Vietnamese speech synthesis for some assistant services on mobile devices

... phân biệt âm tiết cao độ Các g p p tổng hợp tiếng nói giải pháp g ợp g tiếng Việt Ghép tiếng nói Ghép tiếng nói p g Ghép tiếng nói phần vần Ghép tiếng nói từ từ riêng lẻ từ đơn âm g theo hai phần: ... điểm âm tiết tiếng Việt Tính độc lập – Âm tiết tiếng Việt thể rõ ràng, riêng biệt với Trong tiếng Việt tượng nối âm Có khả mang ý nghĩa – Hầu hết âm tiết tiếng Việt...

Ngày tải lên: 07/11/2013, 07:15

Ngày tải lên: 27/03/2015, 15:04

Ngày tải lên: 13/04/2013, 11:10

... distribution Of the 104 broad topics, the top-5 topics contained over 50% of the dynamic questions These top five topics were sports, TV and radio, events, movies, and finance Considering the issues ... use the temporal relations in a question to decompose it into simpler questions, the answers of which are recomposed to produce the answers to the original question 3.1 Que...

Ngày tải lên: 17/03/2014, 00:20

... our web method: using using using using System; System .Web; System .Web. Services; System .Web. Services. Protocols; 8547ch06final.qxd 8/30/07 3:50 PM Page 231 CHAPTER s REPORTING WITH WEB SERVICES AND ... s REPORTING WITH WEB SERVICES AND MOBILE DEVICES Figure 6-3 The web service is hosted with the internal web server of the VS IDE s Note You may get a differ...

Ngày tải lên: 05/10/2013, 08:48

... combination of a predicted user position with prebuffering of data associated with physical locations bears many advantages in increased throughput of mobile devices An interesting solution (Microsoft ... location, and other metadata of the artefact This manager substitutes the online conversion mechanism, which can transform the real online information system data to WLA dat...

Ngày tải lên: 21/06/2014, 22:20

... per each EK Whenever the manufacturer generates a new EK, it informs the Privacy CA, in a safe way, about that EK The Privacy CA, like the manufacturer, maintains a database of all available ... The manufacturer maintains a database of all available EKs (M EKDB), indexed by MD(EK) The database has all information that the manufacturer needs about each SDR-MD it has produced When the m...

Ngày tải lên: 23/06/2014, 00:20

... Chapter Spatial Joins on Mobile Devices 3.1 3.1.1 MobiJoin Motivation and Problem Definition Let q be a spatial query issued at a mobile device (e.g., PDA), which combines information from two spatial ... in Mobile Devices 82 4.3.3 Experimental Evaluation 83 Conclusions 87 Summary Mobile devices like PDAs are capable of retrieving information from various types of...

Ngày tải lên: 09/10/2015, 11:18

... this thesis is to model the characteristics of Vietnamese prosody for speech synthesis It focuses on the influences of the macro -prosody on the micro -prosody, in three types of sentence: assertive, ... characteristics of Vietnamese prosody to generate the prosody description” for speech synthesis In this thesis, we just focus on the differences of...

Ngày tải lên: 19/02/2014, 08:58

... the training phase from the recognizing phase in order to reduce the system resource used in T-Engine The training phase is implement in a PC with speech data from T-Engine, only the recognition ... implemented in T-Engine IV VIETNAMESE SPEECH SYNTHESIS IN T-ENGINE Previous researches in Vietnamese speech synthesis have indicated that PSOLA is an effective...

Ngày tải lên: 12/04/2013, 16:05

... esp regarding prosody), we aim to incrementalize the speech synthesis component itself Dutoit et al (2011) have presented an incremental formulation for HMM-based speech synthesis However, their ... open-source at http://inprotk.sourceforge.net 104 We aim for a fully incremental speech synthesis component that can be integrated into dialogue systems There is some work on in...

Ngày tải lên: 16/03/2014, 20:20

... syllables of disyllabic word in Mandarin Chinese”, Proc ICSLP, Hirschberg, J., 1996 “Training intonational phrasing rules automatically for English and Spanish text -to- speech”, Speech Communication, ... word format and some POS-based ones on the same training set and test set Overall, HMMpath-I can achieve high accuracy by about 10% Conclusions/Discussions We described an approach...

Ngày tải lên: 17/03/2014, 04:20

... for concatenative speech synthesis In Proceedings of Eurospeech, volume 2, pages 607–610 Ivan Bulyko and Mari Ostendorf 2001 Unit selection for speech synthesis using splicing costs with weighted ... with input label a and output b For the purpose of our unit selection system, we had to resort to an approximation This is because in general, the backoff use just outlined...

Ngày tải lên: 23/03/2014, 19:20

... to Speech, incomplete draft, undergroland press, 1979 Chomsky, N., and Halle, M., The Sound Pattern of English, Harper and Row, 1968 Church, K., Stress Assignment in Letter to Sound Rules for Speech ... support the the stress neutral theory because they never receive main stress But, they can also be accounted for under the compound theory because they form nouns, and the...

Ngày tải lên: 31/03/2014, 17:20

... theory The Shannon-McMillan theorem on the Markov chain has been studied extensively see 2, In the recent years, with the development of the information theory scholars get to study the Shannon-McMillan ... comparison between the arbitrary measure and Markov measure on the generalized Bethe tree As corollaries, a class of Shannon-McMillan theorems for a...

Ngày tải lên: 21/06/2014, 05:20