73 citations · 145 across the 13 of their papers we have counts for
15 papers
Learnable Frontends that do not Learn: Quantifying Sensitivity to Filterbank Initialisation
Mark Anderson, Tomi Kinnunen, Naomi Harte
While much of modern speech and audio processing relies on deep neural networks trained using fixed audio representations, recent studies suggest great potential in acoustic fronte…
Learnable Acoustic Frontends in Bird Activity Detection
Mark Anderson, Naomi Harte
Autonomous recording units and passive acoustic monitoring present minimally intrusive methods of collecting bioacoustics data. Combining this data with species agnostic bird activ…
Low Resource Species Agnostic Bird Activity Detection
Mark Anderson, John Kennedy, Naomi Harte
This paper explores low resource classifiers and features for the detection of bird activity, suitable for embedded Automatic Recording Units which are typically deployed for long…
Bioacoustic Event Detection with prototypical networks and data augmentation
Mark Anderson, Naomi Harte
This report presents deep learning and data augmentation techniques used by a system entered into the Few-Shot Bioacoustic Event Detection for the DCASE2021 Challenge. The remit wa…
AV Taris: Online Audio-Visual Speech Recognition
George Sterpu, Naomi Harte
In recent years, Automatic Speech Recognition (ASR) technology has approached human-level performance on conversational speech under relatively clean listening conditions. In more…
Deep Multi-Scale Feature Learning for Defocus Blur Estimation
Ali Karaali, Naomi Harte, Claudio Rosito Jung
This paper presents an edge-based defocus blur estimation method from a single defocused image. We first distinguish edges that lie at depth discontinuities (called depth edges, fo…
Learning to Count Words in Fluent Speech enables Online Speech Recognition
George Sterpu, Christian Saam, Naomi Harte
Sequence to Sequence models, in particular the Transformer, achieve state of the art results in Automatic Speech Recognition. Practical usage is however limited to cases where full…
Should we hard-code the recurrence concept or learn it instead ? Exploring the Transformer architecture for Audio-Visual Speech Recognition
George Sterpu, Christian Saam, Naomi Harte
The audio-visual speech fusion strategy AV Align has shown significant performance improvements in audio-visual speech recognition (AVSR) on the challenging LRS2 dataset. Performan…
Neural Generation of Dialogue Response Timings
Matthew Roddy, Naomi Harte
The timings of spoken response offsets in human dialogue have been shown to vary based on contextual elements of the dialogue. We propose neural models that simulate the distributi…
How to Teach DNNs to Pay Attention to the Visual Modality in Speech Recognition
George Sterpu, Christian Saam, Naomi Harte
Audio-Visual Speech Recognition (AVSR) seeks to model, and thereby exploit, the dynamic relationship between a human voice and the corresponding mouth movements. A recently propose…
Attention-based Audio-Visual Fusion for Robust Automatic Speech Recognition
George Sterpu, Christian Saam, Naomi Harte
Automatic speech recognition can potentially benefit from the lip motion patterns, complementing acoustic speech to improve the overall recognition performance, particularly in noi…
Multimodal Continuous Turn-Taking Prediction Using Multiscale RNNs
Matthew Roddy, Gabriel Skantze, Naomi Harte
In human conversational interactions, turn-taking exchanges can be coordinated using cues from multiple modalities. To design spoken dialog systems that can conduct fluid interacti…
Investigating Speech Features for Continuous Turn-Taking Prediction Using LSTMs
Matthew Roddy, Gabriel Skantze, Naomi Harte
For spoken dialog systems to conduct fluid conversational interactions with users, the systems must be sensitive to turn-taking cues produced by a user. Models should be designed s…
Towards Lipreading Sentences with Active Appearance Models
George Sterpu, Naomi Harte
Automatic lipreading has major potential impact for speech recognition, supplementing and complementing the acoustic modality. Most attempts at lipreading have been performed on sm…
Can DNNs Learn to Lipread Full Sentences?
George Sterpu, Christian Saam, Naomi Harte
Finding visual features and suitable models for lipreading tasks that are more complex than a well-constrained vocabulary has proven challenging. This paper explores state-of-the-a…