Word boundary modelling and full covariance gaussians for Arabic Speech-to-Text systems

This paper describes recent improvements to the Cambridge Arabic Large Vocabulary Continuous Speech Recognition (LVCSR) Speech-to-Text (STT) system. It is shown that wordboundary context markers provide a powerful method to enhance graphemic systems by implicit phonetic information, improving the modelling capability of graphemic systems. In addition, a robust technique for full covariance Gaussian modelling in the Minimum Phone Error (MPE) training framework is introduced. This reduces the full covariance training to a diagonal covariance training problem, thereby solving related robustness problems. The full system results show that the combined use of these and other techniques within a multi-branch combination framework reduces the Word Error Rate (WER) of the complete system by up to 5.9% relative. Copyright © 2011 ISCA.

IPLR: An online resource for Greek word-level and sublexical information

We present a new online psycholinguistic resource for Greek based on analyses of written corpora combined with text processing technologies developed at the Institute for Language & Speech Processing (ILSP), Greece. The "ILSP PsychoLinguistic Resource" (IPLR) is a freely accessible service via a dedicated web page, at http://speech.ilsp.gr/iplr. IPLR provides analyses of user-submitted letter strings (words and nonwords) as well as frequency tables for important units and conditions such as syllables, bigrams, and neighbors, calculated over two word lists based on printed text corpora and their phonetic transcription. Online tools allow retrieval of words matching user-specified orthographic or phonetic patterns. All results and processing code (in the Python programming language) are freely available for noncommercial educational or research use. © 2010 Springer Science+Business Media B.V.

Discriminative spoken language understanding using word confusion networks

Current commercial dialogue systems typically use hand-crafted grammars for Spoken Language Understanding (SLU) operating on the top one or two hypotheses output by the speech recogniser. These systems are expensive to develop and they suffer from significant degradation in performance when faced with recognition errors. This paper presents a robust method for SLU based on features extracted from the full posterior distribution of recognition hypotheses encoded in the form of word confusion networks. Following [1], the system uses SVM classifiers operating on n-gram features, trained on unaligned input/output pairs. Performance is evaluated on both an off-line corpus and on-line in a live user trial. It is shown that a statistical discriminative approach to SLU operating on the full posterior ASR output distribution can substantially improve performance both in terms of accuracy and overall dialogue reward. Furthermore, additional gains can be obtained by incorporating features from the previous system output. © 2012 IEEE.

Using sub-word-level information for confidence estimation with conditional random field models

The task of word-level confidence estimation (CE) for automatic speech recognition (ASR) systems stands to benefit from the combination of suitably defined input features from multiple information sources. However, the information sources of interest may not necessarily operate at the same level of granularity as the underlying ASR system. The research described here builds on previous work on confidence estimation for ASR systems using features extracted from word-level recognition lattices, by incorporating information at the sub-word level. Furthermore, the use of Conditional Random Fields (CRFs) with hidden states is investigated as a technique to combine information for word-level CE. Performance improvements are shown using the sub-word-level information in linear-chain CRFs with appropriately engineered feature functions, as well as when applying the hidden-state CRF model at the word level.

smoothing document language model with local word graph

ACM SIGIR; ACM SIGWEB

CARPS: A Program which Solves Calculus Word Problems

A program was written to solve calculus word problems. The program, CARPS (CALculus Rate Problem Solver), is restricted to rate problems. The overall plan of the program is similar to Bobrow's STUDENT, the primary difference being the introduction of "structures" as the internal model in CARPS. Structures are stored internally as trees. Each structure is designed to hold the information gathered about one object. A description of CARPS is given by working through two problems, one in great detail. Also included is a critical analysis of STUDENT.

Frequency of word-use predicts rates of lexical evolution throughout Indo-European history

Mark Pagel, Quentin D. Atkinson & Andrew Meade (2007). Frequency of word-use predicts rates of lexical evolution throughout Indo-European history. Nature, 449,717-720. RAE2008

Electronic dictionary entries with animated pictures: Lookup preferences and word retention

http://ijl.oxfordjournals.org/cgi/reprint/ecp022?ijkey=FWAwWPvILuZDT1S&keytype=ref

Life-narrative and word-cued autobiographical memories in centenarians: comparisons with 80-year-old control, depressed, and dementia groups.

Centenarians provided autobiographical memories to either a request for a life narrative or a request to produce autobiographical memories to cue words. Both methods produced distributions with childhood-amnesia, reminiscence-bump, and recency components. The life-narrative method produced relatively more bump memories at the expense of recent memories. The life-narrative distributions were similar to those obtained from 80-year-old adults without clinical symptoms and from 80-year-old Alzheimer's dementia and depression patients, except that the centenarians had an additional 20-year period of relatively low recall between the bump and recency components. The centenarians produced more emotionally neutral memories than the other three groups and produced fewer and less detailed memories than the non-clinical 80-year-old sample.

Properties of word cues for autobiographical memory.

A sample of 124 words were used to cue autobiographical memories in 120 adults varying in age from 20 to 73 years. Individual words reliably cued autobiographical memories of different ages with different speeds. For all age groups, words rated high in imagery produced older memories and faster reaction times.