{"title":"Linear interpolation of spectrotemporal excitation pattern representations for automatic speech recognition in the presence of noise","authors":"Adriana Stan","doi":"10.1109/SPED.2009.5156188","DOIUrl":"https://doi.org/10.1109/SPED.2009.5156188","url":null,"abstract":"This article is based on the study of new methods to improve recognition capabilities of automatic speech recognition in the presence of noise systems. Instead of trying to modify complex recognition models, the study is aimed at enhancing the input data's reliability. This is achieved through processing of the acoustic representations of speech. One of these representations, called SpectroTemporal Excitation Pattern (STEP) is used in recognition systems with missing or unreliable data. One of the ideas behind this study was to increase the glimpsing areas in the STEP representations. And, because the glimpsing algorithm requires previous knowledge of the noise, another idea was to estimate noise characteristics, and base the glimpsing areas determination on these estimations. Preliminary tests were conducted with an HMM recognition system, but this will be the object of a future study.","PeriodicalId":259478,"journal":{"name":"2009 Proceedings of the 5-th Conference on Speech Technology and Human-Computer Dialogue","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122604233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A prosodic control module for a Romanian TtS system, based on melodic contour dictionaries","authors":"D. Jitca, V. Apopei","doi":"10.1109/SPED.2009.5156176","DOIUrl":"https://doi.org/10.1109/SPED.2009.5156176","url":null,"abstract":"This paper presents a prosodic control module implementation for a Romanian TtS system based on the F0 contour generation as a sequence of functional elementary melodic contours. The accentual units (AUs) are considered as elementary melodic contours because they contain elementary tonal contrasts to which labels with discourse signification may be assigned. Based on this idea, a set of AU F0 pattern categories was defined after performing an analysis over a Romanian speech corpus. The dictionary containing the parametric descriptions of the AU F0 pattern types in all possible lexical and phonetic contexts is an important resource in the prosodic control module. Another important resource is the dictionary containing the functional descriptions of the partial melodic contours at different intonational phrase (IP) or AU group (AUG) levels. After the intonational model and the label set presentation, we exemplify how our intonational description can be used to annotate the F0 contour. In the next section, the processing steps of the prosodic control module is presented.","PeriodicalId":259478,"journal":{"name":"2009 Proceedings of the 5-th Conference on Speech Technology and Human-Computer Dialogue","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121923691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Automatic rule-based syllabication for Romanian","authors":"Stefan-Adrian Toma, Eugeniu Oancea, D. Munteanu","doi":"10.1109/SPED.2009.5156177","DOIUrl":"https://doi.org/10.1109/SPED.2009.5156177","url":null,"abstract":"The syllable is a speech synthesis unit that is successfully used in high quality speech synthesis systems. In support of a syllable based speech synthesis system, we consider necessary the realization of an algorithm for automatic syllabication. In this paper we present an algorithm for automatic syllabication. The algorithm starts by making the phonetic transcription of the word using a previously developed method which employs a set of phonetic rules represented through a XML scheme. Then it applies a set of rules for syllabication. The system obtained a 10.5% word error rate for syllabication and 4.79% word error rate for phonetic transcription using rules.","PeriodicalId":259478,"journal":{"name":"2009 Proceedings of the 5-th Conference on Speech Technology and Human-Computer Dialogue","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131970888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Discourse theories vs. Topic-Focus articulation applied to prosodic focus assignment in Romanian","authors":"N. Curteanu, Diana Trandabat, M. Moruz","doi":"10.1109/SPED.2009.5156182","DOIUrl":"https://doi.org/10.1109/SPED.2009.5156182","url":null,"abstract":"“…it is not the argument structure that triggers the intonational phrasing, but the [discourse, subclausal n.b.] relation of backgrounding.” (K. von Heusinger, 2007) Is it? If yes, how? The present paper, maintaining our attempts for applying Prague School's Topic-Focus Articulation (TFA) algorithm on the syntax-prosody interface of Romanian, proposes two comparative lines of investigation for the intonational focus assignment: (A) The TFA algorithm is improved at clause level with hints from Gussenhoven's SAAR (Sentence Accent Assignment Rule), then extended to inter-clause level, i.e. complex sentences. The new shape of the TFA algorithm is applied to compute the Topic-Focus values in the discursive context, while the information-structural (IS) spans of Theme(s)-Rheme(s) are detached, at clause level, as lowest-highest degrees of Communicative Dynamism (CD) vs. Systemic Order (SO). (B) The second approach we experiment for assigning intonational focus and phrasing is based on the combined and intensive use of discourse theories for computing the IS categories and structures: the Background-Kontrast entities (associated with the Prague School's Topic-Focus) are obtained with Asher's (1993) Segmented Discourse Representation Theory (SDRT) analysis, while Theme-Rheme structures within the finite clause are