Research on continuous speech recognition with small vocabulary based on biomimetic pattern recognition

Based on biomimetic pattern recognition theory, we proposed a novel speaker-independent continuous speech keyword-spotting algorithm. Without endpoint detection and division, we can get the minimum distance curve between continuous speech samples and every keyword-training net through the dynamic searching to the feature-extracted continuous speech. Then we can count the number of the keywords by investigating the vale-value and the numbers of the vales in the curve. Experiments of small vocabulary continuous speech with various speaking rate have got good recognition results and proved the validity of the algorithm.

The sacred edict; with a translation of the colloquial rendering, notes and vocabulary, by F. W. Baller. Prepared for the use of junior members of the China Inland Mission.

http://www.archive.org/details/thesacrededict01kanguoft

[Book reviews] Review of J. E. Hoch, Semitic Words in Egyptian Texts of the New Kingdom and Third Intermediate Period and D. Sivan and Z. Cochavi-Rainey, West Semitic Vocabulary in Egyptian Script of the 14th to the 10th Centuries BCE

Reviews of: [1] James E. Hoch, Semitic Words in Egyptian Texts of the New Kingdom and Third Intermediate Period, (1994), Princeton University Press. [2] Daniel Sivan and Zipora Cochavi-Rainey, West Semitic Vocabulary in Egyptian Script of the 14th to the 10th Centuries BCE, (1992), Ben-Gurion University of the Negev Press.

FPGA Implementation of a Pipelined Gaussian Calculation for HMM-Based Large Vocabulary Speech Recognition

A scalable large vocabulary, speaker independent speech recognition system is being developed using Hidden Markov Models (HMMs) for acoustic modeling and a Weighted Finite State Transducer (WFST) to compile sentence, word, and phoneme models. The system comprises a software backend search and an FPGA-based Gaussian calculation which are covered here. In this paper, we present an efficient pipelined design implemented both as an embedded peripheral and as a scalable, parallel hardware accelerator. Both architectures have been implemented on an Alpha Data XRC-5T1, reconfigurable computer housing a Virtex 5 SX95T FPGA. The core has been tested and is capable of calculating a full set of Gaussian results from 3825 acoustic models in 9.03 ms which coupled with a backend search of 5000 words has provided an accuracy of over 80%. Parallel implementations have been designed with up to 32 cores and have been successfully implemented with a clock frequency of 133?MHz.

Grounding human vocabulary in robot perception through interaction

This thesis addresses the problem of word learning in computational agents. The motivation behind this work lies in the need to support language-based communication between service robots and their human users, as well as grounded reasoning using symbols relevant for the assigned tasks. The research focuses on the problem of grounding human vocabulary in robotic agent’s sensori-motor perception. Words have to be grounded in bodily experiences, which emphasizes the role of appropriate embodiments. On the other hand, language is a cultural product created and acquired through social interactions. This emphasizes the role of society as a source of linguistic input. Taking these aspects into account, an experimental scenario is set up where a human instructor teaches a robotic agent the names of the objects present in a visually shared environment. The agent grounds the names of these objects in visual perception. Word learning is an open-ended problem. Therefore, the learning architecture of the agent will have to be able to acquire words and categories in an openended manner. In this work, four learning architectures were designed that can be used by robotic agents for long-term and open-ended word and category acquisition. The learning methods used in these architectures are designed for incrementally scaling-up to larger sets of words and categories. A novel experimental evaluation methodology, that takes into account the openended nature of word learning, is proposed and applied. This methodology is based on the realization that a robot’s vocabulary will be limited by its discriminatory capacity which, in turn, depends on its sensors and perceptual capabilities. An extensive set of systematic experiments, in multiple experimental settings, was carried out to thoroughly evaluate the described learning approaches. The results indicate that all approaches were able to incrementally acquire new words and categories. Although some of the approaches could not scale-up to larger vocabularies, one approach was shown to learn up to 293 categories, with potential for learning many more.

Robust handling of out-of-vocabulary words in deep language processing

Tese de doutoramento, Informática (Ciências da Computação), Universidade de Lisboa, Faculdade de Ciências, 2014

Technical Vocabulary and Medieval Text Types: A Semantic Field Approach

This paper seeks to discover in what sense we can classify vocabulary items as technical terms in the later medieval period. In order to arrive at a principled categorization of technicality, distribution is taken as a diagnostic factor: vocabulary shared across the widest range of text types may be assumed to be both prototypical for the semantic field, but also the most general and therefore least technical terms since lexical items derive at least part of their meaning from context, a wider range of contexts implying a wider range of senses. A further way of addressing the question of technicality is tested through the classification of the lexis into semantic hierarchies: in the terms of componential analysis, having more components of meaning puts a term lower in the semantic hierarchy and flags it as having a greater specificity of sense, and thus as more technical. The various text types are interrogated through comparison of the number of levels in their hierarchies and number of lexical items at each level within the hierarchies. Focusing on the vocabulary of a single semantic field, DRESS AND TEXTILES, this paper investigates how four medieval text types (wills, sumptuary laws, petitions, and romances) employ technical terminology in the establishment of the conventions of their genres.

