activity
20102023
most citedDeep Long Audio Inpainting

23 citations · 235 across the 69 of their papers we have counts for

collaborators
Showing eess.ASShow all

22 papers · 1 filter

eess.AS2023

SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts

Haibin Wu, Kai-Wei Chang, Yuan-Kuei Wu +1

Large language models (LLMs) have gained considerable attention for Artificial Intelligence Generated Content (AIGC), particularly with the emergence of ChatGPT. However, the direc…

eess.AS2023

MiniSUPERB: Lightweight Benchmark for Self-supervised Speech Models

Yu-Hsiang Wang, Huang-Yu Chen, Kai-Wei Chang +2

SUPERB was proposed to evaluate the generalizability of self-supervised learning (SSL) speech models across various tasks. However, it incurs high computational costs due to the la…

eess.AS2022

Partially Fake Audio Detection by Self-attention-based Fake Span Discovery

Haibin Wu, Heng-Cheng Kuo, Naijun Zheng +5

The past few years have witnessed the significant advances of speech synthesis and voice conversion technologies. However, such technologies can undermine the robustness of broadly…

eess.AS20215 cited

Speech Representation Learning Through Self-supervised Pretraining And Multi-task Finetuning

Yi-Chen Chen, Shu-wen Yang, Cheng-Kuang Lee +2

Speech representation learning plays a vital role in speech processing. Among them, self-supervised learning (SSL) has become an important research direction. It has been shown tha…

eess.AS2021

Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech

Chung-Ming Chien, Jheng-Hao Lin, Chien-yu Huang +2

The few-shot multi-speaker multi-style voice cloning task is to synthesize utterances with voice and speaking style similar to a reference speaker given only a few reference sample…

eess.AS2021

Utilizing Self-supervised Representations for MOS Prediction

Wei-Cheng Tseng, Chien-yu Huang, Wei-Tsung Kao +2

Speech quality assessment has been a critical issue in speech processing for decades. Existing automatic evaluations usually require clean references or parallel ground truth data,…