scholarly journals High performance segmentation of spontaneous speech using part of speech and trigger word information

Author(s):  
Marsal Gavaldà ◽  
Klaus Zechner ◽  
Gregory Aist
2021 ◽  
Vol 22 (4) ◽  
Author(s):  
Tuan Anh Tran ◽  
Jarunee Duangsuwan ◽  
Wiphada Wettayaprasit

One of the factors improving businesses in business intelligence is summarization systems which could generate summaries based on sentiment from social media. However, these systems could not produce automatically, they used annotated datasets. To automatically produce sentiment summaries without using the annotated datasets, we propose a novel framework using pattern rules. The framework has two procedures: 1) pre-processing and 2) aspect knowledgebase generation. The first procedure is to check and correct misspelt words (bigram and unigram) by a proposed method, and tag part-of-speech all words. The second procedure is to automatically generate aspect knowledgebase used to produce sentiment summaries by the sentiment summarization systems. Pattern rules and semantic similarity-based pruning are used to automatically generate aspect knowledgebase from social media. In the experiments, eight domains from benchmark datasets of reviews are used. The performance evaluation of our proposed approach shows the high performance when compared to other approaches.


Author(s):  
Dim Lam Cing ◽  
Khin Mar Soe

In Natural Language Processing (NLP), Word segmentation and Part-of-Speech (POS) tagging are fundamental tasks. The POS information is also necessary in NLP’s preprocessing work applications such as machine translation (MT), information retrieval (IR), etc. Currently, there are many research efforts in word segmentation and POS tagging developed separately with different methods to get high performance and accuracy. For Myanmar Language, there are also separate word segmentors and POS taggers based on statistical approaches such as Neural Network (NN) and Hidden Markov Models (HMMs). But, as the Myanmar language's complex morphological structure, the OOV problem still exists. To keep away from error and improve segmentation by utilizing POS data, segmentation and labeling should be possible at the same time.The main goal of developing POS tagger for any Language is to improve accuracy of tagging and remove ambiguity in sentences due to language structure. This paper focuses on developing word segmentation and Part-of- Speech (POS) Tagger for Myanmar Language. This paper presented the comparison of separate word segmentation and POS tagging with joint word segmentation and POS tagging.


2020 ◽  
pp. 45-58
Author(s):  
Oleksandr Ishchenko ◽  

The study analyzes speech pauses of Ukrainian. The research material is the audio texts of spontaneous conversational speech of customarily pronunciation and intonation, as well as non-spontaneous (read) speech of clear pronunciation and expressive intonation. We show a robust tendency for high frequency of pauses after nouns. It suggests that pausing is like a predictor of nouns. The frequency of pausing after verbs is slightly lower. The probability of pause location after any another part of speech is much lower. Generally, pausing can be occurred after words of any grammatical category. These findings spread virtually equally to both spontaneous conversational speech and non-spontaneous speech (clear intonated reading). The effect of nouns on pause occurrence may be caused by universal property of the human language. It is recently accepted that nouns slow down speech across structurally and culturally diverse languages. This is because nouns load cognitive processes of the speech production planning more as compared with verbs and other parts. At the same time, some Ukrainian language features also impact the pausing after nouns (these features are characteristic of other Slavic languages too). This is about a prosodic phrasing of Ukrainian according to that interpausal utterances usually are finalized by nouns (rarely by verbs or other principal parts of speech) which get most semantic load. The pauses do not follow after each noun, because they can be exploited in the speech segmentation in depends on linguistic (linguistic structure of speech), physiological (individuality of speech production, breathing), and psycholingual factors. We suggest that the priming effect as a noun- and verb-inducted psycholingual factor can significantly impact pausing in spoken language. Statistical measures show the following: 430 ms ±60% is the average pause duration of non-spontaneous clear expressive speech, 355 ms ±50% is the average pause duration of spontaneous customarily speech. Thus, pauses of non-spontaneous speech have a longer duration than of spontaneous speech. This is indicated by both the average pause duration means (ms) and the relative standard deviation of pause durations (±%). Keywords: expressive speech, spontaneous speech, phonetics, prosody, speech pauses, pausing, prepausal words, nouns, verbs.


