Search Results for author: Mingyang Zhang

Found 19 papers, 3 papers with code

Out-of-Domain Semantics to the Rescue! Zero-Shot Hybrid Retrieval Models

no code implementations25 Jan 2022 Tao Chen, Mingyang Zhang, Jing Lu, Michael Bendersky, Marc Najork

In this work, we carefully select five datasets, including two in-domain datasets and three out-of-domain datasets with different levels of domain shift, and study the generalization of a deep model in a zero-shot setting.

Language Modelling Passage Retrieval

DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding

no code implementations13 Oct 2021 Sergey Nikonorov, Berrak Sisman, Mingyang Zhang, Haizhou Li

At the same time, as the deep neural analyzer is learnable, it is expected to be more accurate for signal reconstruction and manipulation, and generalizable from speech to singing.

Speech Synthesis Voice Conversion

Across-Task Neural Architecture Search via Meta Learning

no code implementations12 Oct 2021 Jingtao Rong, Xinyi Yu, Mingyang Zhang, Linlin Ou

In this paper, an across-task neural architecture search (AT-NAS) is proposed to address the problem through combining gradient-based meta-learning with EA-based NAS to learn over the distribution of tasks.

Meta-Learning Neural Architecture Search

VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over

no code implementations7 Oct 2021 Junchen Lu, Berrak Sisman, Rui Liu, Mingyang Zhang, Haizhou Li

The proposed VisualTTS adopts two novel mechanisms that are 1) textual-visual attention, and 2) visual fusion strategy during acoustic decoding, which both contribute to forming accurate alignment between the input text content and lip motion in input lip sequence.

Speech Synthesis

Indoor Localization Using Smartphone Magnetic with Multi-Scale TCN and LSTM

no code implementations24 Sep 2021 Mingyang Zhang, Jie Jia, Jian Chen

A novel multi-scale temporal convolutional network (TCN) and long short-term memory network (LSTM) based magnetic localization approach is proposed.

Indoor Localization Time Series

RepNAS: Searching for Efficient Re-parameterizing Blocks

1 code implementation8 Sep 2021 Mingyang Zhang, Xinyi Yu, Jingtao Rong, Linlin Ou

However, it is still challenging to search for efficient networks due to the gap between the searched constraint and real inference time exists.

Neural Architecture Search

Dynamic Language Models for Continuously Evolving Content

no code implementations11 Jun 2021 Spurthi Amba Hombaiah, Tao Chen, Mingyang Zhang, Michael Bendersky, Marc Najork

To this end, we both explore two different vocabulary composition methods, as well as propose three sampling methods which help in efficient incremental training for BERT-like models.

Spatially Self-Paced Convolutional Networks for Change Detection in Heterogeneous Images

no code implementations IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2021 Hao Li, Maoguo Gong, Mingyang Zhang, Yue Wu

Change detection in heterogeneous remote sensing images is a challenging problem because it is hard to make a direct comparison in the original observation spaces, and most methods rely on a set of manually labeled samples.

Change Detection

LAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding

no code implementations16 Apr 2021 Te-Lin Wu, Cheng Li, Mingyang Zhang, Tao Chen, Spurthi Amba Hombaiah, Michael Bendersky

text, table, image) and propose a novel layout-aware multimodal hierarchical framework, LAMPreT, to model the blocks and the whole document.

Natural Language Understanding with Privacy-Preserving BERT

no code implementations15 Apr 2021 Chen Qu, Weize Kong, Liu Yang, Mingyang Zhang, Michael Bendersky, Marc Najork

We investigate the privacy and utility implications of applying dx-privacy, a variant of Local Differential Privacy, to BERT fine-tuning in NLU applications.

Language Modelling Natural Language Understanding +2

Effective Model Compression via Stage-wise Pruning

no code implementations10 Nov 2020 Mingyang Zhang, Xinyi Yu, Jingtao Rong, Linlin Ou

To overcome the unfull training, a stage-wise pruning(SWP) method is proposed, which splits a deep supernet into several stage-wise supernets to reduce the candidate number and utilize inplace distillation to supervise the stage training.

Model Compression

Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approach

no code implementations2 Oct 2020 Saar Kuzi, Mingyang Zhang, Cheng Li, Michael Bendersky, Marc Najork

A hybrid approach, which leverages both semantic (deep neural network-based) and lexical (keyword matching-based) retrieval models, is proposed.


Converting Anyone's Emotion: Towards Speaker-Independent Emotional Voice Conversion

1 code implementation13 May 2020 Kun Zhou, Berrak Sisman, Mingyang Zhang, Haizhou Li

We consider that there is a common code between speakers for emotional expression in a spoken language, therefore, a speaker-independent mapping between emotional states is possible.

Voice Conversion

Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching

1 code implementation26 Apr 2020 Liu Yang, Mingyang Zhang, Cheng Li, Michael Bendersky, Marc Najork

In order to better capture sentence level semantic relations within a document, we pre-train the model with a novel masked sentence block language modeling task in addition to the masked word language modeling task used by BERT.

2048 Information Retrieval +6

Urban Anomaly Analytics: Description, Detection, and Prediction

no code implementations25 Apr 2020 Mingyang Zhang, Tong Li, Yue Yu, Yong Li, Pan Hui, Yu Zheng

Urban anomalies may result in loss of life or property if not handled properly.

Graph Pruning for Model Compression

no code implementations22 Nov 2019 Mingyang Zhang, Xinyi Yu, Jingtao Rong, Linlin Ou

Different from previous work, we take the node features from a well-trained graph aggregator instead of the hand-craft features, as the states in reinforcement learning.

AutoML Model Compression +1

VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019

no code implementations27 May 2019 Andros Tjandra, Berrak Sisman, Mingyang Zhang, Sakriani Sakti, Haizhou Li, Satoshi Nakamura

Our proposed approach significantly improved the intelligibility (in CER), the MOS, and discrimination ABX scores compared to the official ZeroSpeech 2019 baseline or even the topline.

Joint training framework for text-to-speech and voice conversion using multi-source Tacotron and WaveNet

no code implementations29 Mar 2019 Mingyang Zhang, Xin Wang, Fuming Fang, Haizhou Li, Junichi Yamagishi

We propose using an extended model architecture of Tacotron, that is a multi-source sequence-to-sequence model with a dual attention mechanism as the shared model for both the TTS and VC tasks.

Speech Synthesis Voice Conversion

Cannot find the paper you are looking for? You can Submit a new open access paper.