computed with Leong's (2004) Inference-Boundary (IB) algorithm (of Hallidayan inspiration), applied for the first time to Romanian. Furthermore, this second direction is inspired from and joins the IS-discourse theory proposed by Heusinger (2007), which relies on SDRT inter-clausal evolution of discourse variables for computing the Background-Kontrast. While maintaining the classical SDRT (including rhetorical) discourse relations at the inter-clause level, Heusinger introduces a set of IS-semantics relations, and hands down at sub-clause level the rhetorical and focus particle relations with significant role in intonational-prosodic phrasing. Examples of these two types of research are compared to a gold, intonationally annotated set of Romanian sentences, the proposed theoretical and procedural techniques aiming to balance the pessimistic-realistic view on prosody prediction that it is the speaker-presupposition (and hearer-accommodation) which determines the IS focal scopes, rather than the bare text.","PeriodicalId":259478,"journal":{"name":"2009 Proceedings of the 5-th Conference on Speech Technology and Human-Computer Dialogue","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124337020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Text conditioning and statistical language modeling for Romanian language","authors":"J. Domokos, G. Toderean, O. Buza, J. Domokos","doi":"10.1109/SPED.2009.5156184","DOIUrl":"https://doi.org/10.1109/SPED.2009.5156184","url":null,"abstract":"In this paper we present a synthesis of the theoretical fundamentals and some practical aspects of statistical (n-gram) language modeling which is a main part of a large vocabulary statistical speech recognition system. There are presented the unigram, bigram and trigram language models as well as the Good-Turing estimator based Katz back-off smoothing algorithm. There is also described the perplexity measure of a language model used for evaluation. The practical experiments were made on Romanian Constitution corpus. There are also presented the text normalization steps before the language model generation. The results are ARPA-MIT format language models for Romanian language. The models were tested and compared using perplexity measure. Finally some comparisons were made between Romanian and English language modeling and conclusions are drawn.","PeriodicalId":259478,"journal":{"name":"2009 Proceedings of the 5-th Conference on Speech Technology and Human-Computer Dialogue","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131655381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Dynamic relationship management for personality rich character presentations in interactive games","authors":"M. Mehta, Kinshuk Mishra, A. Corradini","doi":"10.1109/SPED.2009.5156181","DOIUrl":"https://doi.org/10.1109/SPED.2009.5156181","url":null,"abstract":"The generation of realistic behaviors is paramount to the believability of characters within an interactive computer game. The ideal way to reach the goal is to endow the characters populating the virtual graphical world with the capability of generating human-like behaviors and shape them according to their own personality. In this paper, we focus on non-player characters (NPC) capable of responding appropriately to game activities that helps in increasing game variability, providing a more enjoyable game-play experience. We specifically address the development of techniques that dynamically modify the relationships between players and non-player characters based on ongoing activities during the game. We present a system that models and maintains these relationships and provides methods by which characters can use the current relationship to formulate appropriate reactions in behavior and dialog. In this way, characters become gradually more effective as they learn and adapt to the user's interests, habits and preferences. To modify the interpersonal relationships between characters and the player, the system tries to tailor the characters' approach to dialog with the player based on different game events, goals, existing interpersonal relationships, and the kind of verbal exchange.","PeriodicalId":259478,"journal":{"name":"2009 Proceedings of the 5-th Conference on Speech Technology and Human-Computer Dialogue","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124941036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Michel Vacher, Noe Guirand, J. Serignat, A. Fleury, N. Noury
{"title":"Speech recognition in a smart home: Some experiments for telemonitoring","authors":"Michel Vacher, Noe Guirand, J. Serignat, A. Fleury, N. Noury","doi":"10.1109/SPED.2009.5156185","DOIUrl":"https://doi.org/10.1109/SPED.2009.5156185","url":null,"abstract":"Because of the aging of the population, low-cost solutions are required to help people with loss of autonomy staying at home rather than in public health centers. One solution is to assist human operators with smart information systems. In this case, position and physiologic sensors already give important information, but there are few studies about the utility of sound in patient's habitation. However, sound classification and speech recognition may greatly increase the versatility of such a system: this will be provided by detecting short sentences or words that could characterize a distress situation for the patient. Moreover, analysis and classification of sounds emitted in patient's habitation may be useful for patient's activity monitoring. In this paper, we present a global speech and sound recognition system that can be set-up in a flat. Eight microphones were placed in the Health Smart Home of Grenoble (named HIS, a real living flat of 47m2) to