5 papers
Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression
Xiaoyi Qu, David Aponte, Colby Banbury +5
Structured pruning and quantization are fundamental techniques used to reduce the size of deep neural networks (DNNs) and typically are applied independently. Applying these techni…
Zero-Shot Text-to-Speech from Continuous Text Streams
Trung Dang, David Aponte, Dung Tran +2
Existing zero-shot text-to-speech (TTS) systems are typically designed to process complete sentences and are constrained by the maximum duration for which they have been trained. H…
HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruning
Tianyi Chen, Xiaoyi Qu, David Aponte +7
Structured pruning is one of the most popular approaches to effectively compress the heavy deep neural networks (DNNs) into compact sub-networks while retaining performance. The ex…
SPLAT: A framework for optimised GPU code-generation for SParse reguLar ATtention
Ahan Gupta, Yueming Yuan, Devansh Jain +4
Multi-head-self-attention (MHSA) mechanisms achieve state-of-the-art (SOTA) performance across natural language processing and vision tasks. However, their quadratic dependence on…
LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes
Trung Dang, David Aponte, Dung Tran +1
Prior works have demonstrated zero-shot text-to-speech by using a generative language model on audio tokens obtained via a neural audio codec. It is still challenging, however, to…