Author(s):  
Tetsuo Kosaka ◽  
Takashi Kusama ◽  
Masaharu Kato ◽  
Masaki Kohda

The aim of this work is to improve the recognition performance of spontaneous speech. In order to achieve the purpose, the authors of this chapter propose new approaches of unsupervised adaptation for spontaneous speech and evaluate the methods by using diagonal-covariance and full-covariance hidden Markov models. In the adaptation procedure, both methods of language model (LM) adaptation and acoustic model (AM) adaptation are used iteratively. Several combination methods are tested to find the optimal approach. In the LM adaptation, a word trigram model and a part-of-speech (POS) trigram model are combined to build a more task-specific LM. In addition, the authors propose an unsupervised speaker adaptation technique based on adaptation data weighting. The weighting is performed depending on POS class. In Japan, a large-scale spontaneous speech database “Corpus of Spontaneous Japanese (CSJ)” has been used as the common evaluation database for spontaneous speech and the authors used it for their recognition experiments. From the results, the proposed methods demonstrated a significant advantage in that task.


2019 ◽  
Vol 9 (4) ◽  
pp. 722 ◽  
Author(s):  
Muhetaer Munire ◽  
Xiao Li ◽  
Yating Yang

In this paper, a hybrid strategy of rules and statistics is employed to implement the Uyghur Noun Re-inflection model. More specifically, completed Uyghur sentences are taken as an input, and these Uyghur sentences are marked with part of speech tagging, and the nouns in the sentences remain the form of the stem. In this model, relevant linguistic rules and statistical algorithms are used to find the most probable noun suffixes and output the Uyghur sentences after the nouns are re-inflected. With rules of linguistics artificially summed up, the training corpora are formed by the human–machine exchange. The final experimental result shows that the Uyghur morphological re-inflection model is of high performance and can be applied to various fields of natural language processing, such as Uyghur machine translation and natural language generation.


Author(s):  
A. V. Crewe ◽  
M. Isaacson ◽  
D. Johnson

A double focusing magnetic spectrometer has been constructed for use with a field emission electron gun scanning microscope in order to study the electron energy loss mechanism in thin specimens. It is of the uniform field sector type with curved pole pieces. The shape of the pole pieces is determined by requiring that all particles be focused to a point at the image slit (point 1). The resultant shape gives perfect focusing in the median plane (Fig. 1) and first order focusing in the vertical plane (Fig. 2).


Author(s):  
N. Yoshimura ◽  
K. Shirota ◽  
T. Etoh

One of the most important requirements for a high-performance EM, especially an analytical EM using a fine beam probe, is to prevent specimen contamination by providing a clean high vacuum in the vicinity of the specimen. However, in almost all commercial EMs, the pressure in the vicinity of the specimen under observation is usually more than ten times higher than the pressure measured at the punping line. The EM column inevitably requires the use of greased Viton O-rings for fine movement, and specimens and films need to be exchanged frequently and several attachments may also be exchanged. For these reasons, a high speed pumping system, as well as a clean vacuum system, is now required. A newly developed electron microscope, the JEM-100CX features clean high vacuum in the vicinity of the specimen, realized by the use of a CASCADE type diffusion pump system which has been essentially improved over its predeces- sorD employed on the JEM-100C.


Author(s):  
John W. Coleman

In the design engineering of high performance electromagnetic lenses, the direct conversion of electron optical design data into drawings for reliable hardware is oftentimes difficult, especially in terms of how to mount parts to each other, how to tolerance dimensions, and how to specify finishes. An answer to this is in the use of magnetostatic analytics, corresponding to boundary conditions for the optical design. With such models, the magnetostatic force on a test pole along the axis may be examined, and in this way one may obtain priority listings for holding dimensions, relieving stresses, etc..The development of magnetostatic models most easily proceeds from the derivation of scalar potentials of separate geometric elements. These potentials can then be conbined at will because of the superposition characteristic of conservative force fields.


Sign in / Sign up

Export Citation Format

Share Document