Search Results for author:
Found 45 papers, 11 papers with code
KLMo: Knowledge Graph Enhanced Pretrained Language Model with Fine-Grained Relationships
In this work, we propose to incorporate KG (including both entities and relations) into the language learning process to obtain KG-enhanced pretrained Language Model, namely KLMo.
NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality
In this paper, we answer these questions by first defining the human-level quality based on the statistical significance of subjective measure and introducing appropriate guidelines to judge it, and then developing a TTS system called NaturalSpeech that achieves human-level quality on a benchmark dataset.
Ranked #1 on
Text-To-Speech Synthesis
on LJSpeech
AdaSpeech 4: Adaptive Text to Speech in Zero-Shot Scenarios
We model the speaker characteristics systematically to improve the generalization on new speakers.
InferGrad: Improving Diffusion Models for Vocoder by Considering Inference in Training
In this paper, we propose InferGrad, a diffusion model for vocoder that incorporates inference process into training, to reduce the inference iterations while maintaining high generation quality.
Cross-Lingual Text-to-Speech Using Multi-Task Learning and Speaker Classifier Joint Training
To further improve the speaker similarity, joint training with a speaker classifier is proposed.
Exploring Forensic Dental Identification with Deep Learning
In this work, we pioneer to study deep learning for dental forensic identification based on panoramic radiographs.
LW-GCN: A Lightweight FPGA-based Graph Convolutional Network Accelerator
In this work, we propose LW-GCN, a lightweight FPGA-based accelerator with a software-hardware co-designed process to tackle irregularity in computation and memory access in GCN inference.
LF-YOLO: A Lighter and Faster YOLO for Weld Defect Detection of X-ray Image
To further prove the ability of our method, we test it on public dataset MS COCO, and the results show that our LF-YOLO has a outstanding versatility detection performance.
DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021
The goal of this challenge is to synthesize natural and high-quality speech from text, and we approach this goal in two perspectives: The first is to directly model and generate waveform in 48 kHz sampling rate, which brings higher perception quality than previous systems with 16 kHz or 24 kHz sampling rate; The second is to model the variation information in speech through a systematic design, which improves the prosody and naturalness.
Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge
End-to-end TTS suffers from high data requirements as it is difficult for both costly speech corpora to cover all necessary knowledge and neural models to learn the knowledge, hence additional knowledge needs to be injected manually.
X2Teeth: 3D Teeth Reconstruction from a Single Panoramic Radiograph
Different from single object reconstruction from photos, this task has the unique challenge of constructing multiple objects at high resolutions.
Cross-speaker Style Transfer with Prosody Bottleneck in Neural Speech Synthesis
Secondly, in these models the content/text, prosody, and speaker timbre are usually highly entangled, it's therefore not realistic to expect a satisfied result when freely combining these components, such as to transfer speaking style between speakers.
TumorCP: A Simple but Effective Object-Level Data Augmentation for Tumor Segmentation
Experiments on kidney tumor segmentation task demonstrate that TumorCP surpasses the strong baseline by a remarkable margin of 7. 12% on tumor Dice.
Diff-Net: Image Feature Difference based High-Definition Map Change Detection for Autonomous Driving
Compared to traditional methods based on object detectors, the essential design in our work is a parallel feature difference calculation structure that infers map changes by comparing features extracted from the camera and rasterized images.
Speech BERT Embedding For Improving Prosody in Neural TTS
Experimental results obtained by the Transformer TTS show that the proposed BERT can extract fine-grained, segment-level prosody, which is complementary to utterance-level prosody to improve the final prosody of the TTS speech.
On Addressing Practical Challenges for RNN-Transducer
The first challenge is solved with a splicing data method which concatenates the speech segments extracted from the source domain data.
Exploring Machine Speech Chain for Domain Adaptation and Few-Shot Speaker Adaptation
Machine Speech Chain, which integrates both end-to-end (E2E) automatic speech recognition (ASR) and text-to-speech (TTS) into one circle for joint training, has been proven to be effective in data augmentation by leveraging large amounts of unpaired data.
Multilingual Byte2Speech Models for Scalable Low-resource Speech Synthesis
To scale neural speech synthesis to various real-world languages, we present a multilingual end-to-end framework that maps byte inputs to spectrograms, thus allowing arbitrary input scripts.
Atlas-aware ConvNetfor Accurate yet Robust Anatomical Segmentation
Second, we can largely boost the robustness of existing ConvNets, proved by: (i) testing on scans with synthetic pathologies, and (ii) training and evaluation on scans of different scanning setups across datasets.
SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images
In this paper, we first introduce the concept of semantic objectness to exploit the geometric relationship of these two tasks through an analysis of the imaging process, then propose a Semantic Object Segmentation and Depth Estimation Network (SOSD-Net) based on the objectness assumption.
Ranked #39 on
Semantic Segmentation
on NYU Depth v2
Exploring Instance-Level Uncertainty for Medical Detection
The ability of deep learning to predict with uncertainty is recognized as key for its adoption in clinical routines.
Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability
Because of its streaming nature, recurrent neural network transducer (RNN-T) is a very promising end-to-end (E2E) model that may replace the popular hybrid model for automatic speech recognition.
Accurate Anchor Free Tracking
Specifically, a target object is defined by a bounding box center, tracking offset, and object size.
Oral-3D: Reconstructing the 3D Bone Structure of Oral Cavity from 2D Panoramic X-ray
In this paper, we propose a framework, named Oral-3D, to reconstruct the 3D oral cavity from a single PX image and prior information of the dental arch.
T-Net: Learning Feature Representation with Task-specific Supervision for Biomedical Image Analysis
The encoder-decoder network is widely used to learn deep feature representations from pixel-wise annotations in biomedical image analysis.
Effective Scaling of Blockchain Beyond Consensus Innovations and Moore's Law
As an emerging technology, blockchain has achieved great success in numerous application scenarios, from intelligent healthcare to smart cities.
Cryptography and Security Distributed, Parallel, and Cluster Computing 68M14 C.2.2
CompareNet: Anatomical Segmentation Network with Deep Non-local Label Fusion
Label propagation is a popular technique for anatomical segmentation.
Order Acceptance and Scheduling with Sequence-dependent Setup Times: a New Memetic Algorithm and Benchmark of the State of the Art
Sparrow integrates the exploration ability of BRKGA and the exploitation ability of ALNS.
EnGN: A High-Throughput and Energy-Efficient Accelerator for Large Graph Neural Networks
Inspired by the great success of convolutional neural networks on structural data like videos and images, graph neural network (GNN) emerges as a powerful approach to process non-euclidean data structures and has been proved powerful in various application domains such as social network, e-commerce, and knowledge graph.
Distributed, Parallel, and Cluster Computing
Forward-Backward Decoding for Regularizing End-to-End TTS
Experimental results show our proposed methods especially the second one (bidirectional decoder regularization), leads a significantly improvement on both robustness and overall naturalness, as outperforming baseline (the revised version of Tacotron2) with a MOS gap of 0. 14 in a challenging test, and achieving close to human quality (4. 42 vs. 4. 49 in MOS) on general test.
Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTS
In this paper, we propose a novel stepwise monotonic attention method in sequence-to-sequence acoustic modeling to improve the robustness on out-of-domain inputs.
Exploiting Syntactic Features in a Parsed Tree to Improve End-to-End TTS
The end-to-end TTS, which can predict speech directly from a given sequence of graphemes or phonemes, has shown improved performance over the conventional TTS.
A New GAN-based End-to-End TTS Training Algorithm
However, the autoregressive module training is affected by the exposure bias, or the mismatch between the different distributions of real and predicted data.
Feature reinforcement with word embedding and parsing information in neural TTS
In this paper, we propose a feature reinforcement method under the sequence-to-sequence neural text-to-speech (TTS) synthesis framework.
Modeling Multi-speaker Latent Space to Improve Neural TTS: Quick Enrolling New Speaker and Enhancing Premium Voice
Neural TTS has shown it can generate high quality synthesized speech.
Recurrent Neural Networks with Pre-trained Language Model Embedding for Slot Filling Task
In recent years, Recurrent Neural Networks (RNNs) based models have been applied to the Slot Filling problem of Spoken Language Understanding and achieved the state-of-the-art performances.
Learning latent representations for style control and transfer in end-to-end speech synthesis
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.
Learning Depth from Single Images with Deep Neural Network Embedding Focal Length
In order to learn monocular depth by embedding the focal length, we propose a method to generate synthetic varying-focal-length dataset from fixed-focal-length datasets, and a simple and effective method is implemented to fill the holes in the newly generated images.
Abstractive News Summarization based on Event Semantic Link Network
This paper studies the abstractive multi-document summarization for event-oriented news texts through event information extraction and abstract representation.
Exploring Differential Topic Models for Comparative Summarization of Scientific Papers
This paper investigates differential topic models (dTM) for summarizing the differences among document groups.
A Unified Tagging Solution: Bidirectional LSTM Recurrent Neural Network with Word Embedding
Bidirectional Long Short-Term Memory Recurrent Neural Network (BLSTM-RNN) has been shown to be very effective for modeling and predicting sequential data, e. g. speech utterances or handwritten documents.
Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network
Bidirectional Long Short-Term Memory Recurrent Neural Network (BLSTM-RNN) has been shown to be very effective for tagging sequential data, e. g. speech utterances or handwritten documents.
Fast Iteratively Reweighted Least Squares Algorithms for Analysis-Based Sparsity Reconstruction
The convergence rate of the proposed algorithm is almost the same as that of the traditional IRLS algorithms, that is, exponentially fast.
Preconditioning for Accelerated Iteratively Reweighted Least Squares in Structured Sparsity Reconstruction
In this paper, we propose a novel algorithm for structured sparsity reconstruction.
