1 |
AlloVera: a multilingual allophone database
|
|
|
|
In: LREC 2020: 12th Language Resources and Evaluation Conference ; https://halshs.archives-ouvertes.fr/halshs-02527046 ; LREC 2020: 12th Language Resources and Evaluation Conference, European Language Resources Association, May 2020, Marseille, France ; https://lrec2020.lrec-conf.org/ (2020)
|
|
BASE
|
|
Show details
|
|
3 |
Towards Minimal Supervision BERT-based Grammar Error Correction ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
It's not a Non-Issue: Negation as a Source of Error in Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Automatic Extraction of Rules Governing Morphological Agreement ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
A Summary of the First Workshop on Language Technology for Language Documentation and Revitalization ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
It’s Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Universal Phone Recognition with a Multilingual Allophone System ...
|
|
Li, Xinjian; Dalmia, Siddharth; Li, Juncheng; Lee, Matthew; Littell, Patrick; Yao, Jiali; Anastasopoulos, Antonios; Mortensen, David R.; Neubig, Graham; Black, Alan W; Metze, Florian. - : arXiv, 2020
|
|
Abstract:
Multilingual models can improve language processing, particularly for low resource situations, by sharing parameters across languages. Multilingual acoustic models, however, generally ignore the difference between phonemes (sounds that can support lexical contrasts in a particular language) and their corresponding phones (the sounds that are actually spoken, which are language independent). This can lead to performance degradation when combining a variety of training languages, as identically annotated phonemes can actually correspond to several different underlying phonetic realizations. In this work, we propose a joint model of both language-independent phone and language-dependent phoneme distributions. In multilingual ASR experiments over 11 languages, we find that this model improves testing performance by 2% phoneme error rate absolute in low-resource conditions. Additionally, because we are explicitly modeling language-independent phones, we can build a (nearly-)universal phone recognizer that, when ... : ICASSP 2020 ...
|
|
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/2002.11800 https://dx.doi.org/10.48550/arxiv.2002.11800
|
|
BASE
|
|
Hide details
|
|
10 |
It’s Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information
|
|
|
|
In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2020)
|
|
BASE
|
|
Show details
|
|
11 |
X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
AlloVera: a multilingual allophone database
|
|
|
|
In: LREC 2020: 12th Language Resources and Evaluation Conference ; https://halshs.archives-ouvertes.fr/halshs-02527046 ; LREC 2020: 12th Language Resources and Evaluation Conference, European Language Resources Association, May 2020, Marseille, France ; https://lrec2020.lrec-conf.org/ (2020)
|
|
BASE
|
|
Show details
|
|
|
|