Sheng Li

Multi-valued Neural Network Trained by Differential Evolution for Synthesizing Multiple-Valued Functions

2015

We consider the problem of synthesizing multiple valued logic (MVL) functions by neural networks. A differential evolution algorithm is proposed to train the learnable multiple valued logic network. The optimum window and biasing parameters to …

Data selection from multiple ASR systems' hypotheses for unsupervised acoustic model training

2016

This paper addresses unsupervised training of DNN acoustic model, by exploiting a large amount of unlabeled data with CRF-based classifiers. In the proposed scheme, we obtain ASR hypotheses by complementary GMM and DNN based ASR …

Domain Switch-Aware Holistic Recurrent Neural Network for Modeling Multi-Domain User Behavior

2019

Understanding user behavior and predicting future behavior on the web is critical for providing seamless user experiences as well as increasing revenue of service providers. Recently, thanks to the remarkable success of recurrent neural networks …

Improved square root adaptive cubature Kalman filter

2019 · IET Signal Processing

In this study, an improved square root adaptive cubature Kalman filter (ISRACKF) is proposed to improve the filter performance in terms of accuracy, computation efficiency, and robustness. Through the evaluated measure of non‐linearity value, the …

Domain adaptation for statistical machine translation

2016

Statistical machine translation (SMT) plays more and more important role now. The performance of the SMT is largely dependent on the size and quality of training data. But the demands for translation is rich, how …

Invertible Image Dataset Protection

2021 · arXiv (Cornell University)

Deep learning has achieved enormous success in various industrial applications. Companies do not want their valuable data to be stolen by malicious employees to train pirated models. Nor do they wish the data analyzed by …

Relationship Between Speakers' Physiological Structure and Acoustic Speech Signals: Data-Driven Study Based on Frequency-Wise Attentional Neural Network

2022 · 2022 30th European Signal Processing Conference (EUSIPCO)

Quantitatively revealing the relationship between speakers' physiological structure and acoustic speech signals by considering the properties of resonance and antiresonance can help us to extract effective speaker discriminative information (SDI) from speech signals. The conventional …

KyotoMOS: An Automatic MOS Scoring System for Speech Synthesis

2023

The Mean Opinion Score (MOS) serves as a subjective measure for assessing the quality of synthesized speech. Nevertheless, the conventional approach to MOS evaluations can be resource-intensive in terms of both time and cost. This …

Phantom in the opera: adversarial music attack for robot dialogue system

2024 · Frontiers in Computer Science

This study explores the vulnerability of robot dialogue systems' automatic speech recognition (ASR) module to adversarial music attacks. Specifically, we explore music as a natural camouflage for such attacks. We propose a novel method to …

Lightwave Fabrics: At-Scale Optical Circuit Switching for Datacenter and Machine Learning Systems

2024

We describe our experience developing what we believe to be the world’s first large-scale production deployments of lightwave fabrics used for both datacenter networking and machine-learning (ML) applications [1],[2],[3],[4]. Using optical circuit switches (OCSes) and …

The Cloud Model-Based Evaluation of Public Building Renewal Potential with the Game Theory Combination Weighting Methods-Case Study in China

2024 · Preprints.org

Currently, urban renewal activities in China are booming. And promoting the renovation of public buildings is the key due to its large scale, high cost and significant impact to the nature and social environment. To …

Deep Collaborative Filtering via Marginalized Denoising Auto-encoder

2015

Collaborative filtering (CF) has been widely employed within recommender systems to solve many real-world problems. Learning effective latent factors plays the most important role in collaborative filtering. Traditional CF methods based upon matrix factorization techniques …

A Review on Deep Learning Techniques Applied to Answer Selection

2018 · International Conference on Computational Linguistics

Given a question and a set of candidate answers, answer selection is the task of identifying which of the candidates answers the question correctly. It is an important problem in natural language processing, with applications …