Zobrazeno 1 - 10
of 147
pro vyhledávání: '"Garner, Philip N."'
Autor:
He, Mutian, Garner, Philip N.
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
Externí odkaz:
http://arxiv.org/abs/2410.06846
Autor:
Chen, Haolin, Garner, Philip N.
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) op
Externí odkaz:
http://arxiv.org/abs/2409.10673
Whilst state of the art automatic speech recognition (ASR) can perform well, it still degrades when exposed to acoustic environments that differ from those used when training the model. Unfamiliar environments for a given model may well be known a-pr
Externí odkaz:
http://arxiv.org/abs/2409.05589
Autor:
Bittar, Alexandre, Garner, Philip N.
Publikováno v:
Frontiers in Neuroscience, Vol. 18 (2024)
Understanding cognitive processes in the brain demands sophisticated models capable of replicating neural dynamics at large scales. We present a physiologically inspired speech recognition architecture, compatible and scalable with deep learning fram
Externí odkaz:
http://arxiv.org/abs/2404.14024
Autor:
Chen, Haolin, Garner, Philip N.
We are motivated primarily by the adaptation of text-to-speech synthesis models; however we argue that more generic parameter-efficient fine-tuning (PEFT) is an appropriate framework to do such adaptation. Nevertheless, catastrophic forgetting remain
Externí odkaz:
http://arxiv.org/abs/2402.12220
Autor:
He, Mutian, Garner, Philip N.
Recently, large pretrained language models have demonstrated strong language understanding capabilities. This is particularly reflected in their zero-shot and in-context learning abilities on downstream tasks through prompting. To assess their impact
Externí odkaz:
http://arxiv.org/abs/2305.13512
Autor:
He, Mutian, Garner, Philip N.
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 te
Externí odkaz:
http://arxiv.org/abs/2305.09652
Autor:
Chen, Haolin, Garner, Philip N.
Given the recent success of diffusion in producing natural-sounding synthetic speech, we investigate how diffusion can be used in speaker adaptive TTS. Taking cues from more traditional adaptation approaches, we show that adaptation can be included i
Externí odkaz:
http://arxiv.org/abs/2303.01849
Autor:
Bittar, Alexandre, Garner, Philip N.
Compared to conventional artificial neurons that produce dense and real-valued responses, biologically-inspired spiking neurons transmit sparse and binary information, which can also lead to energy-efficient implementations. Recent research has shown
Externí odkaz:
http://arxiv.org/abs/2212.01187
Current speech recognition architectures perform very well from the point of view of machine learning, hence user interaction. This suggests that they are emulating the human biological system well. We investigate whether the inference can be inverte
Externí odkaz:
http://arxiv.org/abs/2208.11700