2 |
On Investigation of Unsupervised Speech Factorization Based on Normalization Flow ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Phonetic-attention scoring for deep speaker features in speaker verification ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Phonetic Temporal Neural Model for Language Identification ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
AP16-OL7: A Multilingual Database for Oriental Languages and A Language Recognition Baseline ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Multi-task Recurrent Model for True Multilingual Speech Recognition ...
|
|
|
|
Abstract:
Research on multilingual speech recognition remains attractive yet challenging. Recent studies focus on learning shared structures under the multi-task paradigm, in particular a feature sharing structure. This approach has been found effective to improve performance on each individual language. However, this approach is only useful when the deployed system supports just one language. In a true multilingual scenario where multiple languages are allowed, performance will be significantly reduced due to the competition among languages in the decoding space. This paper presents a multi-task recurrent model that involves a multilingual speech recognition (ASR) component and a language recognition (LR) component, and the ASR component is informed of the language information by the LR component, leading to a language-aware recognition. We tested the approach on an English-Chinese bilingual recognition task. The results show that the proposed multi-task recurrent model can improve performance of multilingual ... : APSIPA 2016. arXiv admin note: text overlap with arXiv:1603.09643 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG; Neural and Evolutionary Computing cs.NE
|
|
URL: https://arxiv.org/abs/1609.08337 https://dx.doi.org/10.48550/arxiv.1609.08337
|
|
BASE
|
|
Hide details
|
|
8 |
System Combination for Short Utterance Speaker Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|