Jan 16, 2024 · This paper proposes the use of Quantized Hidden Markov Models (QHMMs) for reducing the footprint of conventional parametric HMM-based TTS system ...
Apr 25, 2024 · Jianguang Weng, Xiaowen Jia: A Memory-Efficient Graph Structured Composite-State Network for Embedded Speech Recognition.
Optimization of Tree-like Core Overlay in Hybrid-structured Application-layer Multicast. ... A Memory-Efficient Graph Structured Composite-State Network for ...
In this work, we propose a new parameter-efficient learning framework based on neural model reprogramming for cross-lingual speech recognition, which can \ ...
Graph Neural Networks for Learning Equivariant Representations of Neural Networks · GraphGuard: Provably Robust Graph Classification against Adversarial Attacks ...
May 15, 1996 · Advances in speech technology and computing power have created a surge of interest in the practical application of speech recognition.
Feb 7, 2020 · In this paper, we begin with a baseline RNN-Transducer architecture comprised of Long Short-Term Memory (LSTM) layers. We then experiment with a ...
Missing: Composite- | Show results with:Composite-
Jan 21, 2024 · Scene Graph Generation (SGG) refers to the task of automatically mapping an image or a video into a semantic structural scene graph, which ...
We substantiate our discussion with experiments on well-known benchmark data sets using compression techniques (quantization, pruning) for a set of resource- ...
Missing: Composite- | Show results with:Composite-
Depth. Improving Distinguishability of Class for Graph Neural Networks · Temporal Data. Continuous-Time Graph Representation with Sequential Survival Process ...