10 accepted papers
Motivated by the sensitivity-based importance score of the adaptive low-rank adaptation (AdaLoRA), we utilize more theoretically supported metrics, including the signal-to-noise ratio (SNR), along with the Improved Variational Online Newton (IVON) optimizer, for adaptive parameter budget allocation.…
Architectures such as Linformer and Mamba have recently emerged as competitive linear time replacements for transformers. However, corresponding large pretrained models are often unavailable, especially in non-text domains. To remedy this, we present a Cross-Architecture Layerwise Distillation (CALD…
End-to-end spoken language understanding (SLU) remains elusive even with current large pretrained language models on text and speech, especially in multilingual cases. Machine translation has been established as a powerful pretraining objective on text as it enables the model to capture high-level s…
We summarise previous work showing that the basic sigmoid activation function arises as an instance of Bayes’s theorem, and that recurrence follows from the prior. We derive a layerwise recurrence without the assumptions of previous work, and show that it leads to a standard recurrence with modest m…
The generalized command response (GCR) model represents intonation as a superposition of muscle responses to spike command signals. We have previously shown that the spikes can be predicted by a two-stage system, consisting of a recurrent neural network and a post-processing procedure, but the respo…
The end-to-end lattice-free maximum mutual information (LF-MMI) approach has recently been shown to be beneficial for automatic speech recognition (ASR) in general. More specifically, its end-to-end nature and use of context independent phone labels make it attractive for multilingual ASR. We show t…
Natural language processing techniques are dependent upon punctuation to work well. When their input is taken from speech recognition, it is necessary to reconstruct the punctuation; in particular sentence boundaries. We define a range of features from low level acoustics to those with high level le…
Current statistical parametric text-to-speech (TTS) synthesis methods allow production of neutral speech with acceptable quality. However, prosody is often qualified as unsatisfactory and sounding too flat. In this paper, we address intonation modelling for TTS based on physiological aspects of pros…
We investigate a vocoder based on artificial neural networks using a phonological speech representation. Speech decomposition is based on the phonological encoders, realised as neural network classifiers, that are trained for a particular language. The speech reconstruction process involves using a…
We propose a novel algorithm to design an optimum array geometry for source localization inside an enclosure. We assume a square-law decay propagation model for the sound acquisition so that the additive noise on the measured source-microphone distances is proportional to the distances regardless of…