Search Results for author:
Found 189 papers, 71 papers with code
Toward Knowledge-Enriched Conversational Recommendation Systems
Conversational Recommendation Systems recommend items through language based interactions with users. In order to generate naturalistic conversations and effectively utilize knowledge graphs (KGs) containing background information, we propose a novel Bag-of-Entities loss, which encourages the generated utterances to mention concepts related to the item being recommended, such as the genre or director of a movie.
Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization
Current emotional text-to-speech (TTS) models predominantly conduct supervised training to learn the conversion from text and desired emotion to its emotional speech, focusing on a single emotion per text-speech pair.
A Compressive Memory-based Retrieval Approach for Event Argument Extraction
Recent works have demonstrated the effectiveness of retrieval augmentation in the Event Argument Extraction (EAE) task.
Half-VAE: An Encoder-Free VAE to Bypass Explicit Inverse Mapping
Variational inference, a subset of Bayesian inference, is primarily used to efficiently approximate complex posterior distributions.
Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language Models
Furthermore, the integration experiments with various LLMs on the mentioned datasets highlight the flexibility of DoG.
LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture
Expanding the long-context capabilities of Multi-modal Large Language Models~(MLLMs) is crucial for video understanding, high-resolution image understanding, and multi-modal agents.
VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing
For tasks such as text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), a cross-modal fine-grained (frame-level) sequence representation is desired, emphasizing the semantic content of the text modality while de-emphasizing the paralinguistic information of the speech modality.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
MulliVC: Multi-lingual Voice Conversion With Cycle Consistency
Specifically, each training step of MulliVC contains three substeps: In step one the model is trained with monolingual speech data; then, steps two and three take inspiration from back translation, construct a cyclical process to disentangle the timbre and other information (content, prosody, and other language-related information) in the absence of multi-lingual data from the same speaker.
Calibrating the Heston Model with Deep Differential Networks
Our neural network, henceforth deep differential network (DDN), learns both the Heston pricing formula for plain-vanilla options and the partial derivatives with respect to the model parameters.
XTraffic: A Dataset Where Traffic Meets Incidents with Explainability and More
Our data can revolutionalize traditional traffic-related tasks towards higher interpretability and practice: instead of traditional prediction or classification tasks, we conduct: (1) post-incident traffic forecasting to quantify the impact of different incidents on traffic indexes; (2) incident classification using traffic indexes to determine the incidents types for precautions measures; (3) global causal analysis among the traffic indexes, meta-attributes, and incidents to give high-level guidance of the interrelations of various factors; (4) local causal analysis within road nodes to examine how different incidents affect the road segments' relations.
Unlocking the Potential of Model Merging for Low-Resource Languages
Adapting large language models (LLMs) to new languages typically involves continual pre-training (CT) followed by supervised fine-tuning (SFT).
DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models
Large language models (LLMs) have demonstrated emergent capabilities across diverse reasoning tasks via popular Chains-of-Thought (COT) prompting.
RefXVC: Cross-Lingual Voice Conversion with Enhanced Reference Leveraging
This paper proposes RefXVC, a method for cross-lingual voice conversion (XVC) that leverages reference information to improve conversion performance.
Extracting thin film structures of energy materials using transformers
Neutron-Transformer Reflectometry and Advanced Computation Engine (N-TRACE ), a neural network model using transformer architecture, is introduced for neutron reflectometry data analysis.
Harvesting Efficient On-Demand Order Pooling from Skilled Couriers: Enhancing Graph Representation Learning for Refining Real-time Many-to-One Assignments
In OFD, pooling multiple orders for simultaneous delivery in real-time order assignment is a pivotal efficiency source, which may in turn extend delivery time.
Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective
Enabling LLMs to handle lengthy context is currently a research hotspot.
Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment
Sh\=ukai quantifies the state to enhance generalizability, introducing Heterogeneous League Training (HELT) to achieve balanced competence, generalizability, and training efficiency.
