1 |
Empirical Evaluation and Combination of Punctuation Prediction Models Applied to Broadcast News
|
|
|
|
In: http://infoscience.epfl.ch/record/264117 (2019)
|
|
BASE
|
|
Show details
|
|
2 |
EMPIRICAL EVALUATION AND COMBINATION OF PUNCTUATION PREDICTION MODELS APPLIED TO BROADCAST NEWS
|
|
|
|
In: http://infoscience.epfl.ch/record/265776 (2019)
|
|
BASE
|
|
Show details
|
|
3 |
Cross-lingual Adaptation of a CTC-based multilingual Acoustic Model
|
|
|
|
In: http://infoscience.epfl.ch/record/263158 (2019)
|
|
BASE
|
|
Show details
|
|
4 |
An Investigation of Multilingual ASR using End-to-End LF-MMI
|
|
|
|
In: http://infoscience.epfl.ch/record/264932 (2019)
|
|
BASE
|
|
Show details
|
|
7 |
A Variational Prosody Model for Mapping the Context-Sensitive Variation of Functional Prosodic Prototypes ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Cross-lingual adaptation of a CTC-based multilingual acoustic model ...
|
|
|
|
Abstract:
Multilingual models for Automatic Speech Recognition (ASR) are attractive as they have been shown to benefit from more training data, and better lend themselves to adaptation to under-resourced languages. However, initialisation from monolingual context-dependent models leads to an explosion of context-dependent states. Connectionist Temporal Classification (CTC) is a potential solution to this as it performs well with monophone labels. We investigate multilingual CTC training in the context of adaptation and regularisation techniques that have been shown to be beneficial in more conventional contexts. The multilingual model is trained to model a universal International Phonetic Alphabet (IPA)-based phone set using the CTC loss function. Learning Hidden Unit Contribution (LHUC) is investigated to perform language adaptive training. During cross-lingual adaptation, the idea of extending the multilingual output layer to new phonemes is introduced and investigated. In addition, dropout during multilingual ...
|
|
URL: https://dx.doi.org/10.5281/zenodo.2359116 https://zenodo.org/record/2359116
|
|
BASE
|
|
Hide details
|
|
9 |
Cross-lingual adaptation of a CTC-based multilingual acoustic model ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Multilingual Training and Cross-lingual Adaptation on CTC-based Acoustic Model ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Intonation modelling using a muscle model and perceptually weighted matching pursuit
|
|
|
|
In: http://infoscience.epfl.ch/record/233571 (2017)
|
|
BASE
|
|
Show details
|
|
14 |
Comparative Study on Sentence Boundary Prediction for German and English Broadcast News
|
|
|
|
In: http://infoscience.epfl.ch/record/229982 (2017)
|
|
BASE
|
|
Show details
|
|
15 |
Sound Pattern Matching for Automatic Prosodic Event Detection
|
|
|
|
In: http://infoscience.epfl.ch/record/218107 (2016)
|
|
BASE
|
|
Show details
|
|
16 |
Composition of Deep and Spiking Neural Networks for Very Low Bit Rate Speech Coding ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Design of a Speech Corpus for Research on Cross-Lingual Prosody Transfer
|
|
|
|
In: http://infoscience.epfl.ch/record/222452 (2016)
|
|
BASE
|
|
Show details
|
|
18 |
PhonVoc: A Phonetic and Phonological Vocoding Toolkit
|
|
|
|
In: http://infoscience.epfl.ch/record/218850 (2016)
|
|
BASE
|
|
Show details
|
|
19 |
An agonist-antagonist pitch production model
|
|
|
|
In: http://infoscience.epfl.ch/record/222448 (2016)
|
|
BASE
|
|
Show details
|
|
20 |
Investigating Cross-lingual Multi-level Adaptive Networks: The Importance of the Correlation of Source and Target Languages
|
|
|
|
In: http://infoscience.epfl.ch/record/223756 (2016)
|
|
BASE
|
|
Show details
|
|
|
|