The effect of context on the acquisition of vocabulary in good and poor readers

This study examined the effectiveness of context on the acquisition of new vocabulary for good and poor readers. Twentyeight Grade Three children, fourteen good readers and fourteen poor readers, took part in a word-learning task within three conditions: (1) strong sentence context, (2) weak sentence context, and (3) list condition. The primary hypothesis was that poor readers would show less learning in the list condition than good readers and that there would be no difference in the amount of learning in the sentence conditions. Results revealed that: (a) Words are read faster in sentence contexts than in 1 ist contexts; (b) more learning or greater improvement in performance occurs in list contexts and weak sentence contexts as opposed to strong sentence contexts; and (c) that most of these differences can be attributed to the build-up of meaning in sentences. Results indicated that good and poor readers learned more about words in all three condi tions. More learning and greater performance occurred in the list condition as opposed to the two sentence conditions for both subject groups. However, the poor readers learned significantly more about words in both the list condition and the weak sentence condition than the good readers.

The generation effect and word learning: a test of the effect of the language experience approach versus the text approach in the acquisition of new reading vocabulary

A class of twenty-two grade one children was tested to determine their reading levels using the Stanford Diagnostic Reading Achievement Test. Based on these results and teacher input the students were paired according to reading ability. The students ages ranged from six years four months to seven years four months at the commencement of the study. Eleven children were assigned to the language experience group and their partners became the text group. Each member of the language experience group generated a list of eight to be learned words. The treatment consisted of exposing the student to a given word three times per session for ten sessions, over a period of five days. The dependent variables consisted of word identification speed, word identification accuracy, and word recognition accuracy. Each member of the text group followed the same procedure using his/her partner's list of words. Upon completion of this training, the entire process was repeated with members of the text group from the first part becoming members of the language experience group and vice versa. The results suggest that generally speaking language experience words are identified faster than text words but that there is no difference in the rate at which these words are learned. Language experience words may be identified faster because the auditory-semantic information is more readily available in them than in text words. The rate of learning in both types of words, however, may be dictated by the orthography of the to be learned word.

The influence on children of the purpose of experiencing reading vocabulary: encoding-retrieval interactions in word perception

This research looked at conditions which result in the development of integrated letter code information in the acquisition of reading vocabulary. Thirty grade three children of normal reading ability acquired new reading words in a Meaning Assigned task and a Letter Comparison task, and worked to increase skill for known reading words in a Copy task. The children were then assessed on their ability to identify the letters in these words. During the test each stimulus word for each child was exposed for 100 msec., after which each child reported as many of his or her letters as he or she could. Familiar words, new words, and a single letter identification task served as within subject controls. Following this, subjects were assessed for word meaning recall of the Meaning Assigned words and word reading times for words in all condi tions • The resul ts supported an episodic model of word recognition in which the overlap between the processing operations employed in encoding a word and those required when decoding it affected decoding performance. In particular, the Meaning Assigned and Copy tasks. appeared to facilitate letter code accessibility and integration in new and familiar words respectively. Performance in the Letter Comparison task, on the other hand, suggested that subjects can process the elements of a new word without integrating them into its lexical structure. It was concluded that these results favour an episodic model of word recognition.

From Word Embeddings to Large Vocabulary Neural Machine Translation

Dans ce mémoire, nous examinons certaines propriétés des représentations distribuées de mots et nous proposons une technique pour élargir le vocabulaire des systèmes de traduction automatique neurale. En premier lieu, nous considérons un problème de résolution d'analogies bien connu et examinons l'effet de poids adaptés à la position, le choix de la fonction de combinaison et l'impact de l'apprentissage supervisé. Nous enchaînons en montrant que des représentations distribuées simples basées sur la traduction peuvent atteindre ou dépasser l'état de l'art sur le test de détection de synonymes TOEFL et sur le récent étalon-or SimLex-999. Finalament, motivé par d'impressionnants résultats obtenus avec des représentations distribuées issues de systèmes de traduction neurale à petit vocabulaire (30 000 mots), nous présentons une approche compatible à l'utilisation de cartes graphiques pour augmenter la taille du vocabulaire par plus d'un ordre de magnitude. Bien qu'originalement développée seulement pour obtenir les représentations distribuées, nous montrons que cette technique fonctionne plutôt bien sur des tâches de traduction, en particulier de l'anglais vers le français (WMT'14).