automatically analyze and classify different sounds and speech utterances (e.g.: normal or distress French sentences). Sounds are clustered in eight classes but this aspect is not discussed in this paper. For speech signals, an input utterance is recognized and a subsequent process classifies it in normal or distress, by analysing the presence of distress keywords. An experimental protocol was defined and then this system has been evaluated in uncontrolled conditions in which heterogeneous speakers were asked to utter predetermined sentences in the HIS. The results of this experiment, where ten subjects were involved, are presented. The Global Error Rate was 15.6%. Moreover, noise suppression techniques were incorporated in the speech and sound recognition system in order to suppress the noise emitted by known sources like TV or radio. An experimental protocol was defined and tested by four speakers in real conditions inside a room. Finally, we discuss the results of this experiment as a function of the noise source: speech or music.","PeriodicalId":259478,"journal":{"name":"2009 Proceedings of the 5-th Conference on Speech Technology and Human-Computer Dialogue","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131671832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mihai Surmei, D. Burileanu, C. Negrescu, Catalin Ungurean, A. Dervis
{"title":"Real-time architectures for a network-based text-to-speech service implementation","authors":"Mihai Surmei, D. Burileanu, C. Negrescu, Catalin Ungurean, A. Dervis","doi":"10.1109/SPED.2009.5156178","DOIUrl":"https://doi.org/10.1109/SPED.2009.5156178","url":null,"abstract":"The communication as we know it is about to change, the simple peer-to-peer voice type of calls being replaced by a mix of different media belonging to the same session. Network-based speech processing technologies are increasingly used, adding flexibility, speed and naturalness to various telecom services. For instance, text-to-speech (TTS) synthesis is already incorporated into commercial telephony applications, but in most of the cases the services offered are not real-time. This paper proposes a solution in building up a network-based media processing environment and designing a multi-threaded and multi-process TTS engine, integrated with the rest of the network by means of flexible and standardized signaling protocols. As a particular application of the proposed approach, we present a convergent real-time telecom service, combining instant messaging, presence and TTS in a single new experience.","PeriodicalId":259478,"journal":{"name":"2009 Proceedings of the 5-th Conference on Speech Technology and Human-Computer Dialogue","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124025767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
C. Paleologu, J. Benesty, S. Ciochină, C. Vladeanu
{"title":"Practical variable step-size adaptive algorithms for echo cancellation","authors":"C. Paleologu, J. Benesty, S. Ciochină, C. Vladeanu","doi":"10.1109/SPED.2009.5156186","DOIUrl":"https://doi.org/10.1109/SPED.2009.5156186","url":null,"abstract":"The most common algorithms used for echo cancellation are the normalized least-mean-square (NLMS) and the affine projection (AP). The classical versions of these algorithms use a constant step-size parameter and need to establish a tradeoff between several performance criteria e.g., high convergence rate versus low misadjustment. In this paper, we present a class of variable step-size NLMS and AP algorithms, which are designed to recover the near-end signal from the error of the adaptive filter. The simulation results indicate a robust behavior of these algorithms against the presence of the near-end signal.","PeriodicalId":259478,"journal":{"name":"2009 Proceedings of the 5-th Conference on Speech Technology and Human-Computer Dialogue","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125865468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Ciobanu, C. Negrescu, D. Stanomir, D. Burileanu
{"title":"Time-frequency processing of partials for high-quality speech synthesis","authors":"A. Ciobanu, C. Negrescu, D. Stanomir, D. Burileanu","doi":"10.1109/SPED.2009.5156175","DOIUrl":"https://doi.org/10.1109/SPED.2009.5156175","url":null,"abstract":"Based on the particularities offered by the chosen signal model, we introduce a novel approach regarding the chain of actions pursued in the analysis stage of the speech signal, which succeeds the level of partial extraction. According to the Harmonic plus Noise Model (HNM) a number of successive estimation and synthesis operations are performed. The present paper proposes a method to enhance the harmonic parameters estimation. This new algorithm proves to have good behavior offering support in selecting an appropriate subset of partials. In addition to reducing the arithmetic complexity of the harmonic synthesis (which is known to be the most resource consuming module), this optimized selection of the partials allows us to perform a specific frequency correction, which enables the possibility of a simple and coherent future pitch manipulation. The performed experiments confirmed the expected complexity reduction. Moreover, we applied the proposed algorithm for partial selection and tracking followed by a frequency aligning of the harmonic components. The reconstructed signal compared to the original speech proved to be a perceptually indistinguishable replica.","PeriodicalId":259478,"journal":{"name":"2009 Proceedings of the 5-th Conference on Speech Technology and Human-Computer Dialogue","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131842671","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}