DE eng

Search in the Catalogues and Directories

Hits 1 – 19 of 19

1
Speech Segmentation Optimization using Segmented Bilingual Speech Corpus for End-to-end Speech Translation ...
BASE
Show details
2
Representing `how you say' with `what you say': English corpus of focused speech and text reflecting corresponding implications ...
Suzuki, Naoaki; Nakamura, Satoshi. - : arXiv, 2022
BASE
Show details
3
Applying Syntax$\unicode{x2013}$Prosody Mapping Hypothesis and Prosodic Well-Formedness Constraints to Neural Sequence-to-Sequence Speech Synthesis ...
BASE
Show details
4
Using Perturbed Length-aware Positional Encoding for Non-autoregressive Neural Machine Translation ...
BASE
Show details
5
Using Perturbed Length-aware Positional Encoding for Non-autoregressive Neural Machine Translation ...
BASE
Show details
6
Simultaneous Neural Machine Translation with Constituent Label Prediction ...
BASE
Show details
7
Transformer VQ-VAE for Unsupervised Unit Discovery and Speech Synthesis: ZeroSpeech 2020 Challenge ...
BASE
Show details
8
Speech-to-speech Translation between Untranscribed Unknown Languages ...
BASE
Show details
9
Towards Machine Speech-to-speech Translation
BASE
Show details
10
Multi-Source Neural Machine Translation with Missing Data ...
BASE
Show details
11
Local Monotonic Attention Mechanism for End-to-End Speech and Language Processing ...
Abstract: Recently, encoder-decoder neural networks have shown impressive performance on many sequence-related tasks. The architecture commonly uses an attentional mechanism which allows the model to learn alignments between the source and the target sequence. Most attentional mechanisms used today is based on a global attention property which requires a computation of a weighted summarization of the whole input sequence generated by encoder states. However, it is computationally expensive and often produces misalignment on the longer input sequence. Furthermore, it does not fit with monotonous or left-to-right nature in several tasks, such as automatic speech recognition (ASR), grapheme-to-phoneme (G2P), etc. In this paper, we propose a novel attention mechanism that has local and monotonic properties. Various ways to control those properties are also explored. Experimental results on ASR, G2P and machine translation between two languages with similar sentence structures, demonstrate that the proposed encoder-decoder ... : Accepted at IJCNLP 2017 --- (V2: added more experiments on G2P & MT) ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences
URL: https://dx.doi.org/10.48550/arxiv.1705.08091
https://arxiv.org/abs/1705.08091
BASE
Hide details
12
Listening while Speaking: Speech Chain by Deep Learning ...
BASE
Show details
13
Incorporating Discrete Translation Lexicons into Neural Machine Translation ...
BASE
Show details
14
Context Awareness and Priority Control for ITS based on Automatic Speech Recognition
In: International conference on ITS Telecommunications ; https://hal.inria.fr/hal-01225312 ; International conference on ITS Telecommunications, Dec 2015, Copenhagen, Denmark ; http://www.itst-conf.org/ (2015)
BASE
Show details
15
Neural Reranking Improves Subjective Quality of Machine Translation: NAIST at WAT2015 ...
BASE
Show details
16
Spoken Dialogue Systems for Ambient Environments : Second International Workshop, IWSDS 2010, Gotemba, Shizuoka, Japan, October 1-2, 2010. Proceedings
Lee, Gary Geunbae; Mariani, Joseph; Minker, Wolfgang. - Berlin, Heidelberg : Springer Berlin Heidelberg, 2010
UB Frankfurt Linguistik
Show details
17
Validation of a training method for L2 continuous-speech segmentation
Cutler, Anne (R12329); Shanley, Janise. - : Japan, ISCA, 2010
BASE
Show details
18
Cultural communication idiosyncrasies in human-computer interaction
Miehle, Juliana; Ultes, Stefan; Minker, Wolfgang. - : ACL (Association for Computational Linguistics)
BASE
Show details
19ALAGIN - Advanced LAnGuage INformation Forum
http://www.alagin.jp/
Topic: Computational linguistics; Corpus linguistics; Pragmalinguistics / Communication research; ...
Language: Chinese, Mandarin; English; Japanese
Source type: Corpora; Linguistic associations; Software / Tools
Access: free access

Catalogues
1
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
1
0
0
0
Open access documents
17
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern