research
∙
09/18/2023
Stabilizing RLHF through Advantage Model and Selective Rehearsal
Large Language Models (LLMs) have revolutionized natural language proces...
share
research
∙
09/18/2023
Proposition from the Perspective of Chinese Language: A Chinese Proposition Classification Evaluation Benchmark
Existing propositions often rely on logical constants for classification...
research
∙
09/15/2023
LASER: LLM Agent with State-Space Exploration for Web Navigation
Large language models (LLMs) have been successfully adapted for interact...
research
∙
09/14/2023
SpatialCodec: Neural Spatial Speech Coding
In this work, we address the challenge of encoding speech captured by a ...
research
∙
09/14/2023
M3-AUDIODEC: Multi-channel multi-speaker multi-spatial audio codec
We introduce M3-AUDIODEC, an innovative neural spatial audio codec desig...
research
∙
09/08/2023
Unsupervised Multi-document Summarization with Holistic Inference
Multi-document summarization aims to obtain core information from a coll...
research
∙
09/04/2023
Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation
Mapping two modalities, speech and text, into a shared representation sp...
research
∙
08/19/2023
Bayes Risk Transducer: Transducer with Controllable Alignment Prediction
Automatic speech recognition (ASR) based on transducers is widely used. ...
research
∙
08/01/2023
Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models
We consider the problem of eliciting compositional generalization capabi...
research
∙
07/19/2023
Thrust: Adaptively Propels Large Language Models with External Knowledge
Although large-scale pre-trained language models (PTLMs) are shown to en...
research
∙
07/16/2023
MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuning
Reasoning in mathematical domains remains a significant challenge for re...
research
∙
07/08/2023
A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation
Recently developed large language models have achieved remarkable succes...
research
∙
05/30/2023
Make-A-Voice: Unified Voice Synthesis With Discrete Representation
Various applications of voice synthesis have been developed independentl...
research
∙
05/24/2023
PIVOINE: Instruction Tuning for Open-world Information Extraction
We consider the problem of Open-world Information Extraction (Open-world...
research
∙
05/24/2023
Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations
Traditional sentence embedding models encode sentences into vector repre...
research
∙
05/22/2023
Open-Domain Event Graph Induction for Mitigating Framing Bias
Researchers have proposed various information extraction (IE) techniques...
research
∙
05/04/2023
Faithful Question Answering with Monte-Carlo Planning
Although large language models demonstrate remarkable question-answering...
research
∙
02/27/2023
3D Neural Beamforming for Multi-channel Speech Separation Against Location Uncertainty
Multi-channel speech separation using speaker's directional information ...
research
∙
02/16/2023
Search-Engine-augmented Dialogue Response Generation with Cheaply Supervised Query Production
Knowledge-aided dialogue response generation aims at augmenting chatbots...
research
∙
01/31/2023
Friend-training: Learning from Models of Different but Related Tasks
Current self-training methods such as standard self-training, co-trainin...
research
∙
01/31/2023
InstructTTS: Modelling Expressive TTS in Discrete Latent Space with Natural Language Style Prompt
Expressive text-to-speech (TTS) aims to synthesize different speaking st...
research
∙
01/31/2023
Neural Target Speech Extraction: An Overview
Humans can listen to a target speaker even in challenging acoustic condi...
research
∙
12/19/2022
OASum: Large-Scale Open Domain Aspect-based Summarization
Aspect or query-based summarization has recently caught more attention, ...
research
∙
12/16/2022
Towards Unified All-Neural Beamforming for Time and Frequency Domain Speech Separation
Recently, frequency domain all-neural beamforming methods have achieved ...
research
∙
12/06/2022
ZeroKBC: A Comprehensive Benchmark for Zero-Shot Knowledge Base Completion
Knowledge base completion (KBC) aims to predict the missing links in kno...
research
∙
11/22/2022
Deep Neural Mel-Subband Beamformer for In-car Speech Separation
While current deep learning (DL)-based beamforming techniques have been ...
research
∙
11/09/2022
Efficient Zero-shot Event Extraction with Context-Definition Alignment
Event extraction (EE) is the task of identifying interested event mentio...
research
∙
10/28/2022
Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models
Fully-parametric language models generally require a huge number of mode...
research
∙
10/28/2022
Toward Unifying Text Segmentation and Long Document Summarization
Text segmentation is important for signaling a document's structure. Wit...
research
∙
10/22/2022
MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure
In this paper, we propose a comprehensive benchmark to investigate model...
research
∙
10/22/2022
Salience Allocation as Guidance for Abstractive Summarization
Abstractive summarization models typically learn to capture the salient ...
research
∙
10/21/2022
Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination
Large-scale pretrained language models have made significant advances in...
research
∙
10/14/2022
Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence tasks
Sequence-to-Sequence (seq2seq) tasks transcribe the input sequence to a ...
research
∙
10/11/2022
Cross-Lingual Speaker Identification Using Distant Supervision
Speaker identification, determining which character said each utterance ...
research
∙
10/01/2022
Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks
Although large language models have achieved impressive zero-shot abilit...
research
∙
08/15/2022
C3-DINO: Joint Contrastive and Non-contrastive Self-Supervised Learning for Speaker Verification
Self-supervised learning (SSL) has drawn an increased attention in the f...
research
∙
07/20/2022
Diffsound: Discrete Diffusion Model for Text-to-sound Generation
Generating sound effects that humans want is an important topic. However...
research
∙
06/22/2022
Hierarchical Context Tagging for Utterance Rewriting
Utterance rewriting aims to recover coreferences and omitted information...
research
∙
06/06/2022
UTTS: Unsupervised TTS with Conditional Disentangled Sequential Variational Auto-encoder
In this paper, we propose a novel unsupervised text-to-speech (UTTS) fra...
research
∙
06/05/2022
LAE: Language-Aware Encoder for Monolingual and Multilingual ASR
Despite the rapid progress in automatic speech recognition (ASR) researc...
research
∙
05/20/2022
NeuralEcho: A Self-Attentive Recurrent Neural Network For Unified Acoustic Echo Suppression And Speech Enhancement
Acoustic echo cancellation (AEC) plays an important role in the full-dup...
research
∙
05/11/2022
Towards Improved Zero-shot Voice Conversion with Conditional DSVAE
Disentangling content and speaking style information is essential for ze...
research
∙
04/27/2022
Distant finetuning with discourse relations for stance classification
Approaches for the stance classification task, an important task for und...
research
∙
04/07/2022
3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition
Recently, Conformer based CTC/AED model has become a mainstream architec...
research
∙
03/30/2022
Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversion
Traditional studies on voice conversion (VC) have made progress with par...
research
∙
03/29/2022
Integrate Lattice-Free MMI into End-to-End Speech Recognition
In automatic speech recognition (ASR) research, discriminative criteria ...
research
∙
03/22/2022
Towards Abstractive Grounded Summarization of Podcast Transcripts
Podcasts have recently shown a rapid rise in popularity. Summarization o...
research
∙
03/19/2022
Learning-by-Narrating: Narrative Pre-Training for Zero-Shot Dialogue Comprehension
Comprehending a dialogue requires a model to capture diverse kinds of ke...
research
∙
03/16/2022
C-MORE: Pretraining to Answer Open-Domain Questions by Consulting Millions of References
We consider the problem of pretraining a two-stage open-domain question ...
research
∙
03/01/2022