10 papers
DisSR: Disentangling Speech Representation for Degradation-Prior Guided Cross-Domain Speech Restoration
Ziqi Liang, Zhijun Jia, Chang Liu +3
Previous speech restoration (SR) primarily focuses on single-task speech restoration (SSR), which cannot address general speech restoration problems. Training specific SSR models f…
CycleFlow: Leveraging Cycle Consistency in Flow Matching for Speaker Style Adaptation
Ziqi Liang, Xulong Zhang, Chang Liu +3
Voice Conversion (VC) aims to convert the style of a source speaker, such as timbre and pitch, to the style of any target speaker while preserving the linguistic content. However,…
AlignCap: Aligning Speech Emotion Captioning to Human Preferences
Ziqi Liang, Haoxiang Shi, Hanhui Chen
Speech Emotion Captioning (SEC) has gradually become an active research task. The emotional content conveyed through human speech are often complex, and classifying them into fixed…
Emotional Cues Extraction and Fusion for Multi-modal Emotion Prediction and Recognition in Conversation
Haoxiang Shi, Ziqi Liang, Jun Yu
Emotion Prediction in Conversation (EPC) aims to forecast the emotions of forthcoming utterances by utilizing preceding dialogues. Previous EPC approaches relied on simple context…
QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering
Sheng Ouyang, Jianzong Wang, Yong Zhang +5
Extractive Question Answering (EQA) in Machine Reading Comprehension (MRC) often faces the challenge of dealing with semantically identical but format-variant inputs. Our work intr…
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…
EM-TTS: Efficiently Trained Low-Resource Mongolian Lightweight Text-to-Speech
Ziqi Liang, Haoxiang Shi, Jiawei Wang +1
Recently, deep learning-based Text-to-Speech (TTS) systems have achieved high-quality speech synthesis results. Recurrent neural networks have become a standard modeling technique…
CP-EB: Talking Face Generation with Controllable Pose and Eye Blinking Embedding
Jianzong Wang, Yimin Deng, Ziqi Liang +3
This paper proposes a talking face generation method named "CP-EB" that takes an audio signal as input and a person image as reference, to synthesize a photo-realistic people talki…
Efficiently Trained Low-Resource Mongolian Text-to-Speech System Based On FullConv-TTS
Ziqi Liang
Recurrent Neural Networks (RNNs) have become the standard modeling technique for sequence data, and are used in a number of novel text-to-speech models. However, training a TTS mod…