Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Poonlap Lamsrichan"'
Publikováno v:
2022 19th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f71a7090bede2bea691cf4e09cb4a26f
https://doi.org/10.1109/ecti-con54298.2022.9795634
https://doi.org/10.1109/ecti-con54298.2022.9795634
Publikováno v:
JCSSE
The out-of-vocabulary (OOV) words is a problem that impacts recognition accuracy, whether it is the HMM model, DNN model, or end-to-end speech recognition. This paper proposes a hybrid input-type recurrent neural network language model (RNNLM) for en
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4cdef0a373bc369b00f6f6d59df7dd33
https://doi.org/10.1109/jcsse53117.2021.9493812
https://doi.org/10.1109/jcsse53117.2021.9493812
Autor:
Poonlap Lamsrichan
Publikováno v:
ICCE
A new color image compression based on block truncation coding is proposed. After integer color transformation, the new method for encoding all 4 RVs in the 4-level BTC effectively is applied to Y component. The chromatic components are down-sampled
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::33cc1eba0a1e1da4b0c33894f72bc1c5
https://doi.org/10.1109/icce50685.2021.9427615
https://doi.org/10.1109/icce50685.2021.9427615
Autor:
Takao Kobayashi, Nattapong Kurpukdee, Tomoki Koriyama, Sawit Kasuriya, Chai Wutiwiwatchai, Poonlap Lamsrichan
Publikováno v:
APSIPA
In this paper, we propose a speech emotion recognition technique using convolutional long short-term memory (LSTM) recurrent neural network (ConvLSTM-RNN) as a phoneme-based feature extractor from raw input speech signal. In the proposed technique, C
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6018488a01ed743652abfc1de24d1444
https://doi.org/10.1109/apsipa.2017.8282315
https://doi.org/10.1109/apsipa.2017.8282315
Autor:
Poonlap Lamsrichan, Vataya Chunwijitra, Sawit Kasuriya, Chai Wutiwiwatchai, Nattapong Kurpukdee
Publikováno v:
2017 8th International Conference of Information and Communication Technology for Embedded Systems (IC-ICTES).
In this paper, efficiency comparison of Support Vector Machines (SVM) and Binary Support Vector Machines (BSVM) techniques in utterance-based emotion recognition is studied. Acoustic features including energy, Mel-frequency cepstral coefficients (MFC
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bc167bc8c34830b2adc2e6b317855563
https://doi.org/10.1109/ictemsys.2017.7958773
https://doi.org/10.1109/ictemsys.2017.7958773
Publikováno v:
2015 12th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON).
The Hybrid encoder is trying to choose the better encoder between the Wavelet Difference Reduction (Type-W) and Simple Bit-plane (Type-B) to get the better results than pure Type-W or pure Type-B was proposed in previous research. In case that the mo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d58f5b31bb6b205ca8ce1bea17d58b1a
https://doi.org/10.1109/ecticon.2015.7207056
https://doi.org/10.1109/ecticon.2015.7207056
Publikováno v:
2015 6th International Conference of Information and Communication Technology for Embedded Systems (IC-ICTES).
In this paper, fingerprint images compressed with WSQ, CAWDR and JPEG2000 are evaluated for fingerprint recognition performance. With high compression ratio between 40:1 to 160:1, fingerprint images which lost a lot of their details are used to find
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c02fe1ef32af9753adc637424ab3a482
https://doi.org/10.1109/ictemsys.2015.7110837
https://doi.org/10.1109/ictemsys.2015.7110837
Publikováno v:
2013 13th International Symposium on Communications and Information Technologies (ISCIT).
The performance of image compression is based on number of levels of wavelet transform and compression algorithm. Padding some extra pixels to the inappropriate-sized images can make them legible for many levels of conventional (or symmetric) wavelet
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e12fcfabb4e347cdf1c2ad197b9bb96f
https://doi.org/10.1109/iscit.2013.6645901
https://doi.org/10.1109/iscit.2013.6645901
Autor:
S. Saychum, Takao Kobayashi, P. Janjoi, Chai Wutiwiwatchai, Nattanun Thatphithakkul, Ausdang Thangthai, Poonlap Lamsrichan
Publikováno v:
2012 9th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology.
This paper presents a bi-lingual Thai-English text-to-speech synthesis (TTS) system on Android mobile devices. The system deploys a Thai text processor and a well-known open-source English text processor, which can analyzes English text at high intel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4a74bbf185b481af972b3fad6c53c242
https://doi.org/10.1109/ecticon.2012.6254283
https://doi.org/10.1109/ecticon.2012.6254283
Autor:
Poonlap Lamsrichan
Publikováno v:
The 8th Electrical Engineering/ Electronics, Computer, Telecommunications and Information Technology (ECTI) Association of Thailand - Conference 2011.
This paper proposes a new image coding technique with low-memory usage and fast encoding/decoding time. In this embedded coder, the wavelet coefficients are tested with adaptive threshold and encoded into bit-stream with wavelet difference reduction
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4e7cbf8d01a03136f414ffae4c54bc7d
https://doi.org/10.1109/ecticon.2011.5948006
https://doi.org/10.1109/ecticon.2011.5948006