the concept of "nearness", which has been dealt with as soon as one started studying digital images, finds one of its rigorous forms in the notion of proximity space. It is this notion, together with "n...
详细信息
this paper describes a practical approach to mathematical morphology and ways to implement its operations. the first chapters treat a formalism that has the potential of implementing morphological operations on binary...
详细信息
Visibility partitions play an important role in computer vision and pattern matching. this paper studies a new type of visibility, reflection-visibility, with applications in affine pattern matching: it is used in the...
详细信息
A method is proposed which computes the visible points of surfaces in a 3-dimensional discrete space. the occlusion of surface points of an object by other object points is determined by shooting a discrete ray from e...
详细信息
In this paper, we describe an improved template-based approach to Chinese-to-English Spoken Language Translation (SLT) and present experimental results. the improved template-based translation approach uses flexible e...
详细信息
ISBN:
(纸本)7801501144
In this paper, we describe an improved template-based approach to Chinese-to-English Spoken Language Translation (SLT) and present experimental results. the improved template-based translation approach uses flexible expression format to describe the template condition. the condition of a template may consist of keywords, parts-of-speech and also semantic features, so the input may be matched with a template from shallow level to deep level. In the condition of a template, the distance between two fixed keywords is stretchable, thus some needless words in the input utterances may be skipped in matching operation. And also the translation results of the same template are alterable. the proper results are finally generated according to the specific context. that is, the relation between a template and translated utterance is one-to-n (where, n is an integer and n≥1). the experiments were performed with input of both text transcription and results of speech recognition. the preliminary experimental results have proven the approach is practical.
A robust parsing model for spontaneous Chinese based on semantic constituent spotting and concept assembling model (SCAM) had been successfully developed in our "LOADSTAR• dialog system[1]. It is a travel informa...
详细信息
ISBN:
(纸本)7801501144
A robust parsing model for spontaneous Chinese based on semantic constituent spotting and concept assembling model (SCAM) had been successfully developed in our "LOADSTAR• dialog system[1]. It is a travel information accessing system and the SCAM is rule based. Considering the domain portability, a statistical model for spoken language understanding is adopted. the statistical spoken language understanding model is developed in the domain of hotel reservation. then the statistical model was ported to the domain of travel information accessing within four weeks.
the two or three layered networks 2LNN, 3LNN which originate from stereovision neural network are applied to speech recognition. To accommodate sequential dataflow, we consider a window to which new acoustic data ente...
详细信息
ISBN:
(纸本)7801501144
the two or three layered networks 2LNN, 3LNN which originate from stereovision neural network are applied to speech recognition. To accommodate sequential dataflow, we consider a window to which new acoustic data enter and from which final neural activities are output. Inside the window recurrent neural network develops neural activity toward a stable point. the process is called Winner-Take-All(WTA) with cooperation and competition. the resulting neural activities clearly showed recognition of a continuous speech of a word. the string of phonemes obtained is compared with reference words by using dynamical programming method. the resulting recognition rate amounts to 96.7% for 100 words spoken by 9 male speakers, which is compared to 97.9% by hidden markov model (HMM) withthree states and single gaussian distribution. the present results which are close to those of HMM seem noticeable because the architecture of the neural network is very simple and parameters in the neural net equations are small numbered and always fixed.
In this paper, in order to deal withthe problems of disfluencies in conversational speech, a partial pattern tree (PPT) and a PPT-based statistical language model are proposed. A partial pattern is defined to represe...
详细信息
ISBN:
(纸本)7801501144
In this paper, in order to deal withthe problems of disfluencies in conversational speech, a partial pattern tree (PPT) and a PPT-based statistical language model are proposed. A partial pattern is defined to represent a sub-sentence with a key-phrase and some optional/functional phrases. the PPT is an integrated tree structure of the partial patterns generated from the training sentences and used to model the n-gram and grammatical constraints. In addition, a PPT merging algorithm is also proposed to reduce the number of partial patterns with similar syntactic structure by minimizing an objective cost function. Using the PPT, the undetected/misdetected errors due to disfluencies can be recovered. Finally, a sentence verification approach is proposed to re-rank the recovered sentences generated from the PPT. In order to assess the performance, a faculty name inquiry system with 2583 names has been implemented. the recognition accuracy of the system using the proposed PPT achieved 77.23%. We also contrasted this method with previous conventional approaches to show its superior performance.
this paper describes a Japanese-to-Chinese spoken language translation (SLT) method based on simple expression and presents the experimental results. the method is aimed at developing a compact speech translation syst...
详细信息
ISBN:
(纸本)7801501144
this paper describes a Japanese-to-Chinese spoken language translation (SLT) method based on simple expression and presents the experimental results. the method is aimed at developing a compact speech translation system, which is robust for spontaneous spoken language phenomena, including the recognition errors and different expression from various speakers. T he idea of translation method based on simple expression is that the mechanism interprets speech-act rather than the direct translation of the speaker's words. the method is realized by mapping the simple expression instead of deep parsing. In this method, only keywords in speech recognition results are extracted, and the corresponding target sentences are extracted from the database by selecting similar example sentences withthe keywords. All training sentences in the bilingual corpus are rewritten into the simple expression and grouped by rules. the rules are specially designed to develop the compact size example database for translation. Comparing with other example-based approaches to SLT, the method based on simple expression is easy to realize, and especially it is practical to develop the SLT systems limited in specific domains.
the proceedings contain 43 papers. the special focus in this conference is on Topology and Discrete Images. the topics include: Homotopy in digital spaces;tesselations by connection in orders;a concise characterizatio...
ISBN:
(纸本)3540413960
the proceedings contain 43 papers. the special focus in this conference is on Topology and Discrete Images. the topics include: Homotopy in digital spaces;tesselations by connection in orders;a concise characterization of 3D simple points;digital jordan curve theorems;a new means for investigating 3-manifolds;nearness in digital images and proximity spaces;morphological operators with discrete line segments;hausdorff discretizations of algebraic sets and diophantine sets;an algorithm for reconstructing special lattice sets from their approximate x-rays;a question of digital linear algebra;reconstruction of discrete sets with absorption;some properties of hyperbolic networks;the reconstruction of the digital hyperbola segment from its code;determining visible points in a three-dimensional discrete space;extended reeb graphs for surface understanding and description;an automatic and reversible geometric smoothing of discrete 3D object boundaries;object discretization in higher dimensions;strong thinning and polyhedrization of the surface of a voxel object;deformable modeling for characterizing biomedical shape changes;naive planes as discrete combinatorial surfaces;surface digitizations by dilations which are tunnel-free;delaunay surface reconstruction from scattered points;go digital, go fuzzy and recognition of digital naive planes and polyhedrization.
暂无评论