7 papers
DiffStyleTTS: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles
Jiaxuan Liu, Zhaoci Liu, Yajun Hu +3
Human speech exhibits rich and flexible prosodic variations. To address the one-to-many mapping problem from text to prosody in a reasonable and flexible manner, we propose DiffSty…
VoxBlink2: A 100K+ Speaker Recognition Corpus and the Open-Set Speaker-Identification Benchmark
Yuke Lin, Ming Cheng, Fulin Zhang +3
In this paper, we provide a large audio-visual speaker recognition dataset, VoxBlink2, which includes approximately 10M utterances with videos from 110K+ speakers in the wild. This…
Exploring Energy-Based Models for Out-of-Distribution Detection in Dialect Identification
Yaqian Hao, Chenguang Hu, Yingying Gao +2
The diverse nature of dialects presents challenges for models trained on specific linguistic patterns, rendering them susceptible to errors when confronted with unseen or out-of-di…
GenDistiller: Distilling Pre-trained Language Models based on an Autoregressive Generative Model
Yingying Gao, Shilei Zhang, Chao Deng +1
Pre-trained speech language models such as HuBERT and WavLM leverage unlabeled speech data for self-supervised learning and offer powerful representations for numerous downstream t…
Plugin Speech Enhancement: A Universal Speech Enhancement Framework Inspired by Dynamic Neural Network
Yanan Chen, Zihao Cui, Yingying Gao +3
The expectation to deploy a universal neural network for speech enhancement, with the aim of improving noise robustness across diverse speech processing tasks, faces challenges due…
Cascaded Multi-task Adaptive Learning Based on Neural Architecture Search
Yingying Gao, Shilei Zhang, Zihao Cui +2
Cascading multiple pre-trained models is an effective way to compose an end-to-end system. However, fine-tuning the full cascaded model is parameter and memory inefficient and our…