TS-Align: A Teacher-Student Collaborative Framework for Scalable Iterative Finetuning of Large Language Models
This automatic mining process is efficiently accomplished through the collaboration between a large-scale teacher model and a small-scale student model.
Functional Programming Paradigm of Python for Scientific Computation Pipeline Integration
The advent of modern data processing has led to an increasing tendency towards interdisciplinarity, which frequently involves the importation of different technical approaches.
Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models
Specifically, inspired by the recent success of large language models (LLMs) in text generation and evaluation, we adopt strong LLMs as both the data generator and gold evaluator.
Nonparametric Teaching of Implicit Neural Representations
We investigate the learning of implicit neural representation (INR) using an overparameterized multilayer perceptron (MLP) via a novel nonparametric teaching perspective.
Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
For fine-grained language understanding, we train a Multimodal Large Language Model to refine the captions of the images.
Can Perplexity Reflect Large Language Model's Ability in Long Text Understanding?
Recent studies have shown that Large Language Models (LLMs) have the potential to process extremely long text.
Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction
Recent mainstream event argument extraction methods process each event in isolation, resulting in inefficient inference and ignoring the correlations among multiple events.
Beyond the Speculative Game: A Survey of Speculative Execution in Large Language Models
The bottleneck is mainly due to the autoregressive innateness of LLMs, where tokens can only be generated sequentially during decoding.
Towards Robustness of Text-to-Visualization Translation against Lexical and Phrasal Variability
Text-to-Vis is an emerging task in the natural language processing (NLP) area that aims to automatically generate data visualizations from natural language questions (NLQs).
Low-Rank Robust Subspace Tensor Clustering for Metro Passenger Flow Modeling
Moreover, a case study in the station clustering based on real passenger flow data is conducted, with quite valuable insights discovered.
DeepFunction: Deep Metric Learning-based Imbalanced Classification for Diagnosing Threaded Pipe Connection Defects using Functional Data
To classify the defect samples based on imbalanced, multichannel, and incomplete functional data is very important but challenging.
Partially-Observable Sequential Change-Point Detection for Autocorrelated Data via Upper Confidence Region
Meanwhile, by treating the detection power as a reward, its connection with the online combinatorial multi-armed bandit (CMAB) problem is formulated and an adaptive upper confidence region algorithm is proposed for adaptive sampling policy design.
Functional-Edged Network Modeling
Contrasts with existing works which all consider nodes as functions and use edges to represent the relationships between different functions.
CrossTune: Black-Box Few-Shot Classification with Label Enhancement
Training or finetuning large-scale language models (LLMs) requires substantial computation resources, motivating recent efforts to explore parameter-efficient adaptation to downstream tasks.
Harder Tasks Need More Experts: Dynamic Routing in MoE Models
In this paper, we introduce a novel dynamic expert selection framework for Mixture of Experts (MoE) models, aiming to enhance computational efficiency and model performance by adjusting the number of activated experts based on input difficulty.
Deep Reinforcement Learning for Modelling Protein Complexes
In this work, by taking each chain as a node and assembly actions as edges, we show that an acyclic undirected connected graph can be used to predict the structure of multi-chain protein complexes (a. k. a., protein complex modelling, PCM).
Teaching Large Language Models an Unseen Language on the Fly
We introduce DiPMT++, a framework for adapting LLMs to unseen languages by in-context learning.
Weakly Supervised Anomaly Detection via Knowledge-Data Alignment
In this paper, we introduce a novel framework Knowledge-Data Alignment (KDAlign) to integrate rule knowledge, typically summarized by human experts, to supplement the limited labeled data.
Prompt4Vis: Prompting Large Language Models with Example Mining and Schema Filtering for Tabular Data Visualization
Data visualization (DV) systems are increasingly recognized for their profound capability to uncover insights from vast datasets, gaining attention across both industry and academia.
PSDF: Prior-Driven Neural Implicit Surface Learning for Multi-view Reconstruction
While NISR has shown impressive results on simple scenes, it remains challenging to recover delicate geometry from uncontrolled real-world scenes which is caused by its underconstrained optimization.
Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis
One-shot 3D talking portrait generation aims to reconstruct a 3D avatar from an unseen image, and then animate it with a reference video or audio to generate a talking portrait video.
Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering
These methods utilize both the metadata and the sRGB image to perform sRGB-to-RAW de-rendering and recover high-quality single-frame RAW data.
A Comprehensive Analysis of the Effectiveness of Large Language Models as Automatic Dialogue Evaluators
Yet, existing works on utilizing LLMs for automatic dialogue evaluation are limited in their scope in terms of the number of meta-evaluation datasets, mode of evaluation, coverage of LLMs, etc.
Relation-Aware Question Answering for Heterogeneous Knowledge Graphs
To address this issue, we construct a \textbf{dual relation graph} where each node denotes a relation in the original KG (\textbf{primal entity graph}) and edges are constructed between relations sharing same head or tail entities.
PR-NeuS: A Prior-based Residual Learning Paradigm for Fast Multi-view Neural Surface Reconstruction
In this work, we propose a prior-based residual learning paradigm for fast multi-view neural surface reconstruction.
Dynamic Erasing Network Based on Multi-Scale Temporal Features for Weakly Supervised Video Anomaly Detection
To address these limitations, we propose a Dynamic Erasing Network (DE-Net) for weakly supervised video anomaly detection, which learns multi-scale temporal features.
Work State-Centric AI Agents: Design, Implementation, and Management of Cognitive Work Threads
AI agents excel in executing predefined tasks, but the dynamic management of work state information during task execution remains an underexplored area.
MC$^2$: Towards Transparent and Culturally-Aware NLP for Minority Languages in China
To address this accessibility challenge, we present MC$^2$, a Multilingual Corpus of Minority Languages in China, which is the largest open-source corpus of its kind so far.
Towards the Law of Capacity Gap in Distilling Language Models
Language model (LM) distillation is a trending area that aims to distil the knowledge residing in a large teacher LM to a small student one.
On Elastic Language Models
To this end, we propose an elastic language model (ElasticLM) that elastically adjusts the tradeoff according to the request stream.
Sparse Contrastive Learning of Sentence Embeddings
Recently, SimCSE has shown the feasibility of contrastive learning in training sentence embeddings and illustrates its expressiveness in spanning an aligned and uniform embedding space.
Choose A Table: Tensor Dirichlet Process Multinomial Mixture Model with Graphs for Passenger Trajectory Clustering
In this paper, we propose a novel tensor Dirichlet Process Multinomial Mixture model with graphs, which can preserve the hierarchical structure of the multi-dimensional trip information and cluster them in a unified one-step manner with the ability to determine the number of clusters automatically.
xDial-Eval: A Multilingual Open-Domain Dialogue Evaluation Benchmark
The English dialogue data are extended to nine other languages with commercial machine translation systems.
PG-NeuS: Robust and Efficient Point Guidance for Multi-View Neural Surface Reconstruction
Recently, learning multi-view neural surface reconstruction with the supervision of point clouds or depth maps has been a promising way.
Unsupervised Learning of Nanoindentation Data to Infer Microstructural Details of Complex Materials
In this study, Cu-Cr composites were studied by nanoindentation.
C2G2: Controllable Co-speech Gesture Generation with Latent Diffusion Model
Co-speech gesture generation is crucial for automatic digital avatar animation.
Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detection
By integrating complementary information from RGB image and depth map, the ability of salient object detection (SOD) for complex and challenging scenes can be improved.
Do We Fully Understand Students' Knowledge States? Identifying and Mitigating Answer Bias in Knowledge Tracing
Existing models tend to memorize the answer bias as a shortcut for achieving high prediction performance in KT, thereby failing to fully understand students' knowledge states.
