1 |
Segmentation en mots faiblement supervisée pour la documentation automatique des langues
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03477475 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
2 |
Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads? ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Lightweight Adapter Tuning for Multilingual Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Multilingual Unsupervised Neural Machine Translation with Denoising Adapters ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settings ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis
|
|
|
|
In: ComputEL-4: Fourth Workshop on the Use of Computational Methods in the Study of Endangered Languages ; https://halshs.archives-ouvertes.fr/halshs-03030529 ; 2020 ; https://computel-workshop.org/ (2020)
|
|
BASE
|
|
Show details
|
|
7 |
A Data Efficient End-To-End Spoken Language Understanding Architecture ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Catplayinginthesnow: Impact of Prior Segmentation on a Model of Visually Grounded Speech ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Investigating Language Impact in Bilingual Approaches for Computational Language Documentation ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Controlling Utterance Length in NMT-based Word Segmentation with Attention ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
MaSS - Multilingual corpus of Sentence-aligned Spoken utterances ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
MaSS - Multilingual corpus of Sentence-aligned Spoken utterances ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
How Does Language Influence Documentation Workflow? Unsupervised Word Discovery Using Translations in Multiple Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Word Recognition, Competition, and Activation in a Model of Visually Grounded Speech ...
|
|
|
|
Abstract:
In this paper, we study how word-like units are represented and activated in a recurrent neural model of visually grounded speech. The model used in our experiments is trained to project an image and its spoken description in a common representation space. We show that a recurrent model trained on spoken sentences implicitly segments its input into word-like units and reliably maps them to their correct visual referents. We introduce a methodology originating from linguistics to analyse the representation learned by neural networks -- the gating paradigm -- and show that the correct representation of a word is only activated if the network has access to first phoneme of the target word, suggesting that the network does not rely on a global acoustic pattern. Furthermore, we find out that not all speech frames (MFCC vectors in our case) play an equal role in the final encoded representation of a given word, but that some frames have a crucial effect on it. Finally, we suggest that word representation could be ... : Accepted at CoNLL2019 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://dx.doi.org/10.48550/arxiv.1909.08491 https://arxiv.org/abs/1909.08491
|
|
BASE
|
|
Hide details
|
|
15 |
Models of Visually Grounded Speech Signal Pay Attention To Nouns: a Bilingual Experiment on English and Japanese ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the "Speaking Rosetta" JSALT 2017 Workshop ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Unsupervised Word Segmentation from Speech with Attention ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|