Related papers: Learnable Frontends that do not Learn: Quantifying…

This paper addresses the challenging scenario for the distant-talking control of a music playback device, a common portable speaker with four small loudspeakers in close proximity to one microphone. The user controls the device through…

Language model (LM) pre-training is useful in many language processing tasks. But can pre-trained LMs be further leveraged for more general machine learning problems? We propose an approach for using LMs to scaffold learning and…

When beginners learn to speak a non-native language, it is difficult for them to judge for themselves whether they are speaking well. Therefore, computer-assisted pronunciation training systems are used to detect learner mispronunciations.…

End-to-end learning treats the entire system as a whole adaptable black box, which, if sufficient data are available, may learn a system that works very well for the target task. This principle has recently been applied to several prototype…

Automated bioacoustic analysis aids understanding and protection of both marine and terrestrial animals and their habitats across extensive spatiotemporal scales, and typically involves analyzing vast collections of acoustic data. With the…

Learned Differentiable Boolean Logic Networks (DBNs) already deliver efficient inference on resource-constrained hardware. We extend them with a trainable, differentiable interconnect whose parameter count remains constant as input width…

Machine learning techniques are an active area of research for speech enhancement for hearing aids, with one particular focus on improving the intelligibility of a noisy speech signal. Recent work has shown that feature encodings from…

Informed by the basic geometry underlying feed forward neural networks, we initialize the weights of the first layer of a neural network using the linear discriminants which best distinguish individual classes. Networks initialized in this…

The application of deep learning to the area of communications systems has been a growing field of interest in recent years. Forward-forward (FF) learning is an efficient alternative to the backpropagation (BP) algorithm, which is the…

Frontier AI systems are making transformative impacts across society, but such benefits are not without costs: models trained on web-scale datasets containing personal and private data raise profound concerns about data privacy and…

Research in bioacoustics, neuroscience, and linguistics often uses birdsong as a proxy to acquire knowledge across diverse areas. This requires audio models to annotate and parse the birdsong. Developing such models requires precise,…

With fewer feature dimensions, filter banks are often used in light-weight full-band speech enhancement models. In order to further enhance the coarse speech in the sub-band domain, it is necessary to apply a post-filtering for harmonic…

Far-field speech recognition in noisy and reverberant conditions remains a challenging problem despite recent deep learning breakthroughs. This problem is commonly addressed by acquiring a speech signal from multiple microphones and…

This paper investigates multilevel initialization strategies for training very deep neural networks with a layer-parallel multigrid solver. The scheme is based on the continuous interpretation of the training problem as a problem of optimal…

Animal sounds can be recognised automatically by machine learning, and this has an important role to play in biodiversity monitoring. Yet despite increasingly impressive capabilities, bioacoustic species classifiers still exhibit imbalanced…

Federated Learning aims to learn machine learning models from multiple decentralized edge devices (e.g. mobiles) or servers without sacrificing local data privacy. Recent Natural Language Processing techniques rely on deep learning and…

We propose a learnable mel-frequency cepstral coefficient (MFCC) frontend architecture for deep neural network (DNN) based automatic speaker verification. Our architecture retains the simplicity and interpretability of MFCC-based features…

Open intent detection is a significant problem in natural language understanding, which aims to identify the unseen open intent while ensuring known intent identification performance. However, current methods face two major challenges.…

Research in speaker recognition has recently seen significant progress due to the application of neural network models and the availability of new large-scale datasets. There has been a plethora of work in search for more powerful…

Deep learning-based speech enhancement (SE) models have achieved impressive performance in the past decade. Numerous advanced architectures have been designed to deliver state-of-the-art performance; however, their scalability potential…