User-Controlled Knowledge Fusion in Large Language Models: Balancing Creativity and Hallucination
Our approach incorporates a numerical tag during the fine-tuning phase of the LLM's training, representing the degree of faithfulness to the reference knowledge in the generated responses.
Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis
However, the prompting mechanisms of zero-shot TTS still face challenges in the following aspects: 1) previous works of zero-shot TTS are typically trained with single-sentence prompts, which significantly restricts their performance when the data is relatively sufficient during the inference stage.
PowerFusion: A Tensor Compiler with Explicit Data Movement Description and Instruction-level Graph IR
To accelerate DNN computation, tensor compilers are proposed to generate efficient code on different domain-specific accelerators.
Tensor Dirichlet Process Multinomial Mixture Model for Passenger Trajectory Clustering
In this paper, we propose a novel Tensor Dirichlet Process Multinomial Mixture model (Tensor-DPMM), which is designed to preserve the multi-mode and hierarchical structure of the multi-dimensional trip information via tensor, and cluster them in a unified one-step manner.
Overview of Robust and Multilingual Automatic Evaluation Metrics for Open-Domain Dialogue Systems at DSTC 11 Track 4
The advent and fast development of neural networks have revolutionized the research on dialogue systems and subsequently have triggered various challenges regarding their automatic evaluation.
Dynamic Causal Graph Convolutional Network for Traffic Prediction
In this work, we propose a novel approach for traffic prediction that embeds time-varying dynamic Bayesian network to capture the fine spatiotemporal topology of traffic data.
Ranked #13 on
Traffic Prediction
on METR-LA
Ada-TTA: Towards Adaptive High-Quality Text-to-Talking Avatar Synthesis
We are interested in a novel task, namely low-resource text-to-talking avatar.
Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias
3) We further use a VQGAN-based acoustic model to generate the spectrogram and a latent code language model to fit the distribution of prosody, since prosody changes quickly over time in a sentence, and language models can capture both local and long-range dependencies.
MM-DAG: Multi-task DAG Learning for Multi-modal Data -- with Application for Traffic Congestion Analysis
This encourages the multi-task design: with each DAG as a task, the MM-DAG tries to learn the multiple DAGs jointly so that their consensus and consistency are maximized.
Nonparametric Iterative Machine Teaching
In this paper, we consider the problem of Iterative Machine Teaching (IMT), where the teacher provides examples to the learner iteratively such that the learner can achieve fast convergence to a target model.
Temporal-spatial Correlation Attention Network for Clinical Data Analysis in Intensive Care Unit
Our method can also find key clinical indicators of important outcomes that can be used to improve treatment options.
Deep Reinforcement Learning Framework for Thoracic Diseases Classification via Prior Knowledge Guidance
The chest X-ray is often utilized for diagnosing common thoracic diseases.
How Many Answers Should I Give? An Empirical Study of Multi-Answer Reading Comprehension
We further analyze how well different paradigms of current multi-answer MRC models deal with different types of multi-answer instances.
The Magic of IF: Investigating Causal Reasoning Abilities in Large Language Models of Code
Causal reasoning, the ability to identify cause-and-effect relationship, is crucial in human thinking.
Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation
Finally, we use LLMs to augment and transform a large amount of audio-label data into audio-text datasets to alleviate the problem of scarcity of temporal data.
Ranked #8 on
Audio Generation
on AudioCaps
Lawyer LLaMA Technical Report
Specifically, we inject domain knowledge during the continual training stage and teach the model to learn professional skills using properly designed supervised fine-tuning tasks.
Enhancing Black-Box Few-Shot Text Classification with Prompt-Based Data Augmentation
To achieve this, we treat the black-box model as a feature extractor and train a classifier with the augmented text data.
Task-agnostic Distillation of Encoder-Decoder Language Models
Finetuning pretrained language models (LMs) have enabled appealing performance on a diverse array of tasks.
