 for Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition

Figure 2 for Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition

Figure 3 for Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition

Figure 4 for Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition

* 5 pages, 2 figures, 2 tables

Access Paper or Ask Questions

SLURP: A Spoken Language Understanding Resource Package

Nov 26, 2020
Emanuele Bastianelli, Andrea Vanzo, Pawel Swietojanski, Verena Rieser

Figure 1 for SLURP: A Spoken Language Understanding Resource Package

Figure 2 for SLURP: A Spoken Language Understanding Resource Package

Figure 3 for SLURP: A Spoken Language Understanding Resource Package

Figure 4 for SLURP: A Spoken Language Understanding Resource Package

* Published at the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP-2020)

Access Paper or Ask Questions

Adaptation Algorithms for Speech Recognition: An Overview

Aug 14, 2020
Peter Bell, Joachim Fainberg, Ondrej Klejch, Jinyu Li, Steve Renals, Pawel Swietojanski

Figure 1 for Adaptation Algorithms for Speech Recognition: An Overview

Figure 2 for Adaptation Algorithms for Speech Recognition: An Overview

Figure 3 for Adaptation Algorithms for Speech Recognition: An Overview

Figure 4 for Adaptation Algorithms for Speech Recognition: An Overview

* Submitted to IEEE Open Journal of Signal Processing. 30 pages, 27 figures

Access Paper or Ask Questions

Multi-task self-supervised learning for Robust Speech Recognition

Jan 25, 2020
Mirco Ravanelli, Jianyuan Zhong, Santiago Pascual, Pawel Swietojanski, Joao Monteiro, Jan Trmal, Yoshua Bengio

Figure 1 for Multi-task self-supervised learning for Robust Speech Recognition

Figure 2 for Multi-task self-supervised learning for Robust Speech Recognition

Figure 3 for Multi-task self-supervised learning for Robust Speech Recognition

Figure 4 for Multi-task self-supervised learning for Robust Speech Recognition

* Accepted at ICASSP 2020

Access Paper or Ask Questions

Benchmarking Natural Language Understanding Services for building Conversational Agents

Mar 26, 2019
Xingkun Liu, Arash Eshghi, Pawel Swietojanski, Verena Rieser

Figure 1 for Benchmarking Natural Language Understanding Services for building Conversational Agents

Figure 2 for Benchmarking Natural Language Understanding Services for building Conversational Agents

Figure 3 for Benchmarking Natural Language Understanding Services for building Conversational Agents

Figure 4 for Benchmarking Natural Language Understanding Services for building Conversational Agents

* Accepted by IWSDS2019

Access Paper or Ask Questions

Differentiable Pooling for Unsupervised Acoustic Model Adaptation

Jul 13, 2016
Pawel Swietojanski, Steve Renals

Figure 1 for Differentiable Pooling for Unsupervised Acoustic Model Adaptation

Figure 2 for Differentiable Pooling for Unsupervised Acoustic Model Adaptation

Figure 3 for Differentiable Pooling for Unsupervised Acoustic Model Adaptation

Figure 4 for Differentiable Pooling for Unsupervised Acoustic Model Adaptation

* 11 pages, 7 Tables, 7 Figures in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 24, num. 11, 2016

Access Paper or Ask Questions

Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation

Jul 13, 2016
Pawel Swietojanski, Jinyu Li, Steve Renals

Figure 1 for Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation

Figure 2 for Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation

Figure 3 for Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation

Figure 4 for Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation

* 14 pages, 9 Tables, 11 Figues in IEEE/ACM Transactions on Audio, Speech and Language Processing, Vol. 24, Num. 8, 2016

Access Paper or Ask Questions