標(biāo)題: Titlebook: Computational Processing of the Portuguese Language; 6th International Wo Nuno J. Mamede,Isabel Trancoso,Maria Gra?as Volpe Conference pro [打印本頁] 作者: Intimidate 時(shí)間: 2025-3-21 16:40
書目名稱Computational Processing of the Portuguese Language影響因子(影響力)
書目名稱Computational Processing of the Portuguese Language影響因子(影響力)學(xué)科排名
書目名稱Computational Processing of the Portuguese Language網(wǎng)絡(luò)公開度
書目名稱Computational Processing of the Portuguese Language網(wǎng)絡(luò)公開度學(xué)科排名
書目名稱Computational Processing of the Portuguese Language被引頻次
書目名稱Computational Processing of the Portuguese Language被引頻次學(xué)科排名
書目名稱Computational Processing of the Portuguese Language年度引用
書目名稱Computational Processing of the Portuguese Language年度引用學(xué)科排名
書目名稱Computational Processing of the Portuguese Language讀者反饋
書目名稱Computational Processing of the Portuguese Language讀者反饋學(xué)科排名
作者: evince 時(shí)間: 2025-3-21 22:38
Computational Processing of the Portuguese Language6th International Wo作者: 取之不竭 時(shí)間: 2025-3-22 01:42
Nuno J. Mamede,Isabel Trancoso,Maria Gra?as Volpe 作者: 阻撓 時(shí)間: 2025-3-22 07:46 作者: Gustatory 時(shí)間: 2025-3-22 09:48
Devoicing Measures of European Portuguese Fricativestio of variances of the laryngograph signal during the VF transition and during the fricative) were used to classify the examples into two or three categories. The results of the automatic and manual measures of devoicing are compared, and an explanation for observed misclassifications is presented.作者: embolus 時(shí)間: 2025-3-22 13:35 作者: embolus 時(shí)間: 2025-3-22 19:34 作者: 悅耳 時(shí)間: 2025-3-23 00:43 作者: 打包 時(shí)間: 2025-3-23 01:32 作者: fatty-acids 時(shí)間: 2025-3-23 06:54
Evaluation of a Segmental Durations Model for TTSn. This model is based on artificial neural networks. The evaluation of the model quality was made by comparison with read speech. The standard deviation reached in test set is 19.5 ms and the linear correlation coefficient is 0.84. The model is perceptually evaluated with 4.12 against 4.30 for natu作者: PHONE 時(shí)間: 2025-3-23 12:10 作者: 中和 時(shí)間: 2025-3-23 17:30 作者: 紀(jì)念 時(shí)間: 2025-3-23 20:20
Automatic Discovery of Brazilian Portuguese Letter to Phoneme Conversion Rules through Genetic Progrne the mapping of letters into sounds. This paper presents results of the application of an evolutionary computation technique (Genetic Programming), in Brazilian Portuguese synthesis, aiming to discover automatically programs implementing specific synthesis rules.作者: 誘使 時(shí)間: 2025-3-23 23:26
Experimental Phonetics Contributions to the Portuguese Articulatory Synthesizer Developmentesizer for Portuguese. Examples of analyses and results regarding glottal source parameters and from EMMA and acoustic analyses related to the tongue position are presented. In our studies contextual and regional variation is considered.作者: VEST 時(shí)間: 2025-3-24 04:35 作者: ascend 時(shí)間: 2025-3-24 09:20
Reusability of Dictionaries in the Compilation of NLP Lexiconsation, in the compilation process of a machine-tractable thesaurus-like lexical database for Brazilian Portuguese. After delimiting the scope of the polysemous term ., the paper focuses on the improvement of the resulting object by a small team, in a form compatible with and inspired by WordNet guid作者: 妨礙議事 時(shí)間: 2025-3-24 14:05
Homonymy in Natural Language Processes: A Representation Using Pustejovsky’s Qualia Structure and Onor its computational implementation in Systems of Natural Language Processing (SNLP). Pustejovsky’s Generative Lexicon was used as a theoretical model. From this model, the Qualia Structure — QS (and the Formal, Telic, Agentive and Constitutive roles) was selected as one of the linguistic and semant作者: lobster 時(shí)間: 2025-3-24 15:04
Using Adaptive Formalisms to Describe Context-Dependencies in Natural Languaged to syntactical ambiguities and non-determinisms in NL handling we extend it to consider context-dependencies not previously addressed. Although based on the powerful adaptive formalism [.], our method relies on adaptive structured pushdown automata [.] and grammars [.] — resulting simplicity, low-作者: textile 時(shí)間: 2025-3-24 21:50
Some Regularities of Frozen Expressions in Brazilian Portuguesef 3.550 verbal expressions, according to the distribution of the fixed and free components of each expression. Some regularity could be observed in this class, which resulted in the construction of a graph in order to identify the expressions of this class in large corpora.作者: 委屈 時(shí)間: 2025-3-25 00:39 作者: 燈泡 時(shí)間: 2025-3-25 05:47
