Analysis of Multilingual Sequence-to-Sequence Speech Recognition Systems
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F19%3APU134178" target="_blank" >RIV/00216305:26230/19:PU134178 - isvavai.cz</a>
Result on the web
<a href="https://www.isca-speech.org/archive/Interspeech_2019/pdfs/2355.pdf" target="_blank" >https://www.isca-speech.org/archive/Interspeech_2019/pdfs/2355.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.21437/Interspeech.2019-2355" target="_blank" >10.21437/Interspeech.2019-2355</a>
Alternative languages
Result language
angličtina
Original language name
Analysis of Multilingual Sequence-to-Sequence Speech Recognition Systems
Original language description
This paper investigates the applications of various multilingual approaches developed in conventional deep neural network - hidden Markov model (DNN-HMM) systems to sequence-tosequence (seq2seq) automatic speech recognition (ASR). We employ a joint connectionist temporal classification-attention network as our base model. Our main contribution is separated into two parts. First, we investigate the effectiveness of the seq2seq model with stacked multilingual bottle-neck features obtained from a conventional DNN-HMM system on the Babel multilingual speech corpus. Second, we investigate the effectiveness of transfer learning from a pre-trained multilingual seq2seq model with and without the target language included in the original multilingual training data. In this experiment, we also explore various architectures and training strategies of the multilingual seq2seq model by making use of knowledge obtained in the DNN-HMM based transfer-learning. Although both approaches significantly improved the performance from a monolingual seq2seq baseline, interestingly, we found the multilingual bottle-neck features to be superior to multilingual models with transfer learning. This finding suggests that we can efficiently combine the benefits of the DNN-HMM system with the seq2seq system through multilingual bottle-neck feature techniques.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/LQ1602" target="_blank" >LQ1602: IT4Innovations excellence in science</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of Interspeech
ISBN
—
ISSN
1990-9772
e-ISSN
—
Number of pages
5
Pages from-to
2220-2224
Publisher name
International Speech Communication Association
Place of publication
Graz
Event location
INTERSPEECH 2019
Event date
Sep 15, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—