Audio

CLN-VC: Text-Free Voice Conversion Based on Fine-Grained Style Control and Contrastive Learning with Negative Samples Augmentation
Better disentanglement of speech representation is essential to improve the quality of voice conversion. Recently contrastive learning …
Cite arXiv IEEE
CLN-VC: Text-Free Voice Conversion Based on Fine-Grained Style Control and Contrastive Learning with Negative Samples Augmentation
CP-EB: Talking Face Generation with Controllable Pose and Eye Blinking Embedding
This paper proposes a talking face generation method named “CP-EB” that takes an audio signal as input and a person image as reference, …
Cite arXiv IEEE
CP-EB: Talking Face Generation with Controllable Pose and Eye Blinking Embedding
DQR-TTS: Semi-supervised Text-to-speech Synthesis with Dynamic Quantized Representation
Most existing neural-based text-to-speech methods rely on extensive datasets and face challenges under low-resource condition. In this …
Cite arXiv IEEE
DQR-TTS: Semi-supervised Text-to-speech Synthesis with Dynamic Quantized Representation
VoiceExtender: Short-utterance Text-independent Speaker Verification with Guided Diffusion Model
Speaker Verification (SV) performance gets worse as utterances get shorter. To this end, we propose a new architecture called …
Cite arXiv IEEE
VoiceExtender: Short-utterance Text-independent Speaker Verification with Guided Diffusion Model
FastGraphTTS: An Ultrafast Syntax-Aware Speech Synthesis Framework
This paper integrates graph-to-sequence into an end-to-end text-to-speech framework for syntax-aware modelling with syntactic …
Cite arXiv IEEE DEMO
FastGraphTTS: An Ultrafast Syntax-Aware Speech Synthesis Framework
DiffTalker: Co-driven audio-image diffusion for talking faces via intermediate landmarks
Generating realistic talking faces is a complex and widely discussed task with numerous applications. In this paper, we present …
Cite Code arXiv
DiffTalker: Co-driven audio-image diffusion for talking faces via intermediate landmarks
Symbolic and Acoustic: Multi-domain Music Emotion Modeling for Instrumental Music
Music Emotion Recognition involves the automatic identification of emotional elements within music tracks, and it has garnered …
Cite arXiv Springer
Symbolic and Acoustic: Multi-domain Music Emotion Modeling for Instrumental Music
Voice Conversion with Denoising Diffusion Probabilistic GAN Models
Voice conversion is a method that allows for the transformation of speaking style while maintaining the integrity of linguistic …
Cite arXiv Springer
Voice Conversion with Denoising Diffusion Probabilistic GAN Models
Boosting Chinese ASR Error Correction with Dynamic Error Scaling Mechanism
Chinese Automatic Speech Recognition (ASR) error correction presents significant challenges due to the Chinese language’s unique …
PDF Cite arXiv ISCA
Boosting Chinese ASR Error Correction with Dynamic Error Scaling Mechanism
EmoMix: Emotion Mixing via Diffusion Models for Emotional Speech Synthesis
There has been significant progress in emotional Text-To-Speech (TTS) synthesis technology in recent years. However, existing methods …
PDF Cite arXiv ISCA DEMO
EmoMix: Emotion Mixing via Diffusion Models for Emotional Speech Synthesis