Haizhou Li

On statistical machine translation method for lexicon refinement in speech recognition

2015

In low resource Automatic Speech Recognition (ASR), one usually resorts to the Statistical Machine Translation (SMT) technique to learn transform rules to refine grapheme lexicon. To do this, we face two challenges. One is to …

Spoofing detection under noisy conditions: a preliminary investigation and an initial database

2016 · arXiv (Cornell University)

Spoofing detection for automatic speaker verification (ASV), which is to discriminate between live speech and attacks, has received increasing attentions recently. However, all the previous studies have been done on the clean data without significant …

A Modularized Neural Network with Language-Specific Output Layers for Cross-lingual Voice Conversion

2019 · arXiv (Cornell University)

This paper presents a cross-lingual voice conversion framework that adopts a modularized neural network. The modularized neural network has a common input structure that is shared for both languages, and two separate output modules, one …

HLT-NUS SUBMISSION FOR 2020 NIST Conversational Telephone Speech SRE

2021 · arXiv (Cornell University)

This work provides a brief description of Human Language Technology (HLT) Laboratory, National University of Singapore (NUS) system submission for 2020 NIST conversational telephone speech (CTS) speaker recognition evaluation (SRE). The challenge focuses on evaluation …

LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT

2022 · arXiv (Cornell University)

Self-supervised speech representation learning has shown promising results in various speech processing tasks. However, the pre-trained models, e.g., HuBERT, are storage-intensive Transformers, limiting their scope of applications under low-resource settings. To this end, we propose …

Just Rank: Rethinking Evaluation with Word and Sentence Similarities

2022 · arXiv (Cornell University)

Word and sentence embeddings are useful feature representations in natural language processing. However, intrinsic evaluation for embeddings lags far behind, and there has been no significant update since the past decade. Word and sentence similarity …

Relational Sentence Embedding for Flexible Semantic Matching

2023

We present Relational Sentence Embedding (RSE), a new paradigm to further discover the potential of sentence embeddings.Prior work mainly models the similarity between sentences based on their embedding distance.Because of the complex semantic meanings conveyed, …

RefXVC: Cross-Lingual Voice Conversion With Enhanced Reference Leveraging

2024 · IEEE/ACM Transactions on Audio Speech and Language Processing

This paper proposes RefXVC, a method for cross-lingual voice conversion (XVC) that leverages reference information to improve conversion performance. Previous XVC works generally take an average speaker embedding to condition the speaker identity, which does …

Target Speech Detection With Multimodal Prompts

2025 · IEEE Transactions on Audio Speech and Language Processing

Traditional speaker diarization seeks to detect “who spoke when” according to speaker characteristics. Extending to target speech detection, we detect “when target speech event occurs” according to the semantic characteristics of speech. We propose a …

Utilizing Contextual Clues and Role Correlations for Enhancing Document-Level Event Argument Extraction

2025 · IEEE Transactions on Audio Speech and Language Processing

Document-level event argument extraction is a crucial yet challenging task within the field of information extraction. Current mainstream approaches primarily focus on the information interaction between event triggers and their arguments, facing two limitations: insufficient …

Adequacy–Fluency Metrics: Evaluating MT in the Continuous Space Model Framework

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

This work extends and evaluates a two-dimensional automatic evaluation metric for machine translation, which is designed to operate at the sentence level. The metric is based on the concepts of adequacy and fluency, aiming at …