An Account of the Challenge of Tagging a Reference Corpus for Brazilian Portugueseho, a 1.1 million word Brazilian Portuguese corpus of newspaper articles that has been developed in the Lacio-Web Project. Rather than simply presenting the annotated corpus and describing its tagset, we elaborate on the criteria for establishing the tagset and analyze some interesting cases amongst作者: JOT 時(shí)間: 2025-3-25 11:08 作者: 叢林 時(shí)間: 2025-3-25 13:08
HMM/MLP Hybrid Speech Recognizer for the Portuguese Telephone SpeechDat Corpus which will be described in detail, giving its recording conditions, speaker characteristics and contents categories. The automatic recognizer is a state-of-the-art HMM/MLP hybrid system employing different kinds of robust acoustic features. Training and testing was carried out on the clean digits a作者: 龍卷風(fēng) 時(shí)間: 2025-3-25 19:12
Pitch Restoration for Robust Speech Recognitionpeech spectrum. This algorithm was implemented over a baseline spectral normalisation method, which purpose is to emphasize the robustness in the regions of less energy of the speech spectrum, since in these regions the noise is more dominant.作者: bifurcate 時(shí)間: 2025-3-25 23:09
Improving the Accuracy of the Speech Synthesis Based Phonetic Alignment Using Multiple Acoustic Featacoustic features used in this procedure, it can perform poorly when applied to continuous speech utterances. In this paper we propose a new method to select the best features to use in the alignment procedure for each pair of phonetic segment classes. The results show that this selection considerably reduces the segment boundary location errors.作者: 存在主義 時(shí)間: 2025-3-26 04:05
Reusability of Dictionaries in the Compilation of NLP Lexiconselines, comments on the dictionary entries, addresses selected problems found in the process of extracting the relevant lexical information form the selected dictionaries, and provides some strategies to overcome them.作者: exostosis 時(shí)間: 2025-3-26 04:32
Homonymy in Natural Language Processes: A Representation Using Pustejovsky’s Qualia Structure and Onic expedients for the achievement of disambiguation of homonym forms. So that analyzed and treated data could be manipulated, we elaborated a Lexical Knowledge Base (LKB) where lexical items are correlated and interconnected by different kinds of semantic relations in the QS and ontological information.作者: 一條卷發(fā) 時(shí)間: 2025-3-26 09:29 作者: Hypomania 時(shí)間: 2025-3-26 14:45 作者: optic-nerve 時(shí)間: 2025-3-26 18:26 作者: 羊欄 時(shí)間: 2025-3-26 23:54 作者: Accommodation 時(shí)間: 2025-3-27 04:57 作者: jeopardize 時(shí)間: 2025-3-27 07:52 作者: 繞著哥哥問 時(shí)間: 2025-3-27 10:34
Devoicing Measures of European Portuguese Fricativestegories. The results of the automatic and manual measures of devoicing are compared, and an explanation for observed misclassifications is presented. Devoicing occurs extensively in Portuguese; results are compared to those for English.作者: esthetician 時(shí)間: 2025-3-27 14:41
A Study on the Reliability of Two Discourse Segmentation Modelsucturing discourse in European Portuguese. We compared the models of (.) and (.) using spontaneous speech. The latter displayed a higher level of consensus among coders. We also observed that listening to the original speech influenced the level of agreement among coders.作者: 負(fù)擔(dān) 時(shí)間: 2025-3-27 19:00 作者: capillaries 時(shí)間: 2025-3-28 00:34 作者: 怎樣才咆哮 時(shí)間: 2025-3-28 02:18
Nari Sivanandam Arunraj,Diane Ahrenspeech spectrum. This algorithm was implemented over a baseline spectral normalisation method, which purpose is to emphasize the robustness in the regions of less energy of the speech spectrum, since in these regions the noise is more dominant.作者: 灰姑娘 時(shí)間: 2025-3-28 09:49
https://doi.org/10.1007/978-3-8349-3928-9acoustic features used in this procedure, it can perform poorly when applied to continuous speech utterances. In this paper we propose a new method to select the best features to use in the alignment procedure for each pair of phonetic segment classes. The results show that this selection considerably reduces the segment boundary location errors.作者: Expand 時(shí)間: 2025-3-28 13:58