EE-TTS: Emphatic Expressive TTS with Linguistic Information
EE-TTS contains an emphasis predictor that can identify appropriate emphasis positions from text and a conditioned acoustic model to synthesize expressive speech with emphasis and linguistic information.
Chest X-ray Image Classification: A Causal Perspective
The chest X-ray (CXR) is one of the most common and easy-to-get medical tests used to diagnose common diseases of the chest.
Lifting the Curse of Capacity Gap in Distilling Language Models
However, when the capacity gap between the teacher and the student is large, a curse of capacity gap appears, invoking a deficiency in distilling LMs.
Instrumental Variable Learning for Chest X-ray Classification
The chest X-ray (CXR) is commonly employed to diagnose thoracic illnesses, but the challenge of achieving accurate automatic diagnosis through this method persists due to the complex relationship between pathology.
REMAST: Real-time Emotion-based Music Arrangement with Soft Transition
Music as an emotional intervention medium has important applications in scenarios such as music therapy, games, and movies.
Phoenix: Democratizing ChatGPT across Languages
This paper presents our efforts to democratize ChatGPT across language.
Modular Retrieval for Generalization and Interpretation
Built upon the paradigm, we propose a retrieval model with modular prompt tuning named REMOP.
Road Extraction with Satellite Images and Partial Road Maps
In this paper, we propose to conduct road extraction based on satellite images and partial road maps, which is new.
STGIC: a graph and image convolution-based method for spatial transcriptomic clustering
Spatial transcriptomic (ST) clustering employs spatial and transcription information to group spots spatially coherent and transcriptionally similar together into the same spatial domain.
Cross-Lingual Question Answering over Knowledge Base as Reading Comprehension
We convert KB subgraphs into passages to narrow the gap between KB schemas and questions, which enables our model to benefit from recent advances in multilingual pre-trained language models (MPLMs) and cross-lingual machine reading comprehension (xMRC).
Cross-Lingual Question Answering
Machine Reading Comprehension
DMNet: Delaunay Meshing Network for 3D Shape Representation
We model the Delaunay triangulation as a dual graph, extract local geometric information from the points, and embed it into the structural representation of Delaunay triangulation in an organic way, benefiting fine-grained details reconstruction.
PoE: a Panel of Experts for Generalized Automatic Dialogue Assessment
To tackle the multi-domain dialogue evaluation task, we propose a Panel of Experts (PoE), a multitask network that consists of a shared transformer encoder and a collection of lightweight adapters.
One-shot Machine Teaching: Cost Very Few Examples to Converge Faster
Then, relying on the surjective mapping from the teaching set to the parameter, we develop a design strategy of the optimal teaching set under appropriate settings, of which two popular efficiency metrics, teaching dimension and iterative teaching dimension are one.
Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection
Weakly supervised video anomaly detection aims to identify abnormal events in videos using only video-level labels.
VideoDubber: Machine Translation with Speech-Aware Length Control for Video Dubbing
In this paper, we propose a machine translation system tailored for the task of video dubbing, which directly considers the speech duration of each token in translation, to match the length of source and target speech.
DGEKT: A Dual Graph Ensemble Learning Method for Knowledge Tracing
Knowledge tracing aims to trace students' evolving knowledge states by predicting their future performance on concept-related exercises.
FineD-Eval: Fine-grained Automatic Dialogue-Level Evaluation
Recent model-based reference-free metrics for open-domain dialogue evaluation exhibit promising correlations with human judgment.
Analyzing and Evaluating Faithfulness in Dialogue Summarization
The factual correctness of summaries has the highest priority before practical applications.
Deep Learning Based Stage-wise Two-dimensional Speaker Localization with Large Ad-hoc Microphone Arrays
To further boost the estimation accuracy, we introduce a node selection algorithm that strategically filters the most reliable nodes.
XPrompt: Exploring the Extreme of Prompt Tuning
Prompt tuning learns soft prompts to condition frozen Pre-trained Language Models (PLMs) for performing downstream tasks in a parameter-efficient manner.
