papers

Publications (8)

cs.CL2021

BERT's output layer recognizes all hidden layers? Some Intriguing Phenomena and a simple way to boost BERT

Wei-Tsung Kao, Tsung-Han Wu, Po-Han Chi +2

Although Bidirectional Encoder Representations from Transformers (BERT) have achieved tremendous success in many natural language processing (NLP) tasks, it remains a black box. A…

eess.AS2020

Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders

Andy T. Liu, Shu-wen Yang, Po-Han Chi +2

We present Mockingjay as a new speech representation learning approach, where bidirectional Transformer encoders are pre-trained on a large amount of unlabeled speech. Previous spe…

cs.CL2021

SUPERB: Speech processing Universal PERformance Benchmark

Shu-wen Yang, Po-Han Chi, Yung-Sung Chuang +17

Self-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on large…

eess.AS2021

Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation

Po-Han Chi, Pei-Hung Chung, Tsung-Han Wu +4

For self-supervised speech processing, it is crucial to use pretrained models as speech representation extractors. In recent works, increasing the size of the model has been utiliz…

q-bio.QM2021

Leveraging Sequence Embedding and Convolutional Neural Network for Protein Function Prediction

Wei-Cheng Tseng, Po-Han Chi, Jia-Hua Wu +1

The capability of accurate prediction of protein functions and properties is essential in the biotechnology industry, e.g. drug development and artificial protein synthesis, etc. T…

eess.AS2020

Input-independent Attention Weights Are Expressive Enough: A Study of Attention in Self-supervised Audio Transformers

Tsung-Han Wu, Chun-Chen Hsieh, Yen-Hao Chen +2

In this paper, we seek solutions for reducing the computation complexity of transformer-based models for speech representation learning. We evaluate 10 attention algorithms; then,…

eess.AS2024

A Large-Scale Evaluation of Speech Foundation Models

Shu-wen Yang, Heng-Jui Chang, Zili Huang +18

The foundation model paradigm leverages a shared foundation model to achieve state-of-the-art (SOTA) performance for various tasks, requiring minimal downstream-specific modeling a…

cs.CL2021

SpeechNet: A Universal Modularized Model for Speech Processing Tasks

Yi-Chen Chen, Po-Han Chi, Shu-wen Yang +7

There is a wide variety of speech processing tasks ranging from extracting content information from speech signals to generating speech signals. For different tasks, model networks…