58 citations · 205 across the 130 of their papers we have counts for
47 papers · 1 filter
Generalized Audio Deepfake Detection Using Frame-level Latent Information Entropy
Botao Zhao, Zuheng Kang, Yayun He +4
Generalizability, the capacity of a robust model to perform effectively on unseen data, is crucial for audio deepfake detection due to the rapid evolution of text-to-speech (TTS) a…
RSET: Remapping-based Sorting Method for Emotion Transfer Speech Synthesis
Haoxiang Shi, Jianzong Wang, Xulong Zhang +3
Although current Text-To-Speech (TTS) models are able to generate high-quality speech samples, there are still challenges in developing emotion intensity controllable TTS. Most exi…
MAIN-VC: Lightweight Speech Representation Disentanglement for One-shot Voice Conversion
Pengcheng Li, Jianzong Wang, Xulong Zhang +3
One-shot voice conversion aims to change the timbre of any source speech to match that of the unseen target speaker with only one speech sample. Existing methods face difficulties…
Learning Expressive Disentangled Speech Representations with Soft Speech Units and Adversarial Style Augmentation
Yimin Deng, Jianzong Wang, Xulong Zhang +2
Voice conversion is the task to transform voice characteristics of source speech while preserving content information. Nowadays, self-supervised representation learning models are…
EfficientASR: Speech Recognition Network Compression via Attention Redundancy and Chunk-Level FFN Optimization
Jianzong Wang, Ziqi Liang, Xulong Zhang +2
In recent years, Transformer networks have shown remarkable performance in speech recognition tasks. However, their deployment poses challenges due to high computational and storag…
EAD-VC: Enhancing Speech Auto-Disentanglement for Voice Conversion with IFUB Estimator and Joint Text-Guided Consistent Learning
Ziqi Liang, Jianzong Wang, Xulong Zhang +3
Using unsupervised learning to disentangle speech into content, rhythm, pitch, and timbre for voice conversion has become a hot research topic. Existing works generally take into a…
CONTUNER: Singing Voice Beautifying with Pitch and Expressiveness Condition
Jianzong Wang, Pengcheng Li, Xulong Zhang +2
Singing voice beautifying is a novel task that has application value in people's daily life, aiming to correct the pitch of the singing voice and improve the expressiveness without…
Retrieval-Augmented Audio Deepfake Detection
Zuheng Kang, Yayun He, Botao Zhao +4
With recent advances in speech synthesis including text-to-speech (TTS) and voice conversion (VC) systems enabling the generation of ultra-realistic audio deepfakes, there is growi…
Learning Disentangled Speech Representations with Contrastive Learning and Time-Invariant Retrieval
Yimin Deng, Huaizhen Tang, Xulong Zhang +3
Voice conversion refers to transferring speaker identity with well-preserved content. Better disentanglement of speech representations leads to better voice conversion. Recent stud…
CLN-VC: Text-Free Voice Conversion Based on Fine-Grained Style Control and Contrastive Learning with Negative Samples Augmentation
Yimin Deng, Xulong Zhang, Jianzong Wang +2
Better disentanglement of speech representation is essential to improve the quality of voice conversion. Recently contrastive learning is applied to voice conversion successfully b…
VoiceExtender: Short-utterance Text-independent Speaker Verification with Guided Diffusion Model
Yayun He, Zuheng Kang, Jianzong Wang +2
Speaker verification (SV) performance deteriorates as utterances become shorter. To this end, we propose a new architecture called VoiceExtender which provides a promising solution…
Contrastive Latent Space Reconstruction Learning for Audio-Text Retrieval
Kaiyi Luo, Xulong Zhang, Jianzong Wang +3
Cross-modal retrieval (CMR) has been extensively applied in various domains, such as multimedia search engines and recommendation systems. Most existing CMR methods focus on image-…
FastGraphTTS: An Ultrafast Syntax-Aware Speech Synthesis Framework
Jianzong Wang, Xulong Zhang, Aolan Sun +2
This paper integrates graph-to-sequence into an end-to-end text-to-speech framework for syntax-aware modelling with syntactic information of input text. Specifically, the input tex…
Voice Conversion with Denoising Diffusion Probabilistic GAN Models
Xulong Zhang, Jianzong Wang, Ning Cheng +1
Voice conversion is a method that allows for the transformation of speaking style while maintaining the integrity of linguistic information. There are many researchers using deep g…
Symbolic & Acoustic: Multi-domain Music Emotion Modeling for Instrumental Music
Kexin Zhu, Xulong Zhang, Jianzong Wang +2
Music Emotion Recognition involves the automatic identification of emotional elements within music tracks, and it has garnered significant attention due to its broad applicability…
PMVC: Data Augmentation-Based Prosody Modeling for Expressive Voice Conversion
Yimin Deng, Huaizhen Tang, Xulong Zhang +3
Voice conversion as the style transfer task applied to speech, refers to converting one person's speech into a new speech that sounds like another person's. Up to now, there has be…
EmoMix: Emotion Mixing via Diffusion Models for Emotional Speech Synthesis
Haobin Tang, Xulong Zhang, Jianzong Wang +2
There has been significant progress in emotional Text-To-Speech (TTS) synthesis technology in recent years. However, existing methods primarily focus on the synthesis of a limited…
SVVAD: Personal Voice Activity Detection for Speaker Verification
Zuheng Kang, Jianzong Wang, Junqing Peng +1
Voice activity detection (VAD) improves the performance of speaker verification (SV) by preserving speech segments and attenuating the effects of non-speech. However, this scheme i…
SAR: Self-Supervised Anti-Distortion Representation for End-To-End Speech Model
Jianzong Wang, Xulong Zhang, Haobin Tang +3
In recent Text-to-Speech (TTS) systems, a neural vocoder often generates speech samples by solely conditioning on acoustic features predicted from an acoustic model. However, there…
Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropy
Xulong Zhang, Haobin Tang, Jianzong Wang +3
Because of predicting all the target tokens in parallel, the non-autoregressive models greatly improve the decoding efficiency of speech recognition compared with traditional autor…
QI-TTS: Questioning Intonation Control for Emotional Speech Synthesis
Haobin Tang, Xulong Zhang, Jianzong Wang +2
Recent expressive text to speech (TTS) models focus on synthesizing emotional speech, but some fine-grained styles such as intonation are neglected. In this paper, we propose QI-TT…
Feature-Rich Audio Model Inversion for Data-Free Knowledge Distillation Towards General Sound Classification
Zuheng Kang, Yayun He, Jianzong Wang +3
Data-Free Knowledge Distillation (DFKD) has recently attracted growing attention in the academic community, especially with major breakthroughs in computer vision. Despite promisin…
Improving Music Genre Classification from Multi-Modal Properties of Music and Genre Correlations Perspective
Ganghui Ru, Xulong Zhang, Jianzong Wang +2
Music genre classification has been widely studied in past few years for its various applications in music information retrieval. Previous works tend to perform unsatisfactorily, s…
SVLDL: Improved Speaker Age Estimation Using Selective Variance Label Distribution Learning
Zuheng Kang, Jianzong Wang, Junqing Peng +1
Estimating age from a single speech is a classic and challenging topic. Although Label Distribution Learning (LDL) can represent adjacent indistinguishable ages well, the uncertain…