1 |
When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation? ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Application of Quantum Density Matrix in Classical Question Answering and Classical Image Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Compilable Neural Code Generation with Compiler Feedback ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
RMBR: A Regularized Minimum Bayes Risk Reranking Framework for Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
SimpleBERT: A Pre-trained Model That Learns to Generate Simple Words ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Sound Source Separation Mechanisms of Different Deep Networks Explained from the Perspective of Auditory Perception
|
|
|
|
In: Applied Sciences; Volume 12; Issue 2; Pages: 832 (2022)
|
|
Abstract:
Thanks to the development of deep learning, various sound source separation networks have been proposed and made significant progress. However, the study on the underlying separation mechanisms is still in its infancy. In this study, deep networks are explained from the perspective of auditory perception mechanisms. For separating two arbitrary sound sources from monaural recordings, three different networks with different parameters are trained and achieve excellent performances. The networks’ output can obtain an average scale-invariant signal-to-distortion ratio improvement (SI-SDRi) higher than 10 dB, comparable with the human performance to separate natural sources. More importantly, the most intuitive principle—proximity—is explored through simultaneous and sequential organization experiments. Results show that regardless of network structures and parameters, the proximity principle is learned spontaneously by all networks. If components are proximate in frequency or time, they are not easily separated by networks. Moreover, the frequency resolution at low frequencies is better than at high frequencies. These behavior characteristics of all three networks are highly consistent with those of the human auditory system, which implies that the learned proximity principle is not accidental, but the optimal strategy selected by networks and humans when facing the same task. The emergence of the auditory-like separation mechanisms provides the possibility to develop a universal system that can be adapted to all sources and scenes.
|
|
Keyword:
proximity principle; separation mechanisms; sound source separation
|
|
URL: https://doi.org/10.3390/app12020832
|
|
BASE
|
|
Hide details
|
|
8 |
A comparison of high-flow nasal cannula and standard facemask as pre-oxygenation technique for general anesthesia: A PRISMA-compliant systemic review and meta-analysis
|
|
|
|
In: Medicine (Baltimore) (2022)
|
|
BASE
|
|
Show details
|
|
9 |
Economic Evaluation of Dapagliflozin in the Treatment of Patients With Heart Failure: A Systematic Review
|
|
|
|
In: Front Pharmacol (2022)
|
|
BASE
|
|
Show details
|
|
10 |
Resilience, smartphone use and language among urban refugees in the Global south
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Intensive phototherapy vs. exchange transfusion for the treatment of neonatal hyperbilirubinemia: a multicenter retrospective cohort study
|
|
|
|
In: Chin Med J (Engl) (2022)
|
|
BASE
|
|
Show details
|
|
12 |
Three essays on entrepreneurial resource acquisition through crowdfunding
|
|
|
|
BASE
|
|
Show details
|
|
13 |
The Effect of Word Frequency and Position-in-Utterance in Mandarin Speech Errors: A Connectionist Model of Speech Production
|
|
|
|
In: Chinese Lexical Semantics ; https://hal.archives-ouvertes.fr/hal-03435818 ; Meichun Liu, Chunyu Kit, Qi Su. Chinese Lexical Semantics, 12278, Springer International Publishing, pp.491-500, 2021, Lecture Notes in Computer Science, ⟨10.1007/978-3-030-81197-6_42⟩ (2021)
|
|
BASE
|
|
Show details
|
|
14 |
A corpus study of lexical speech errors in Mandarin
|
|
|
|
In: ISSN: 1994-2559 ; Taiwan Journal of Linguistics ; https://hal.archives-ouvertes.fr/hal-03435803 ; Taiwan Journal of Linguistics, Crane Publishing, 2021, 19 (2), pp.87-120. ⟨10.6519/TJL.202107_19(2).0003⟩ (2021)
|
|
BASE
|
|
Show details
|
|
15 |
A Multimodal Approach to the Discursive Construction of Stances in Political Debates in Hong Kong
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Data for: Improving English Language Arts Instruction in Indiana Dual Language Bilingual Education Classrooms ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Data for: Improving English Language Arts Instruction in Indiana Dual Language Bilingual Education Classrooms ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Making Better Use of Bilingual Information for Cross-Lingual AMR Parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
偏鄉小校以繪本進行英語線上教學之個案研究 ; A Case Study of Online English Teaching in Rural Schools Using Picture Books
|
|
|
|
BASE
|
|
Show details
|
|
20 |
台灣大學生對多媒體英文學習看法與學習成效之研究 ; A Research of Taiwanese College Students' Perceptions toward Using Multimedia in English Learning and Its Efficacy
|
|
|
|
BASE
|
|
Show details
|
|
|
|