Does Thermal Really Always Matter for RGB-T Salient Object Detection?
In addition, considering the role of thermal modality, we set up different cross-modality interaction mechanisms in the encoding phase and the decoding phase.
Sparse Teachers Can Be Dense with Knowledge
Recent advances in distilling pretrained language models have discovered that, besides the expressiveness of knowledge, the student-friendliness should be taken into consideration to realize a truly knowledgable teacher.
CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection
Focusing on the issue of how to effectively capture and utilize cross-modality information in RGB-D salient object detection (SOD) task, we present a convolutional neural network (CNN) model, named CIR-Net, based on the novel cross-modality interaction and refinement.
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
A Focused Study on Sequence Length for Dialogue Summarization
Output length is critical to dialogue summarization systems.
Asset Pricing and Deep Learning
My findings not only justify the value of deep learning in blooming fintech development, but also highlight their prospects and advantages over traditional machine learning methods.
Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training
An activation function is an element-wise mathematical function and plays a crucial role in deep neural networks (DNN).
SongDriver: Real-time Music Accompaniment Generation without Logical Latency nor Exposure Bias
In this paper, we propose SongDriver, a real-time music accompaniment generation system without logical latency nor exposure bias.
A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels
In this paper, we focus on a new weakly-supervised SOD task under hybrid labels, where the supervision labels include a large number of coarse labels generated by the traditional unsupervised method and a small number of real labels.
Ranked #7 on
RGB Salient Object Detection
on PASCAL-S
Knowledge-enhanced Iterative Instruction Generation and Reasoning for Knowledge Base Question Answering
Multi-hop Knowledge Base Question Answering(KBQA) aims to find the answer entity in a knowledge base which is several hops from the topic entity mentioned in the question.
Multi-scale temporal-frequency attention for music source separation
In recent years, deep neural networks (DNNs) based approaches have achieved the start-of-the-art performance for music source separation (MSS).
Structural Bias for Aspect Sentiment Triplet Extraction
Thus, a natural question arises: Is structural bias still a necessity in the context of PLMs?
ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization
In this work, we propose a fixed-length adaptive numerical data type called ANT to achieve low-bit quantization with tiny hardware overheads.
PyABSA: A Modularized Framework for Reproducible Aspect-based Sentiment Analysis
The advancement of aspect-based sentiment analysis (ABSA) has urged the lack of a user-friendly framework that can largely lower the difficulty of reproducing state-of-the-art ABSA performance, especially for beginners.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+5
Doge Tickets: Uncovering Domain-general Language Models by Playing Lottery Tickets
To uncover the domain-general LM, we propose to identify domain-general parameters by playing lottery tickets (dubbed doge tickets).
Aspect-specific Context Modeling for Aspect-based Sentiment Analysis
Extensive experimental results on standard and adversarial benchmarks for SC and OE demonstrate the effectiveness and robustness of the proposed method, yielding new state-of-the-art performance on OE and competitive performance on SC.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
SummScore: A Comprehensive Evaluation Metric for Summary Quality Based on Cross-Encoder
However, the existing evaluation metrics for summary text are only rough proxies for summary quality, suffering from low correlation with human scoring and inhibition of summary diversity.
BANet: Motion Forecasting with Boundary Aware Network
We propose a motion forecasting model called BANet, which means Boundary-Aware Network, and it is a variant of LaneGCN.
MiniDisc: Minimal Distillation Schedule for Language Model Compression
In particular, motivated by the finding that the performance of the student is positively correlated to the scale-performance tradeoff of the teacher assistant, MiniDisc is designed with a $\lambda$-tradeoff to measure the optimality of the teacher assistant without trial distillation to the student.
Making Pretrained Language Models Good Long-tailed Learners
Prompt-tuning has shown appealing performance in few-shot classification by virtue of its capability in effectively exploiting pre-trained knowledge.
