DE eng

Search in the Catalogues and Directories

Page: 1 2 3
Hits 1 – 20 of 55

1
Findings of the IWSLT 2020 Evaluation campaign
Niehues, Jan; Federico, Marcello; Ma, Xutai. - : Association for Computational Linguistics, 2022
BASE
Show details
2
KIT Lecture Translator: Multilingual Speech Translation with One-Shot Learning
Nguyen, Thai-Son; Zenkel, Thomas; Waibel, Alex. - : Association for Computational Linguistics, 2022
BASE
Show details
3
Lecture Translator Speech translation framework for simultaneous lecture translation
Waibel, Alex; Nguyen, Thai-Son; Cho, Eunah. - : Association for Computational Linguistics, 2022
BASE
Show details
4
Open Source Toolkit for Speech to Text Translation
In: The Prague Bulletin of Mathematical Linguistics, 111 (1), 125–135 ; ISSN: 0032-6585, 1804-0462 (2022)
BASE
Show details
5
Lightly Supervised Quality Estimation
Waibel, Alex; Niehues, Jan; Stüker, Sebastian. - : Association for Computational Linguistics, 2022
BASE
Show details
6
ELITR Multilingual Live Subtitling: Demo and Strategy ...
BASE
Show details
7
Efficient Weight factorization for Multilingual Speech Recognition ...
BASE
Show details
8
Efficientweight factorization for multilingual speech recognition
Pham, Ngoc-Quan; Nguyen, Tuan-Nam; Stueker, Sebastian. - : Curran Associates, Inc., 2021
BASE
Show details
9
Findings of the IWSLT 2020 Evaluation campaign ...
Ansari, Ebrahim; Axelrod, Amittai; Bach, Nguyen. - : Association for Computational Linguistics, 2020
BASE
Show details
10
Super-Human Performance in Online Low-latency Recognition of Conversational Speech ...
BASE
Show details
11
Neural Language Codes for Multilingual Acoustic Models ...
Abstract: Multilingual Speech Recognition is one of the most costly AI problems, because each language (7,000+) and even different accents require their own acoustic models to obtain best recognition performance. Even though they all use the same phoneme symbols, each language and accent imposes its own coloring or "twang". Many adaptive approaches have been proposed, but they require further training, additional data and generally are inferior to monolingually trained models. In this paper, we propose a different approach that uses a large multilingual model that is \emph{modulated} by the codes generated by an ancillary network that learns to code useful differences between the "twangs" or human language. We use Meta-Pi networks to have one network (the language code net) gate the activity of neurons in another (the acoustic model nets). Our results show that during recognition multilingual Meta-Pi networks quickly adapt to the proper language coloring without retraining or new data, and perform better than ... : 5 pages, 3 figures, accepted at Interspeech 2018 ...
Keyword: Audio and Speech Processing eess.AS; Computation and Language cs.CL; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Machine Learning cs.LG; Sound cs.SD
URL: https://dx.doi.org/10.48550/arxiv.1807.01956
https://arxiv.org/abs/1807.01956
BASE
Hide details
12
Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the "Speaking Rosetta" JSALT 2017 Workshop ...
BASE
Show details
13
19: Grundlagen der Automatischen Spracherkennung, Vorlesung, WS 2017/18, 24.01.2018
BASE
Show details
14
Open Source Toolkit for Speech to Text Translation
In: Prague Bulletin of Mathematical Linguistics , Vol 111, Iss 1, Pp 125-135 (2018) (2018)
BASE
Show details
15
Multilingual Adaptation of RNN Based ASR Systems ...
BASE
Show details
16
Phonemic and Graphemic Multilingual CTC Based Speech Recognition ...
BASE
Show details
17
Comparison of Decoding Strategies for CTC Acoustic Models ...
BASE
Show details
18
13: Grundbegriffe der Informatik, Vorlesung, WS 2017/18, 01.12.2017
BASE
Show details
19
Grundlagen der Automatischen Spracherkennung, Vorlesung, WS 2016/17, 18.01.2017, 18
BASE
Show details
20
03: Grundlagen der Automatischen Spracherkennung, Vorlesung, WS 2017/18, 30.10.2017
BASE
Show details

Page: 1 2 3

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
55
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern