Zobrazeno 1 - 10
of 87
pro vyhledávání: '"Mei-Yuh Hwang"'
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 27:1826-1838
End-to-end speech recognition, such as attention based approaches, is an emerging and attractive topic in recent years. It has achieved comparable performance with the traditional speech recognition framework. Because end-to-end approaches integrate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1c892b26b4e8e2ce7cb0fcb947e55b37
https://doi.org/10.1109/taslp.2019.2933146
https://doi.org/10.1109/taslp.2019.2933146
Publikováno v:
IEEE Signal Processing Letters. 26:1471-1475
We apply an anchor-based region proposal network (RPN) for end-to-end keyword spotting (KWS). RPNs have been widely used for object detection in image and video processing; here, it is used to jointly model keyword classification and localization. Th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9f3eb24d2e3f11b4b779ab9f915703a7
https://doi.org/10.1109/lsp.2019.2936282
https://doi.org/10.1109/lsp.2019.2936282
Publikováno v:
ICASSP
Max-pooling neural network architectures have been proven to be useful for keyword spotting (KWS), but standard training methods suffer from a class-imbalance problem when using all frames from negative utterances. To address the problem, we propose
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::871f3cab3522206d0499d59254b6f4b9
https://doi.org/10.1109/icassp40776.2020.9053009
https://doi.org/10.1109/icassp40776.2020.9053009
Publikováno v:
APSIPA
Far-field speech recognition is becoming a hot topic in research and industrial applications. In this paper, in order to improve far-field speech recognition performance, we propose to use multiple fixed beamformers with a spacial Wiener-form postfil
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::135f1d464ef42d55fc47df36a82a7b16
https://doi.org/10.1109/apsipaasc47483.2019.9023131
https://doi.org/10.1109/apsipaasc47483.2019.9023131
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f66b110792c74fa894a3b8efe91fbbb2
https://doi.org/10.21437/interspeech.2019-2944
https://doi.org/10.21437/interspeech.2019-2944
Publikováno v:
ACL (1)
Clarifying user needs is essential for existing task-oriented dialogue systems. However, in real-world applications, developers can never guarantee that all possible user demands are taken into account in the design phase. Consequently, existing syst
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f20a8eabd02f4493ae5be5288238e229
http://arxiv.org/abs/1906.04991
http://arxiv.org/abs/1906.04991
Publikováno v:
ICASSP
Recurrent Neural Networks (RNNs) have dominated language modeling because of their superior performance over traditional N-gram based models. In many applications, a large Recurrent Neural Network language model (RNNLM) or an ensemble of several RNNL
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bebd3afcad6596ee546cf54e89131555
https://doi.org/10.1109/icassp.2019.8683533
https://doi.org/10.1109/icassp.2019.8683533
Publikováno v:
ICASSP
Long Short Term Memory Connectionist Temporal Classification (LSTM-CTC) based end-to-end models are widely used in speech recognition due to its simplicity in training and efficiency in decoding. In conventional LSTM-CTC based models, a bottleneck pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fc940e6164dab02c4320710c5d627b69
https://doi.org/10.1109/icassp.2019.8683297
https://doi.org/10.1109/icassp.2019.8683297
Publikováno v:
5th International Workshop on Speech Processing in Everyday Environments (CHiME 2018).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7aa22e5aeff029c45b7f0098c40c3ce5
https://doi.org/10.21437/chime.2018-19
https://doi.org/10.21437/chime.2018-19
Publikováno v:
INTERSPEECH
This paper explores the use of adversarial examples in training speech recognition systems to increase robustness of deep neural network acoustic models. During training, the fast gradient sign method is used to generate adversarial examples augmenti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::130fea67a9819b3209aadf4a9776ed99
https://doi.org/10.21437/interspeech.2018-1247
https://doi.org/10.21437/interspeech.2018-1247