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
(using extra training data)
Adaptable Text Matching via Meta-Weight Regulator
Neural text matching models have been used in a range of applications such as question answering and natural language inference, and have yielded a good performance.
Split Hierarchical Variational Compression
Secondly, we define our coding framework, the autoregressive initial bits, that flexibly supports parallel coding and avoids -- for the first time -- many of the practicalities commonly associated with bits-back coding.
Automatic Song Translation for Tonal Languages
This paper develops automatic song translation (AST) for tonal languages and addresses the unique challenge of aligning words' tones with melody of a song in addition to conveying the original meaning.
Report from the NSF Future Directions Workshop on Automatic Evaluation of Dialog: Research Directions and Challenges
This is a report on the NSF Future Directions Workshop on Automatic Evaluation of Dialog.
S3T: Self-Supervised Pre-training with Swin Transformer for Music Classification
To our knowledge, S3T is the first method combining the Swin Transformer with a self-supervised learning method for music classification.
L3DAS22 Challenge: Learning 3D Audio Sources in a Real Office Environment
The L3DAS22 Challenge is aimed at encouraging the development of machine learning strategies for 3D speech enhancement and 3D sound localization and detection in office-like environments.
SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation
This paper proposes an on-the-fly DFQ framework with sub-second quantization time, called SQuant, which can quantize networks on inference-only devices with low computation and memory requirements.
A two-step backward compatible fullband speech enhancement system
Speech enhancement methods based on deep learning have surpassed traditional methods.
MDD-Eval: Self-Training on Augmented Data for Multi-Domain Dialogue Evaluation
Chatbots are designed to carry out human-like conversations across different domains, such as general chit-chat, knowledge exchange, and persona-grounded conversations.
Ranked #1 on
Dialogue Evaluation
on USR-TopicalChat
Boosting Mobile CNN Inference through Semantic Memory
Human brains are known to be capable of speeding up visual recognition of repeatedly presented objects through faster memory encoding and accessing procedures on activated neurons.
A Practical Method for Automated Modeling and Parametric Stability Analysis of VSC with Periodical Steady State
In these studies, acquisition of the VSC's PSS conditions is a necessary precondition for proper linearization and stability analysis, and the efficiency of this process is particularly important for parametric studies.
Automatic Evaluation and Moderation of Open-domain Dialogue Systems
The development of Open-Domain Dialogue Systems (ODS)is a trending topic due to the large number of research challenges, large societal and business impact, and advances in the underlying technology.
OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compression
To eliminate the requirement of saving separate models for different target datasets, we propose a novel setting that starts from a pretrained deep generative model and compresses the data batches while adapting the model with a dynamical system for only one epoch.
Transient Synchronization Stability Analysis of Wind Farms with MMC-HVDC Integration Under Offshore AC Grid Fault
The MMC-HVDC connected offshore wind farms (OWFs) could suffer short circuit fault (SCF), whereas their transient stability is not well analysed.
Conditional Variational Autoencoder for Learned Image Reconstruction
Learned image reconstruction techniques using deep neural networks have recently gained popularity, and have delivered promising empirical results.
Investigating the Impact of Pre-trained Language Models on Dialog Evaluation
Yet, the impact of different Pr-LMs on the performance of automatic metrics is not well-understood.
Revisiting Self-Training for Few-Shot Learning of Language Model
In this work, we revisit the self-training technique for language model fine-tuning and present a state-of-the-art prompt-based few-shot learner, SFLM.
Improving Object Permanence using Agent Actions and Reasoning
Finally, we evaluate the usability of our approach in real-world applications by conducting qualitative experiments with two Universal Robots (UR5 and UR16e) in both lab and industrial settings.
Spread Flows for Manifold Modelling
Flow-based models typically define a latent space with dimensionality identical to the observational space.