https://doi.org/10.1007/978-3-658-42635-4elines, comments on the dictionary entries, addresses selected problems found in the process of extracting the relevant lexical information form the selected dictionaries, and provides some strategies to overcome them.作者: Malcontent 時(shí)間: 2025-3-28 17:07 作者: nettle 時(shí)間: 2025-3-28 20:07
Dirk Sackmann,Alexandra Rittmannhe use of finite state transducers allowed a very flexible and modular framework for deriving and testing new rule sets. Our experience led us to believe that letter-to-sound modules could be helpful tools for researchers involved in the establishment of orthographic conventions for lesser spoken languages.作者: 膽小鬼 時(shí)間: 2025-3-29 01:36 作者: Adenocarcinoma 時(shí)間: 2025-3-29 04:17 作者: 加花粗鄙人 時(shí)間: 2025-3-29 07:26
Grapheme-Phone Transcription Algorithm for a Brazilian Portuguese TTSesis system. This paper focuses on the grapheme-phone transcription algorithm. A complete set of rules for every grapheme is presented. Experimental results, obtained running the proposed algorithm through a text database, gave rise to 98,43% of accuracy rate.作者: rods366 時(shí)間: 2025-3-29 12:01 作者: progestogen 時(shí)間: 2025-3-29 18:45
A Methodology to Analyze Homographs for a Brazilian Portuguese TTS Systemystem. The reasoning is based on grammatical construction. An algorithm structured on the presented methodology was implemented to solve the reading decision problem for the word . giving rise to 95,0% of accuracy rate when tested on the CETEN-Folha text database.作者: 泄露 時(shí)間: 2025-3-29 20:40 作者: 敏捷 時(shí)間: 2025-3-30 01:09
Experimental Phonetics Contributions to the Portuguese Articulatory Synthesizer Developmentesizer for Portuguese. Examples of analyses and results regarding glottal source parameters and from EMMA and acoustic analyses related to the tongue position are presented. In our studies contextual and regional variation is considered.作者: 凝乳 時(shí)間: 2025-3-30 07:37
Using Adaptive Formalisms to Describe Context-Dependencies in Natural Languaged to syntactical ambiguities and non-determinisms in NL handling we extend it to consider context-dependencies not previously addressed. Although based on the powerful adaptive formalism [.], our method relies on adaptive structured pushdown automata [.] and grammars [.] — resulting simplicity, low-cost and efficiency.作者: 倔強(qiáng)不能 時(shí)間: 2025-3-30 09:13 作者: Stable-Angina 時(shí)間: 2025-3-30 13:29 作者: AXIOM 時(shí)間: 2025-3-30 19:54 作者: BOLT 時(shí)間: 2025-3-31 00:04
Computational Processing of the Portuguese Language978-3-540-45011-5Series ISSN 0302-9743 Series E-ISSN 1611-3349 作者: 行業(yè) 時(shí)間: 2025-3-31 03:38 作者: amyloid 時(shí)間: 2025-3-31 06:43 作者: 投票 時(shí)間: 2025-3-31 09:11 作者: 爵士樂 時(shí)間: 2025-3-31 14:19
Ramona Niederschweiberer,Florian C. Kleemannystem. The reasoning is based on grammatical construction. An algorithm structured on the presented methodology was implemented to solve the reading decision problem for the word . giving rise to 95,0% of accuracy rate when tested on the CETEN-Folha text database.作者: Abominate 時(shí)間: 2025-3-31 20:11 作者: inventory 時(shí)間: 2025-4-1 00:24
Janosch Brinker,Hans-Dietrich Haasisesizer for Portuguese. Examples of analyses and results regarding glottal source parameters and from EMMA and acoustic analyses related to the tongue position are presented. In our studies contextual and regional variation is considered.作者: 同謀 時(shí)間: 2025-4-1 01:56
Jakob Keller,Kristin Laub,Rainer Laschd to syntactical ambiguities and non-determinisms in NL handling we extend it to consider context-dependencies not previously addressed. Although based on the powerful adaptive formalism [.], our method relies on adaptive structured pushdown automata [.] and grammars [.] — resulting simplicity, low-cost and efficiency.作者: 橫截,橫斷 時(shí)間: 2025-4-1 08:28 作者: 令人作嘔 時(shí)間: 2025-4-1 12:11 作者: 詞匯 時(shí)間: 2025-4-1 17:26 作者: Facilities 時(shí)間: 2025-4-1 22:12 作者: CRASS 時(shí)間: 2025-4-1 22:41
https://doi.org/10.1007/3-540-45011-4Portuguese language; Syntax; algorithms; corpus; dialogue; discourse; indexing; information extraction; mach作者: 倒轉(zhuǎn) 時(shí)間: 2025-4-2 06:15 作者: 駁船 時(shí)間: 2025-4-2 07:23
Michael Westerburg,Christoph Bodetio of variances of the laryngograph signal during the VF transition and during the fricative) were used to classify the examples into two or three categories. The results of the automatic and manual measures of devoicing are compared, and an explanation for observed misclassifications is presented.
