Search Results - "Mei-Yuh Hwang"

Domain Adversarial Training for Accented Speech Recognition by Sun, Sining, Yeh, Ching-Feng, Hwang, Mei-Yuh, Ostendorf, Mari, Xie, Lei

“…In this paper, we propose a domain adversarial training (DAT) algorithm to alleviate the accented speech recognition problem. In order to reduce the mismatch…”
Get full text

Adversarial Regularization for Attention Based End-to-End Robust Speech Recognition by Sun, Sining, Guo, Pengcheng, Xie, Lei, Hwang, Mei-Yuh

“…End-to-end speech recognition, such as attention based approaches, is an emerging and attractive topic in recent years. It has achieved comparable performance…”
Get full text

Contextual spoken language understanding using recurrent neural networks by Yangyang Shi, Kaisheng Yao, Hu Chen, Yi-Cheng Pan, Mei-Yuh Hwang, Baolin Peng

“…We present a contextual spoken language understanding (contextual SLU) method using Recurrent Neural Networks (RNNs). Previous work has shown that context…”
Get full text

Region Proposal Network Based Small-Footprint Keyword Spotting by Hou, Jingyong, Shi, Yangyang, Ostendorf, Mari, Hwang, Mei-Yuh, Xie, Lei

“…We apply an anchor-based region proposal network (RPN) for end-to-end keyword spotting (KWS). RPNs have been widely used for object detection in image and…”
Get full text

Recent innovations in speech-to-text transcription at SRI-ICSI-UW by Stolcke, A., Barry Chen, Franco, H., Venkata Ramana Rao Gadde, Graciarena, M., Mei-Yuh Hwang, Kirchhoff, K., Mandal, A., Morgan, N., Xin Lei, Ng, T., Ostendorf, M., Sonmez, K., Venkataraman, A., Vergyri, D., Wen Wang, Jing Zheng, Qifeng Zhu

“…We summarize recent progress in automatic speech-to-text transcription at SRI, ICSI, and the University of Washington. The work encompasses all components of…”
Get full text

Building A Highly Accurate Mandarin Speech Recognizer With Language-Independent Technologies and Language-Dependent Modules by Mei-Yuh Hwang, Gang Peng, Ostendorf, M., Wen Wang, Faria, A., Heidel, A.

“…We describe a system for highly accurate large-vocabulary Mandarin speech recognition. The prevailing hidden Markov model based technologies are essentially…”
Get full text

Mining Effective Negative Training Samples for Keyword Spotting by Hou, Jingyong, Shi, Yangyang, Ostendorf, Mari, Hwang, Mei-Yuh, Xie, Lei

“…Max-pooling neural network architectures have been proven to be useful for keyword spotting (KWS), but standard training methods suffer from a class-imbalance…”
Get full text

A factorization network based method for multi-lingual domain classification by Yangyang Shi, Yi-Cheng Pan, Mei-Yuh Hwang, Kaisheng Yao, Hu Chen, Yuanhang Zou, Baolin Peng

“…In many spoken language understanding systems (SLUS), domain classification is the most crucial component, as system responses based on wrong domains often…”
Get full text

Knowledge Distillation for Recurrent Neural Network Language Modeling with Trust Regularization by Shi, Yangyang, Hwang, Mei-Yuh, Lei, Xin, Sheng, Haoyu

“…Recurrent Neural Networks (RNNs) have dominated language modeling because of their superior performance over traditional N-gram based models. In many…”
Get full text

End-to-end Speech Recognition Using a High Rank LSTM-CTC Based Model by Shi, Yangyang, Hwang, Mei-Yuh, Lei, Xin

“…Long Short Term Memory Connectionist Temporal Classification (LSTM-CTC) based end-to-end models are widely used in speech recognition due to its simplicity in…”
Get full text

New methods and evaluation experiments on translating TED talks in the IWSLT benchmark by Axelrod, A., Xiaodong He, Li Deng, Acero, A., Mei-Yuh Hwang

“…The IWSLT benchmark task is an annual evaluation campaign on spoken language translation held by the International Workshop on Spoken Language Processing…”
Get full text

Combining Discriminative Feature, Transform, and Model Training for Large Vocabulary Speech Recognition by Jing Zheng, Cetin, O., Mei-Yuh Hwang, Xin Lei, Stolcke, A., Morgan, N.

“…Recent developments in large vocabulary continuous speech recognition (LVCSR) have shown the effectiveness of discriminative training approaches, employing the…”
Get full text

Semi-supervised slot tagging in spoken language understanding using recurrent transductive support vector machines by Yangyang Shi, Kaisheng Yao, Hu Chen, Yi-Cheng Pan, Mei-Yuh Hwang

“…In this paper, we propose a recurrent transductive support vector machine (rtsvm) for semi-supervised slot tagging. Taking advantage of the superior sequence…”
Get full text

Multiple fixed beamformers with a spacial Wiener-form postfilter for far-field speech recognition by Sun, Sining, Zhou, Shuran, Hwang, Mei-Yuh, Xie, Lei, Li, Qin, Lei, Xin

“…Far-field speech recognition is becoming a hot topic in research and industrial applications. In this paper, in order to improve far-field speech recognition…”
Get full text

Web-data augmented language models for Mandarin conversational speech recognition by Ng, T., Ostendorf, M., Mei-Yuh Hwang, Manhung Siu, Bulyko, I., Xin Lei

“…Lack of data is a problem in training language models for conversational speech recognition, particularly for languages other than English. Experiments in…”
Get full text

A Robust Nonlinear Microphone Array Postfilter for Noise Reduction by Bu, Suliang, Zhao, Yunxin, Hwang, Mei-Yuh, Sun, Sining

“…We propose a robust nonlinear microphone array postfilter for noise reduction. This postfilter is formulated as a function of noise power ratio before and…”
Get full text

Shared-distribution hidden Markov models for speech recognition by Hwang, Mei-Yuh, Huang, Xuedong

“…A shared-distribution hidden Markov model (HMM) is presented for speaker-independent continuous speech recognition. The output distributions across different…”
Get full text

Generating a task-adapted acoustic model from one or more different corpora by Hwang, Mei Yuh

Get full text

Predicting unseen triphones with senones by Mei-Yuh Hwang, Xuedong Huang, Alleva, F.A.

“…In large-vocabulary speech recognition, we often encounter triphones that are not covered in the training data. These unseen triphones are usually backed off…”
Get full text

Generating a task-adapted acoustic model from one or more supervised and/or unsupervised corpora by Hwang, Mei Yuh

Get full text