Zhen-Hua Ling

A Deep Generative Architecture for Postfiltering in Statistical Parametric Speech Synthesis

2015 · IEEE/ACM Transactions on Audio Speech and Language Processing

The generated speech of hidden Markov model (HMM)-based statistical parametric speech synthesis still sounds “muffled.” One cause of this degradation in speech quality may be the loss of fine spectral structures. In this paper, we …

Hybrid semi-Markov CRF for Neural Sequence Labeling

2018

This paper proposes hybrid semi-Markov conditional random fields (SCRFs) for neural sequence labeling in natural language processing. Based on conventional conditional random fields (CRFs), SCRFs have been designed for the tasks of assigning labels to …

Detecting Speaker Personas from Conversational Texts

2021 · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Personas are useful for dialogue response prediction.

Voice spoofing detection with raw waveform based on Dual Path Res2net

2021

The natural-sounding speech produced by recent text-to-speech and voice conversion techniques pose serious threats to automatic speaker verification systems. The majority of existing spoofing detection countermeasures perform well when the nature of the attacks is …

SHINE: Syntax-augmented Hierarchical Interactive Encoder for Zero-shot Cross-lingual Information Extraction

2023 · arXiv (Cornell University)

Zero-shot cross-lingual information extraction(IE) aims at constructing an IE model for some low-resource target languages, given annotations exclusively in some rich-resource languages. Recent studies based on language-universal features have shown their effectiveness and are attracting …

Stage-Wise and Prior-Aware Neural Speech Phase Prediction

2024 · arXiv (Cornell University)

This paper proposes a novel Stage-wise and Prior-aware Neural Speech Phase Prediction (SP-NSPP) model, which predicts the phase spectrum from input amplitude spectrum by two-stage neural networks. In the initial prior-construction stage, we preliminarily predict …

RISE: Reasoning Enhancement via Iterative Self-Exploration in Multi-hop Question Answering

2025 · arXiv (Cornell University)

Large Language Models (LLMs) excel in many areas but continue to face challenges with complex reasoning tasks, such as Multi-Hop Question Answering (MHQA). MHQA requires integrating evidence from diverse sources while managing intricate logical dependencies, …

Enhancing and Combining Sequential and Tree LSTM for Natural Language Inference.

2016 · arXiv (Cornell University)

Reasoning and inference are central to human and artificial intelligence. Modeling inference in human language is notoriously challenging but is fundamental to natural language understanding and many applications. With the availability of large annotated data, …

Distraction-based neural networks for modeling documents

2016 · International Joint Conference on Artificial Intelligence

Distributed representation learned with neural networks has recently shown to be effective in modeling natural languages at fine granularities such as words, phrases, and even sentences. Whether and how such an approach can be extended …

Enhanced LSTM for Natural Language Inference

2017

Reasoning and inference are central to human and artificial intelligence. Modeling inference in human language is very challenging. With the availability of large annotated data In this paper, we present a new state-of-the-art result, achieving …

Neural Natural Language Inference Models Enhanced with External Knowledge

2018

Modeling natural language inference is a very challenging task. With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to achieve …

Forward Attention in Sequence- To-Sequence Acoustic Modeling for Speech Synthesis

2018

This paper proposes a forward attention method for the sequence-to-sequence acoustic modeling of speech synthesis. This method is motivated by the nature of the monotonic alignment from phone sequences to acoustic sequences. Only the alignment …

Learning Latent Representations for Style Control and Transfer in End-to-end Speech Synthesis

2019

In this paper, we introduce the Variational Autoencoder (VAE) to an end-to-end speech synthesis model, to learn the latent representation of speaking styles in an unsupervised manner. The style representation learned through VAE shows good …

Distant Supervision Relation Extraction with Intra-Bag and Inter-Bag Attentions

2019

Zhi-Xiu Ye, Zhen-Hua Ling. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2019.