371 citations · 2.1k across the 193 of their papers we have counts for
22 papers · 1 filter
Adversarial Learning of Label Dependency: A Novel Framework for Multi-class Classification
Che-Ping Tsai, Hung-Yi Lee
Recent work has shown that exploiting relations between labels improves the performance of multi-label classification. We propose a novel framework based on generative adversarial…
Improved Audio Embeddings by Adjacency-Based Clustering with Applications in Spoken Term Detection
Sung-Feng Huang, Yi-Chen Chen, Hung-yi Lee +1
Embedding audio signal segments into vectors with fixed dimensionality is attractive because all following processing will be easier and more efficient, for example modeling, class…
Adversarial Training of End-to-end Speech Recognition Using a Criticizing Language Model
Alexander H. Liu, Hung-yi Lee, Lin-shan Lee
In this paper we proposed a novel Adversarial Training (AT) approach for end-to-end speech recognition using a Criticizing Language Model (CLM). In this way the CLM and the automat…
Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation
Ching-Ting Chang, Shun-Po Chuang, Hung-Yi Lee
Code-switching is about dealing with alternative languages in speech or text. It is partially speaker-depend and domain-related, so completely explaining the phenomenon by linguist…
Almost-unsupervised Speech Recognition with Close-to-zero Resource Based on Phonetic Structures Learned from Very Small Unpaired Speech and Text Data
Yi-Chen Chen, Chia-Hao Shen, Sung-Feng Huang +2
Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we…
Learning to Encode Text as Human-Readable Summaries using Generative Adversarial Networks
Yau-Shian Wang, Hung-Yi Lee
Auto-encoders compress input data into a latent-space representation and reconstruct the original data from the representation. This latent representation is not easily interpreted…
Generative Adversarial Networks for Unpaired Voice Transformation on Impaired Speech
Li-Wei Chen, Hung-Yi Lee, Yu Tsao
This paper focuses on using voice conversion (VC) to improve the speech intelligibility of surgical patients who have had parts of their articulators removed. Due to the difficulty…
Temporal Pattern Attention for Multivariate Time Series Forecasting
Shun-Yao Shih, Fan-Keng Sun, Hung-yi Lee
Forecasting multivariate time series data, such as prediction of electricity consumption, solar power production, and polyphonic piano pieces, has numerous valuable applications. H…
Proximal Policy Optimization and its Dynamic Version for Sequence Generation
Yi-Lin Tuan, Jinzhi Zhang, Yujia Li +1
In sequence generation task, many works use policy gradient for model optimization to tackle the intractable backpropagation issue when maximizing the non-differentiable evaluation…
Towards Audio to Scene Image Synthesis using Generative Adversarial Network
Chia-Hung Wan, Shun-Po Chuang, Hung-Yi Lee
Humans can imagine a scene from a sound. We want machines to do so by using conditional generative adversarial networks (GANs). By applying the techniques including spectral norm,…
Rhythm-Flexible Voice Conversion without Parallel Data Using Cycle-GAN over Phoneme Posteriorgram Sequences
Cheng-chieh Yeh, Po-chun Hsu, Ju-chieh Chou +2
Speaking rate refers to the average number of phonemes within some unit time, while the rhythmic patterns refer to duration distributions for realizations of different phonemes wit…
ODSQA: Open-domain Spoken Question Answering Dataset
Chia-Hsuan Lee, Shang-Ming Wang, Huan-Cheng Chang +1
Reading comprehension by machine has been widely studied, but machine comprehension of spoken content is still a less investigated problem. In this paper, we release Open-Domain Sp…
Segmental Audio Word2Vec: Representing Utterances as Sequences of Vectors with Applications in Spoken Term Detection
Yu-Hsuan Wang, Hung-yi Lee, Lin-shan Lee
While Word2Vec represents words (in text) as vectors carrying semantic information, audio Word2Vec was shown to be able to represent signal segments of spoken words as vectors carr…
Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation
Yi-Lin Tuan, Hung-Yi Lee
Sequence generative adversarial networks (SeqGAN) have been used to improve conditional sequence generation tasks, for example, chit-chat dialogue generation. To stabilize the trai…
Phonetic-and-Semantic Embedding of Spoken Words with Applications in Spoken Content Retrieval
Yi-Chen Chen, Sung-Feng Huang, Chia-Hao Shen +2
Word embedding or Word2Vec has been successful in offering semantics for text words learned from the context of words. Audio Word2Vec was shown to offer phonetic structures for spo…
Noise Adaptive Speech Enhancement using Domain Adversarial Training
Chien-Feng Liao, Yu Tsao, Hung-Yi Lee +1
In this study, we propose a novel noise adaptive speech enhancement (SE) system, which employs a domain adversarial training (DAT) approach to tackle the issue of a noise type mism…
Scalable Sentiment for Sequence-to-sequence Chatbot Response with Performance Analysis
Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu +3
Conventional seq2seq chatbot models only try to find the sentences with the highest probabilities conditioned on the input sequences, without considering the sentiment of the outpu…
Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations
Ju-chieh Chou, Cheng-chieh Yeh, Hung-yi Lee +1
Recently, cycle-consistent adversarial network (Cycle-GAN) has been successfully applied to voice conversion to a different speaker without parallel data, although in those approac…
Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension
Chia-Hsuan Li, Szu-Lin Wu, Chi-Liang Liu +1
Reading comprehension has been widely studied. One of the most representative reading comprehension tasks is Stanford Question Answering Dataset (SQuAD), on which machine is alread…
Joint Learning of Interactive Spoken Content Retrieval and Trainable User Simulator
Pei-Hung Chung, Kuan Tung, Ching-Lun Tai +1
User-machine interaction is crucial for information retrieval, especially for spoken content retrieval, because spoken content is difficult to browse, and speech recognition has a…
Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings
Da-Rong Liu, Kuan-Yu Chen, Hung-Yi Lee +1
Unsupervised discovery of acoustic tokens from audio corpora without annotation and learning vector representations for these tokens have been widely studied. Although these techni…
Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only
Yi-Chen Chen, Chia-Hao Shen, Sung-Feng Huang +1
Automatic speech recognition (ASR) has been widely researched with supervised approaches, while many low-resourced languages lack audio-text aligned data, and supervised methods ca…