Picture for Shun-Po Chuang

Shun-Po Chuang

ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection

Add code
Aug 17, 2023
Viaarxiv icon

EURO: ESPnet Unsupervised ASR Open-source Toolkit

Add code
Dec 01, 2022
Viaarxiv icon

Anticipation-free Training for Simultaneous Translation

Add code
Jan 30, 2022
Figure 1 for Anticipation-free Training for Simultaneous Translation
Figure 2 for Anticipation-free Training for Simultaneous Translation
Figure 3 for Anticipation-free Training for Simultaneous Translation
Figure 4 for Anticipation-free Training for Simultaneous Translation
Viaarxiv icon

Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation

Add code
May 11, 2021
Figure 1 for Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation
Figure 2 for Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation
Figure 3 for Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation
Figure 4 for Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation
Viaarxiv icon

Non-autoregressive Mandarin-English Code-switching Speech Recognition with Pinyin Mask-CTC and Word Embedding Regularization

Add code
Apr 06, 2021
Figure 1 for Non-autoregressive Mandarin-English Code-switching Speech Recognition with Pinyin Mask-CTC and Word Embedding Regularization
Figure 2 for Non-autoregressive Mandarin-English Code-switching Speech Recognition with Pinyin Mask-CTC and Word Embedding Regularization
Figure 3 for Non-autoregressive Mandarin-English Code-switching Speech Recognition with Pinyin Mask-CTC and Word Embedding Regularization
Figure 4 for Non-autoregressive Mandarin-English Code-switching Speech Recognition with Pinyin Mask-CTC and Word Embedding Regularization
Viaarxiv icon

Self-supervised Pre-training Reduces Label Permutation Instability of Speech Separation

Add code
Oct 29, 2020
Figure 1 for Self-supervised Pre-training Reduces Label Permutation Instability of Speech Separation
Figure 2 for Self-supervised Pre-training Reduces Label Permutation Instability of Speech Separation
Figure 3 for Self-supervised Pre-training Reduces Label Permutation Instability of Speech Separation
Figure 4 for Self-supervised Pre-training Reduces Label Permutation Instability of Speech Separation
Viaarxiv icon

Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translation

Add code
May 21, 2020
Figure 1 for Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translation
Figure 2 for Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translation
Figure 3 for Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translation
Figure 4 for Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translation
Viaarxiv icon

Training a code-switching language model with monolingual data

Add code
Nov 14, 2019
Figure 1 for Training a code-switching language model with monolingual data
Figure 2 for Training a code-switching language model with monolingual data
Figure 3 for Training a code-switching language model with monolingual data
Figure 4 for Training a code-switching language model with monolingual data
Viaarxiv icon

Sequence-to-sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding

Add code
Oct 28, 2019
Figure 1 for Sequence-to-sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding
Figure 2 for Sequence-to-sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding
Figure 3 for Sequence-to-sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding
Viaarxiv icon

Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation

Add code
Nov 19, 2018
Figure 1 for Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation
Figure 2 for Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation
Figure 3 for Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation
Figure 4 for Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation
Viaarxiv icon