TeleMelody: Lyric-to-Melody Generation with a Template-Based Two-Stage Method
In this paper, we develop TeleMelody, a two-stage lyric-to-melody generation system with music template (e. g., tonality, chord progression, rhythm pattern, and cadence) to bridge the gap between lyrics and melodies (i. e., the system consists of a lyric-to-template module and a template-to-melody module).
Revisiting the Characteristics of Stochastic Gradient Noise and Dynamics
In this paper, we characterize the noise of stochastic gradients and analyze the noise-induced dynamics during training deep neural networks by gradient-based optimizers.
PDAugment: Data Augmentation by Pitch and Duration Adjustments for Automatic Lyrics Transcription
Considering that there is a large amount of ASR training data, a straightforward method is to leverage ASR data to enhance ALT training.
Automatic Lyrics Transcription
Automatic Speech Recognition
+3
Extract, Integrate, Compete: Towards Verification Style Reading Comprehension
In this paper, we present a new verification style reading comprehension dataset named VGaokao from Chinese Language tests of Gaokao.
Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms
In this framework, the environment can be easily configured to realize all kinds of RL tasks in the mainstream research.
Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection
For the cross-modality interaction in feature encoder, existing methods either indiscriminately treat RGB and depth modalities, or only habitually utilize depth cues as auxiliary information of the RGB branch.
A Causal U-net based Neural Beamforming Network for Real-Time Multi-Channel Speech Enhancement
In this work, a new causal U-net based multiple-in-multiple-out structure is proposed for real-time multi-channel speech enhancement.
CompConv: A Compact Convolution Module for Efficient Feature Learning
Convolutional Neural Networks (CNNs) have achieved remarkable success in various computer vision tasks but rely on tremendous computational cost.
DynaEval: Unifying Turn and Dialogue Level Evaluation
Effective evaluation metrics should reflect the dynamics of such interaction.
Why Machine Reading Comprehension Models Learn Shortcuts?
A thorough empirical analysis shows that MRC models tend to learn shortcut questions earlier than challenging questions, and the high proportions of shortcut questions in training sets hinder models from exploring the sophisticated reasoning skills in the later stage of training.
Parkinsonian Chinese Speech Analysis towards Automatic Classification of Parkinson's Disease
Speech disorders often occur at the early stage of Parkinson's disease (PD).
Exploiting Position Bias for Robust Aspect Sentiment Classification
Aspect sentiment classification (ASC) aims at determining sentiments expressed towards different aspects in a sentence.
Large-Signal Grid-Synchronization Stability Analysis of PLL-based VSCs Using Lyapunov's Direct Method
Grid-synchronization stability (GSS) is an emerging stability issue of grid-tied voltage source converters (VSCs), which can be provoked by severe grid voltage sags.
Dual-side Sparse Tensor Core
We demonstrate the feasibility of our design with minimal changes to the existing production-scale inner-product-based Tensor Core.
KECRS: Towards Knowledge-Enriched Conversational Recommendation System
The chit-chat-based conversational recommendation systems (CRS) provide item recommendations to users through natural language interactions.
Decorating Your Own Bedroom: Locally Controlling Image Generation with Generative Adversarial Networks
Generative Adversarial Networks (GANs) have made great success in synthesizing high-quality images.
Multi-view Clustering via Deep Matrix Factorization and Partition Alignment
iii) The partition level information has not been utilized in existing work.
Multi-view Clustering with Deep Matrix Factorization and Global Graph Refinement
Multi-view clustering is an important yet challenging task in machine learning and data mining community.
iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression
We also propose a lossless compression algorithm based on iVPF.
Untangling scaling dimensions of fixed charge operators in Higgs Theories
We go beyond a systematic review of the semiclassical approaches for determining the scaling dimensions of fixed-charge operators in $U(1)$ and $O(N)$ models by introducing a general strategy apt at determining the relation between a given charge configuration and the associated operators for more involved symmetry groups such as the $U(N) \times U(M)$.
High Energy Physics - Theory Statistical Mechanics High Energy Physics - Lattice High Energy Physics - Phenomenology