Searcharxiv⌕ Search

arXiv subjects

Yue Lin

Publications and source records attributed to Yue Lin.

51 records · Page 3Linked to original sources
arXiv2022

Improve few-shot voice cloning using multi-modal learning

Recently, few-shot voice cloning has achieved a significant improvement. However, most models for few-shot voice cloning are single-modal, and multi-modal few-shot voice cloning has been understudied. In this paper, we propose to use multi-modal learning to improve the few-shot voice cloning performance. Inspired by the recent works on unsupervised speech representation, the proposed multi-modal system is built by extending Tacotron2 with an unsupervised speech representation module. We evaluate our proposed system in two few-shot voice cloning scenarios, namely few-shot text-to-speech(TTS) and voice conversion(VC). Experimental results demonstrate that the proposed multi-modal learning can significantly improve the few-shot voice cloning performance over their counterpart single-modal systems.

cs.SD↗
arXiv2022

DGC-vector: A new speaker embedding for zero-shot voice conversion

Recently, more and more zero-shot voice conversion algorithms have been proposed. As a fundamental part of zero-shot voice conversion, speaker embeddings are the key to improving the converted speech's speaker similarity. In this paper, we study the impact of speaker embeddings on zero-shot voice conversion performance. To better represent the characteristics of the target speaker and improve the speaker similarity in zero-shot voice conversion, we propose a novel speaker representation method in this paper. Our method combines the advantages of D-vector, global style token (GST) based speaker representation and auxiliary supervision. Objective and subjective evaluations show that the proposed method achieves a decent performance on zero-shot voice conversion and significantly improves speaker similarity over D-vector and GST-based speaker embedding.

cs.SD↗
arXiv2022

MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned

Reinforcement learning competitions advance the field by providing appropriate scope and support to develop solutions toward a specific problem. To promote the development of more broadly applicable methods, organizers need to enforce the use of general techniques, the use of sample-efficient methods, and the reproducibility of the results. While beneficial for the research community, these restrictions come at a cost -- increased difficulty. If the barrier for entry is too high, many potential participants are demoralized. With this in mind, we hosted the third edition of the MineRL ObtainDiamond competition, MineRL Diamond 2021, with a separate track in which we permitted any solution to promote the participation of newcomers. With this track and more extensive tutorials and support, we saw an increased number of submissions. The participants of this easier track were able to obtain a diamond, and the participants of the harder track progressed the generalizable solutions in the same task.

cs.LG↗
arXiv2021

Revisiting IPA-based Cross-lingual Text-to-speech

International Phonetic Alphabet (IPA) has been widely used in cross-lingual text-to-speech (TTS) to achieve cross-lingual voice cloning (CL VC). However, IPA itself has been understudied in cross-lingual TTS. In this paper, we report some empirical findings of building a cross-lingual TTS model using IPA as inputs. Experiments show that the way to process the IPA and suprasegmental sequence has a negligible impact on the CL VC performance. Furthermore, we find that using a dataset including one speaker per language to build an IPA-based TTS system would fail CL VC since the language-unique IPA and tone/stress symbols could leak the speaker information. In addition, we experiment with different combinations of speakers in the training dataset to further investigate the effect of the number of speakers on the CL VC performance.

cs.CL↗
arXiv2021

A Technical Report for ICCV 2021 VIPriors Re-identification Challenge

Person re-identification has always been a hot and challenging task. This paper introduces our solution for the re-identification track in VIPriors Challenge 2021. In this challenge, the difficulty is how to train the model from scratch without any pretrained weight. In our method, we show use state-of-the-art data processing strategies, model designs, and post-processing ensemble methods, it is possible to overcome the difficulty of data shortage and obtain competitive results. (1) Both image augmentation strategy and novel pre-processing method for occluded images can help the model learn more discriminative features. (2) Several strong backbones and multiple loss functions are used to learn more representative features. (3) Post-processing techniques including re-ranking, automatic query expansion, ensemble learning, etc., significantly improve the final performance. The final score of our team (ALONG) is 96.5154% mAP, ranking first in the leaderboard.

cs.CV↗
arXiv2021

Structural and dynamic disorder, not ionic trapping, controls charge transport in highly doped conducting polymers

Doped organic semiconductors are critical to emerging device applications, including thermoelectrics, bioelectronics, and neuromorphic computing devices. It is commonly assumed that low conductivities in these materials result primarily from charge trapping by the Coulomb potentials of the dopant counter-ions. Here, we present a combined experimental and theoretical study rebutting this belief. Using a newly developed doping technique, we find the conductivity of several classes of high-mobility conjugated polymers to be strongly correlated with paracrystalline disorder but poorly correlated with ionic size, suggesting that Coulomb traps do not limit transport. A general model for interacting electrons in highly doped polymers is proposed and carefully parameterized against atomistic calculations, enabling the calculation of electrical conductivity within the framework of transient localisation theory. Theoretical calculations are in excellent agreement with experimental data, providing insights into the disordered-limited nature of charge transport and suggesting new strategies to further improve conductivities.

cond-mat.mtrl-sci↗
arXiv2021

Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report

Image super-resolution is one of the most popular computer vision problems with many important applications to mobile devices. While many solutions have been proposed for this task, they are usually not optimized even for common smartphone AI hardware, not to mention more constrained smart TV platforms that are often supporting INT8 inference only. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based image super-resolution solutions that can demonstrate a real-time performance on mobile or edge NPUs. For this, the participants were provided with the DIV2K dataset and trained quantized models to do an efficient 3X image upscaling. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated NPU capable of accelerating quantized neural networks. The proposed solutions are fully compatible with all major mobile AI accelerators and are capable of reconstructing Full HD images under 40-60 ms while achieving high fidelity results. A detailed description of all models developed in the challenge is provided in this paper.

