DE eng

Search in the Catalogues and Directories

Hits 1 – 17 of 17

1
A Complementary Joint Training Approach Using Unpaired Speech and Text for Low-Resource Automatic Speech Recognition ...
Du, Ye-Qian; Zhang, Jie; Zhu, Qiu-Shi. - : arXiv, 2022
BASE
Show details
2
XLST: Cross-lingual Self-training to Learn Multilingual Representation for Low Resource Speech Recognition ...
BASE
Show details
3
Recognition-Synthesis Based Non-Parallel Voice Conversion with Adversarial Learning ...
BASE
Show details
4
Improving Sequence-to-Sequence Acoustic Modeling by Adding Text-Supervision ...
BASE
Show details
5
LID-senones and their statistics for language identification
Jin, Ma; Song, Yan; McLoughlin, Ian Vince; Dai, Li-Rong. - : Institute of Electrical and Electronics Engineers, 2017
Abstract: Recent research on end-to-end training structures for language identification has raised the possibility that intermediate language-sensitive feature units exist which are analogous to phonetically-sensitive senones in automatic speech recognition systems. Termed LID (language identification)-senones, the statistics derived from these feature units have been shown to be beneficial in discriminating between languages, particularly for short utterances. This paper examines the evidence for the existence of LID-senones before designing and evaluating LID systems based on low and high level statistics of LID-senones with both generative and discriminative models. For the standard NIST LRE 2009 task on 23 languages, LID-senone based systems are shown to outperform state-of-the art DNN/i-vector methods both when LID-senones are used directly for classification and when LID-senone statistics are used for i-vector formation.
Keyword: T Technology
URL: https://doi.org/10.1109/TASLP.2017.2766023
https://kar.kent.ac.uk/64034/7/08080255.pdf
https://kar.kent.ac.uk/64034/
https://kar.kent.ac.uk/64034/1/LID_senone_J_v9.pdf
BASE
Hide details
6
A human neurodevelopmental model for Williams syndrome.
In: Nature, vol 536, iss 7616 (2016)
BASE
Show details
7
A human neurodevelopmental model for Williams syndrome.
In: Nature, vol 536, iss 7616 (2016)
BASE
Show details
8
Improvements on Deep Bottleneck Network based I-Vector Representation for Spoken Language Identification
BASE
Show details
9
Deep Bottleneck Feature for Image Classification
BASE
Show details
10
HMM-based unit selection speech synthesis using log likelihood ratios derived from perceptual data
In: Speech communication. - Amsterdam [u.a.] : Elsevier 63 (2014), 27-37
OLC Linguistik
Show details
11
Deep Bottleneck Features for Spoken Language Identification
Jiang, Bing; Song, Yan; Wei, Si. - : Public Library of Science, 2014
BASE
Show details
12
Whisper-to-speech conversion using restricted Boltzmann machine arrays
Li, Jing-jie; McLoughlin, Ian Vince; Dai, Li-Rong. - : IET Digital Library, 2014
BASE
Show details
13
Deep bottleneck features for spoken language identification
Jiang, Bing; Song, Yan; Wei, Si. - : Public Library of Science, 2014
BASE
Show details
14
Minimum Kullback-Leibler divergence parameter generation for HMM-based speech synthesis
In: Institute of Electrical and Electronics Engineers. IEEE transactions on audio, speech and language processing. - New York, NY : Inst. 20 (2012) 5, 1492-1502
BLLDB
OLC Linguistik
Show details
15
Trust region-based optimization for maximum mutual information estimation of HMMs in speech recognition
In: Institute of Electrical and Electronics Engineers. IEEE transactions on audio, speech and language processing. - New York, NY : Inst. 19 (2011) 8, 2474-2485
BLLDB
OLC Linguistik
Show details
16
Intelligence in Williams Syndrome is related to STX1A, which encodes a component of the presynaptic SNARE complex.
In: PloS one, vol 5, iss 4 (2010)
BASE
Show details
17
Intelligence in Williams Syndrome Is Related to STX1A, Which Encodes a Component of the Presynaptic SNARE Complex
Gao, Michael C.; Bellugi, Ursula; Dai, Li. - : Public Library of Science, 2010
BASE
Show details

Catalogues
0
0
3
0
0
0
0
Bibliographies
2
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
14
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern