1 |
以《Cofacts 真的假的》資料庫為基礎建立中文科學假訊息之探勘模型 ; Text Mining Model for Detecting Chinese Fake Scientific Messages based on Cofacts Open Data
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition ...
|
|
|
|
Abstract:
End-to-end models have achieved impressive results on the task of automatic speech recognition (ASR). For low-resource ASR tasks, however, labeled data can hardly satisfy the demand of end-to-end models. Self-supervised acoustic pre-training has already shown its amazing ASR performance, while the transcription is still inadequate for language modeling in end-to-end models. In this work, we fuse a pre-trained acoustic encoder (wav2vec2.0) and a pre-trained linguistic encoder (BERT) into an end-to-end ASR model. The fused model only needs to learn the transfer from speech to language during fine-tuning on limited labeled data. The length of the two modalities is matched by a monotonic attention mechanism without additional parameters. Besides, a fully connected layer is introduced for the hidden mapping between modalities. We further propose a scheduled fine-tuning strategy to preserve and utilize the text context modeling ability of the pre-trained linguistic encoder. Experiments show our effective utilizing ...
|
|
Keyword:
Audio and Speech Processing eess.AS; Computation and Language cs.CL; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Sound cs.SD
|
|
URL: https://arxiv.org/abs/2101.06699 https://dx.doi.org/10.48550/arxiv.2101.06699
|
|
BASE
|
|
Hide details
|
|
4 |
Unsupervised pre-training for sequence to sequence speech recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Unsupervised Neural Machine Translation with Weight Sharing ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Multilingual End-to-End Speech Recognition with A Single Transformer on Low-Resource Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Anticipatory Posturing of the Vocal Tract Reveals Dissociation of Speech Movement Plans from Linguistic Units
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Statistical Approach to ChineseEnglish Spoken-language Translation
|
|
|
|
In: http://www.colips.org/conference/iscslp2006/anthology/2000/paper/PsB2/057.pdf (2000)
|
|
BASE
|
|
Show details
|
|
19 |
RULE-BASED POST-PROCESSING OF PINYIN TO1 CHINESE CHARACTERS CONVERSION SYSTEM
|
|
|
|
In: http://www.colips.org/conference/iscslp2006/anthology/2000/paper/PSB2/106.pdf
|
|
BASE
|
|
Show details
|
|
20 |
ClassTriphone Acoustic Modeling Based On Decision Tree
|
|
|
|
In: http://www.colips.org/conference/iscslp2006/anthology/1998/papers/asr-a1.pdf
|
|
BASE
|
|
Show details
|
|
|
|