26 |
Lab meeting
2022-11-03
|
BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model
(pdf)
|
25 |
Lab meeting
2022-09-15
|
Knowledge Transfer and Distillation from Autoregressive to Non-Autoregressive Speech Recognition
(pdf)
|
24 |
Lab meeting
2022-08-09
|
Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition
(pdf)
|
23 |
Lab meeting
2022-06-10
|
PERT: Pre-training BERT with Permuted Language Model
(pdf)
|
22 |
Lab meeting
2022-05-20
|
Non-autoregressive Transformer with Unified Bidirectional Decoder for Automatic Speech Recognition
(pdf)
|
21 |
Lab meeting
2022-04-26
|
Contextual Representation Learning beyond Masked Language Modeling
(pdf)
|
20 |
Lab meeting
2022-04-08
|
UNDERSTANDING THE ROLE OF SELF ATTENTION FOR EFFICIENT SPEECH RECOGNITION
(pdf)
|
19 |
Lab meeting
2022-03-11
|
Improving CTC-based speech recognition via knowledge transferring from pre-trained language models
(pdf)
|
18 |
Lab meeting
2022-02-18
|
Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models
(pdf)
|
17 |
Lab meeting
2022-01-10
|
Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units
(pdf)
|
16 |
Lab meeting
2021-12-23
|
Improving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Model
(pdf)
|
15 |
Lab meeting
2021-11-11
|
Optimizing Alignment of Speech and Language Latent Spaces for End-to-End Speech Recognition and Understanding
(pdf)
|
14 |
Lab meeting
2021-10-18
|
LoRA: Low-Rank Adaptation ofLarge Language Models
(pdf)
|
13 |
Lab meeting
2021-09-30
|
Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition
(pdf)
|
12 |
Lab meeting
2021-08-30
|
W2V-BERT: COMBINING CONTRASTIVE LEARNING AND MASKED LANGUAGE MODELING FOR SELF-SUPERVISED SPEECH PRE-TRAINING
(pdf)
|
11 |
Lab meeting
2021-08-09
|
Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
(pdf)
|
10 |
Lab meeting
2021-07-22
|
E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning
(pdf)
|
9 |
Lab meeting
2021-07-01
|
You Only Learn One Representation: Unified Network for Multiple Tasks
(pdf)
|
8 |
Lab meeting
2021-06-03
|
FNet: Mixing Tokens with Fourier Transforms
(pdf)
|
7 |
Lab meeting
2021-05-06
|
SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels
(pdf)
|
6 |
Course Presentation
2021-05-05
|
Facebook Hate Speech Detection(Interim Presentation)
|
5 |
Lab meeting
2021-03-25
|
Transformer is All You Need: Multimodal Multitask Learning with a Unified Transformer
(pdf)
|
4 |
Sinica meeting
2021-03-16
|
VinVL: Making Visual Representations Matter in Vision-Language Models
(pdf)
|
3 |
Sinica meeting
2021-02-02
|
Speech-Based Visual Question Answering
(pdf)
|
2 |
Lab meeting
2021-01-26
|
Speech-Based Visual Question Answering
(pdf)
|
1 |
Course Presentation
2021-01-15
|
Speech and BERT
(pdf)
|