Yayue Deng

Yayue Deng

Auto-generated profile, based on publicly available information

Yayue Deng

Beijing University of Posts and Telecommunications, Beijing, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 October 2024 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
JXJinlong Xue
Jinlong Xue
YDYayue Deng
Yayue Deng
Yingming GaoYingming Gao
Yingming Gao
Ya LiYa Li
Ya Li
Recent advancements in diffusion models and large language models (LLMs) have significantly propelled the field of generation tasks. Text-to-Audio (TTA), a burgeoning generation application designed to generate audio from natural language prompts, is attracting increasing attention. However, existing TTA studies often struggle with generation quality and text-audio alignment, especially for complex textual inputs. Drawing inspiration from state-of-the-art Text-to-Image (T2I) diffusion models, we introduce Auffusion, a TTA system adapting T2I model frameworks to TTA task, by effectively leveraging their inherent generative strengths and precise cross-modal alignment. Our objective and subjective evaluations demonstrate that Auffusion surpasses previous TTA approaches using limited data and computational resources. Furthermore, the text encoder serves as a critical bridge between text and audio, since it acts as an instruction for the diffusion model to generate coherent content. Previous studies in T2I recognize the significant impact of encoder choice on cross-modal alignment, like fine-grained details and object bindings, while similar evaluation is lacking in prior TTA works. Through comprehensive ablation studies and innovative cross-attention map visualizations, we provide insightful assessments, being the first to reveal the internal mechanisms in the TTA field and intuitively explain how different text encoders influence the diffusion process. Our findings reveal Auffusion's superior capability in generating audios that accurately match textual descriptions, which is further demonstrated in several related tasks, such as audio style transfer, inpainting, and other manipulations.

26 October 2023
Verified
Conference Paper
Open access
YDYayue Deng
Yayue Deng
JXJinlong Xue
Jinlong Xue
FWFengping Wang
Fengping Wang
Yingming GaoYingming Gao
Yingming Gao
Ya LiYa Li
Ya Li
Conversational Speech Synthesis (CSS) aims to produce speech appropriate for oral communication. However, the complexity of context dependency modeling poses significant challenges in the field of CSS, especially the mutual psychological influence between interlocutors. Previous studies have verified that prior commonsense knowledge helps machines understand subtle psychological information (e.g., feelings and intentions) in spontaneous oral dialogues. Therefore, to enhance context understanding and improve the naturalness of synthesized speech, we propose a novel conversational speech synthesis system (CMCU-CSS) that incorporates the Commonsense-based Multi-modal Context Understanding (CMCU) module to model the dynamic emotional interaction among interlocutors. Specifically, we first utilize three implicit states (intent state, internal state and external state) in CMCU to model the context dependency between inter/intra speakers with the help of commonsense knowledge. Furthermore, we infer emotion vectors from the fusion of these implicit states and multi-modal features to enhance the emotion discriminability of synthesized speech. This is the first attempt to combine commonsense knowledge with conversational speech synthesis, and its effect in terms of emotion discriminability of synthetic speech is evaluated by emotion recognition in conversation task. The results of subjective and objective evaluations demonstrate that the CMCU-CSS model achieves more natural speech with context-appropriate emotion and is equipped with the best emotion discriminability, surpassing that of other conversational speech synthesis models.

21 October 2024
Verified
Conference Paper
Open access
XYXinjie Yang
Xinjie Yang
XGXiaocheng Gong
Xiaocheng Gong
BTBinghao Tang
Binghao Tang
YLYang Lei
Yang Lei
YDYayue Deng
Yayue Deng
YXYajing Xu
Yajing Xu
Joint Multimodal Entity-Relation Extraction (JMERE) aims to extract entity-relationship triples in texts from given image-text pairs. As a joint multimodal information extraction task, it has attracted increasing research interest. Previous works of JMERE typically utilize graph networks to align textual entities and visual objects and achieve promising performance. However, these methods do not pay attention to the inconsistency between text and image and the straight alignment could limit the performance of JMERE models. In this paper, we propose a Consistency-adaptive text-image Alignment Generation (CAG) framework for various text-image consistency scenarios. Specifically, we propose a Consistency Factor (CF) to measure the consistency between images and texts. We also design consistency-adaptive contrastive learning based on CF, which can reduce the impact of inconsistent visual and textual information. Additionally, we adopt JMERE-specifical instruction tuning for better entity-relationship triplet generation. Experimental results on the JMERE dataset demonstrate that our proposed CAG is effective and achieves state-of-the-art performance.

26 March 2022 in arXiv
Verified
Preprint
Open access
PDF file
JXJinlong Xue
Jinlong Xue
YDYayue Deng
Yayue Deng
YHYichen Han
Yichen Han
Ya LiYa Li
Ya Li
JSJianqing Sun
Jianqing Sun
JLJiaen Liang
Jiaen Liang
In recent years, neural network based methods for multi-speaker text-to-speech synthesis (TTS) have made significant progress. However, the current speaker encoder models used in these methods still cannot capture enough speaker information. In this paper, we focus on accurate speaker encoder modeling and propose an end-to-end method that can generate high-quality speech and better similarity for both seen and unseen speakers. The proposed architecture consists of three separately trained components: a speaker encoder based on the state-of-the-art ECAPA-TDNN model which is derived from speaker verification task, a FastSpeech2 based synthesizer, and a HiFi-GAN vocoder. The comparison among different speaker encoder models shows our proposed method can achieve better naturalness and similarity. To efficiently evaluate our synthesized speech, we are the first to adopt deep learning based automatic MOS evaluation methods to assess our results, and these methods show great potential in automatic speech quality assessment.

5 June 2023 in arXiv
Verified
Preprint
Open access
PDF file
DKDengfeng Ke
Dengfeng Ke
YDYayue Deng
Yayue Deng
YJYukang Jia
Yukang Jia
JXJinlong Xue
Jinlong Xue
QLQi Luo
Qi Luo
BLBinghuai Lin
Binghuai Lin
Regressive Text-to-Speech (TTS) system utilizes attention mechanism to generate alignment between text and acoustic feature sequence. Alignment determines synthesis robustness (e.g, the occurence of skipping, repeating, and collapse) and rhythm via duration control. However, current attention algorithms used in speech synthesis cannot control rhythm using external duration information to generate natural speech while ensuring robustness. In this study, we propose Rhythm-controllable Attention (RC-Attention) based on Tracotron2, which improves robustness and naturalness simultaneously. Proposed attention adopts a trainable scalar learned from four kinds of information to achieve rhythm control, which makes rhythm control more robust and natural, even when synthesized sentences are extremely longer than training corpus. We use word errors counting and AB preference test to measure robustness of proposed method and naturalness of synthesized speech, respectively. Results shows that RC-Attention has the lowest word error rate of nearly 0.6%, compared with 11.8% for baseline system. Moreover, nearly 60% subjects prefer to the speech synthesized with RC-Attention to that with Forward Attention, because the former has more natural rhythm.