137 citations · 235 across the 9 of their papers we have counts for
11 papers
Segmental Attention Decoding With Long Form Acoustic Encodings
Pawel Swietojanski, Xinwei Li, Mingbin Xu +3
We address the fundamental incompatibility of attention-based encoder-decoder (AED) models with long-form acoustic encodings. AED models trained on segmented utterances learn to en…
Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval
Nikolaos Flemotomos, Roger Hsiao, Pawel Swietojanski +3
Neural contextual biasing allows speech recognition models to leverage contextually relevant information, leading to improved transcription accuracy. However, the biasing mechanism…
Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition
Maurits Bleeker, Pawel Swietojanski, Stefan Braun +1
This paper presents an extension to train end-to-end Context-Aware Transformer Transducer ( CATT ) models by using a simple, yet efficient method of mining hard negative phrases fr…
Variable Attention Masking for Configurable Transformer Transducer Speech Recognition
Pawel Swietojanski, Stefan Braun, Dogan Can +9
This work studies the use of attention masking in transformer transducer based speech recognition for building a single configurable model for different deployment scenarios. We pr…
Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generation
Thien Nguyen, Nathalie Tran, Liuhui Deng +16
Code-switching describes the practice of using more than one language in the same sentence. In this study, we investigate how to optimize a neural transducer based bilingual automa…
SLURP: A Spoken Language Understanding Resource Package
Emanuele Bastianelli, Andrea Vanzo, Pawel Swietojanski +1
Spoken Language Understanding infers semantic meaning directly from audio data, and thus promises to reduce error propagation and misunderstandings in end-user applications. Howeve…
Building Proactive Voice Assistants: When and How (not) to Interact
O. Miksik, I. Munasinghe, J. Asensio-Cubero +17
Voice assistants have recently achieved remarkable commercial success. However, the current generation of these devices is typically capable of only reactive interactions. In other…
Multi-task self-supervised learning for Robust Speech Recognition
Mirco Ravanelli, Jianyuan Zhong, Santiago Pascual +4
Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To take a step in this direction, we recentl…
Static Visual Spatial Priors for DoA Estimation
Pawel Swietojanski, Ondrej Miksik
As we interact with the world, for example when we communicate with our colleagues in a large open space or meeting room, we continuously analyse the surrounding environment and, i…
Benchmarking Natural Language Understanding Services for building Conversational Agents
Xingkun Liu, Arash Eshghi, Pawel Swietojanski +1
We have recently seen the emergence of several publicly available Natural Language Understanding (NLU) toolkits, which map user utterances to structured, but more abstract, Dialogu…
Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation
Pawel Swietojanski, Jinyu Li, Steve Renals
This work presents a broad study on the adaptation of neural network acoustic models by means of learning hidden unit contributions (LHUC) -- a method that linearly re-combines hid…