eess.IV↗
arXiv2021

Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report

Camera scene detection is among the most popular computer vision problem on smartphones. While many custom solutions were developed for this task by phone vendors, none of the designed models were available publicly up until now. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop quantized deep learning-based camera scene classification solutions that can demonstrate a real-time performance on smartphones and IoT platforms. For this, the participants were provided with a large-scale CamSDD dataset consisting of more than 11K images belonging to the 30 most important scene categories. The runtime of all models was evaluated on the popular Apple Bionic A11 platform that can be found in many iOS devices. The proposed solutions are fully compatible with all major mobile AI accelerators and can demonstrate more than 100-200 FPS on the majority of recent smartphone platforms while achieving a top-3 accuracy of more than 98%. A detailed description of all models developed in the challenge is provided in this paper.

eess.IV↗
arXiv2020

A Clarifying Question Selection System from NTES_ALONG in Convai3 Challenge

This paper presents the participation of NetEase Game AI Lab team for the ClariQ challenge at Search-oriented Conversational AI (SCAI) EMNLP workshop in 2020. The challenge asks for a complete conversational information retrieval system that can understanding and generating clarification questions. We propose a clarifying question selection system which consists of response understanding, candidate question recalling and clarifying question ranking. We fine-tune a RoBERTa model to understand user's responses and use an enhanced BM25 model to recall the candidate questions. In clarifying question ranking stage, we reconstruct the training dataset and propose two models based on ELECTRA. Finally we ensemble the models by summing up their output probabilities and choose the question with the highest probability as the clarification question. Experiments show that our ensemble ranking model outperforms in the document relevance task and achieves the best recall@[20,30] metrics in question relevance task. And in multi-turn conversation evaluation in stage2, our system achieve the top score of all document relevance metrics.

cs.AI↗
arXiv2020

AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results

This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020. This challenge involves three tracks to super-resolve an input image for $\times$2, $\times$3 and $\times$4 scaling factors, respectively. The goal is to attract more attention to realistic image degradation for the SR task, which is much more complicated and challenging, and contributes to real-world image super-resolution applications. 452 participants were registered for three tracks in total, and 24 teams submitted their results. They gauge the state-of-the-art approaches for real image SR in terms of PSNR and SSIM.

cs.CV↗
arXiv2020

Unsupervised Learning For Sequence-to-sequence Text-to-speech For Low-resource Languages

Recently, sequence-to-sequence models with attention have been successfully applied in Text-to-speech (TTS). These models can generate near-human speech with a large accurately-transcribed speech corpus. However, preparing such a large data-set is both expensive and laborious. To alleviate the problem of heavy data demand, we propose a novel unsupervised pre-training mechanism in this paper. Specifically, we first use Vector-quantization Variational-Autoencoder (VQ-VAE) to ex-tract the unsupervised linguistic units from large-scale, publicly found, and untranscribed speech. We then pre-train the sequence-to-sequence TTS model by using the pairs. Finally, we fine-tune the model with a small amount of paired data from the target speaker. As a result, both objective and subjective evaluations show that our proposed method can synthesize more intelligible and natural speech with the same amount of paired training data. Besides, we extend our proposed method to the hypothesized low-resource languages and verify the effectiveness of the method using objective evaluation.

eess.AS↗
arXiv2016

Enhanced Superconductivity in TiO Epitaxial Thin Films

Titanium oxides have many fascinating optical and electrical properties, such as the superconductivity at 2.0 K in cubic titanium monoxide TiO polycrystalline bulk. However, the lack of TiO single crystals or epitaxial films has prevented systematic investigations on its superconductivity. Here, we report the basic superconductivity characterizations of cubic TiO films epitaxially grown on (0001)-oriented Al2O3 substrates. The magnetic and electronic transport measurements confirmed that TiO is a type-II superconductor and the record high Tc is about 7.4 K. The lower critical field (Hc1) at 1.9 K, the extrapolated upper critical field Hc2(0) and coherence length are about 18 Oe, 13.7 T and 4.9 nm, respectively. With increasing pressure, the value of Tc shifts to lower temperature while the normal state resistivity increases. Our results on the superconducting TiO films confirm the strategy to achieve higher Tc in epitaxial films, which may be helpful for finding more superconducting materials in various related systems.

cond-mat.supr-con↗
arXiv2012

Density Sensitive Hashing

Nearest neighbors search is a fundamental problem in various research fields like machine learning, data mining and pattern recognition. Recently, hashing-based approaches, e.g., Locality Sensitive Hashing (LSH), are proved to be effective for scalable high dimensional nearest neighbors search. Many hashing algorithms found their theoretic root in random projection. Since these algorithms generate the hash tables (projections) randomly, a large number of hash tables (i.e., long codewords) are required in order to achieve both high precision and recall. To address this limitation, we propose a novel hashing algorithm called {\em Density Sensitive Hashing} (DSH) in this paper. DSH can be regarded as an extension of LSH. By exploring the geometric structure of the data, DSH avoids the purely random projections selection and uses those projective functions which best agree with the distribution of the data. Extensive experimental results on real-world data sets have shown that the proposed method achieves better performance compared to the state-of-the-art hashing approaches.

cs.IR↗