Search Results for author:
Found 25 papers, 8 papers with code
InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music Generation
This framework enables the controllable generation of high-fidelity long-form music at a higher sampling rate from both text and audio prompts.
Emotional Dimension Control in Language Model-Based Text-to-Speech: Spanning a Broad Spectrum of Human Emotions
Current emotional text-to-speech (TTS) systems face challenges in mimicking a broad spectrum of human emotions due to the inherent complexity of emotions and limitations in emotional speech datasets and models.
Skip-Layer Attention: Bridging Abstract and Detailed Dependencies in Transformers
The Transformer architecture has significantly advanced deep learning, particularly in natural language processing, by effectively managing long-range dependencies.
Phonetic Enhanced Language Modeling for Text-to-Speech Synthesis
Recent language model-based text-to-speech (TTS) frameworks demonstrate scalability and in-context learning capabilities.
LiqD: A Dynamic Liquid Level Detection Model under Tricky Small Containers
A large number of experimental results show that the proposed model can effectively detect the dynamic liquid level changes of the liquid in the container, providing a novel and efficient solution for related fields.
ICE-GRT: Instruction Context Enhancement by Generative Reinforcement based Transformers
The emergence of Large Language Models (LLMs) such as ChatGPT and LLaMA encounter limitations in domain-specific tasks, with these models often lacking depth and accuracy in specialized areas, and exhibiting a decrease in general capabilities when fine-tuned, particularly analysis ability in small sized models.
Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token-based ASR
We find that applying the conventional cross-entropy loss on input speech tokens does not consistently improve the ASR performance over the Loss Masking approach.
Balancing Specialized and General Skills in LLMs: The Impact of Modern Tuning and Data Strategy
This paper introduces a multifaceted methodology for fine-tuning and evaluating large language models (LLMs) for specialized monetization tasks.
SPGM: Prioritizing Local Features for enhanced speech separation performance
Dual-path is a popular architecture for speech separation models (e. g. Sepformer) which splits long sequences into overlapping chunks for its intra- and inter-blocks that separately model intra-chunk local features and inter-chunk global relationships.
Ranked #11 on
Speech Separation
on WSJ0-2mix
ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention
In this paper, we propose ACA-Net, a lightweight, global context-aware speaker embedding extractor for Speaker Verification (SV) that improves upon existing work by using Asymmetric Cross Attention (ACA) to replace temporal pooling.
Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings
Prior studies diagnose the anisotropy problem in sentence representations from pre-trained language models, e. g., BERT, without fine-tuning.
Doubly Robust Estimators with Weak Overlap
In this paper, we derive a new class of doubly robust estimators for treatment effect estimands that is also robust against weak covariate overlap.
Adaptive Knowledge Distillation between Text and Speech Pre-trained Models
Learning on a massive amount of speech corpus leads to the recent success of many self-supervised speech models.
Identification-robust inference for the LATE with high-dimensional covariates
This paper presents an inference method for the local average treatment effect (LATE) in the presence of high-dimensional covariates, irrespective of the strength of identification.
Dyadic double/debiased machine learning for analyzing determinants of free trade agreements
Together with the use of Neyman orthogonal scores, this novel cross fitting method enables root-$n$ consistent estimation and inference robustly against dyadic dependence.
Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch
In this paper, we are the first to study training from scratch an N:M fine-grained structured sparse network, which can maintain the advantages of both unstructured fine-grained sparsity and structured coarse-grained sparsity simultaneously on specifically designed GPUs.
MulCode: A Multiplicative Multi-way Model for Compressing Neural Language Model
For example, input embedding and Softmax matrices in IWSLT-2014 German-to-English data set account for more than 80{\%} of the total model parameters.
Learning Classifiers on Positive and Unlabeled Data with Policy Gradient
Existing algorithms aiming to learn a binary classifier from positive (P) and unlabeled (U) data generally require estimating the class prior or label noises ahead of building a classification model.
Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization
Experiment results show that SCT improves accuracy of single Resnet-50 on ImageNet by 1. 7% and 11. 5% accuracy when testing on image sizes of 224 and 128 respectively.
Phonetic-enriched Text Representation for Chinese Sentiment Analysis with Reinforcement Learning
Furthermore, we also fuse phonetic features with textual and visual features in order to mimic the way humans read and understand Chinese text.
Deep Heterogeneous Autoencoders for Collaborative Filtering
This paper leverages heterogeneous auxiliary information to address the data sparsity problem of recommender systems.
Concept-Based Embeddings for Natural Language Processing
In this work, we focus on effectively leveraging and integrating information from concept-level as well as word-level via projecting concepts and words into a lower dimensional space while retaining most critical semantics.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM
Analyzing people’s opinions and sentiments towards certain aspects is an important task of natural language understanding.
Ranked #4 on
Aspect-Based Sentiment Analysis (ABSA)
on Sentihood
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
Label Embedding for Zero-shot Fine-grained Named Entity Typing
Named entity typing is the task of detecting the types of a named entity in context.
