Previously, we proposed a flexible two-layered speech recogniser architecture, called FLaVoR. In the first layer an unconstrained, task independent phone recogniser generates a phone lattice. Only in the second layer the task specific lexicon and language model are applied to decode the phone lattice and produce a word level recognition result. In this paper, we present a further evaluation of ...

In this paper, we report on the automatic recognition of Japanese broadcast-news speech. We have been working on largevocabulary continuous speech recognition (LVCSR) for Japanese newspaper speech transcription and have achieved good performance. We have recently applied our LVCSR system to transcribing Japanese broadcast-news speech. We extended the vocabulary from 7k words to 20k words and tr...

We have performed heat capacity measurements in magnetic fields to 90 kOe on single crystals of the cubic heavy fermion compound Ce3Co4Sn13. In zero field, there are no signs of long-range magnetic order down to 0.35K. However, C=T increases rapidly below 2K, reaching a very large maximum value of 4 J=mol Ce–K around 0.8K in zero field, and the high-field magnetic entropy approaches R ln 2 at 2...

The aim of this paper is to present the first Amazighe POS tagger. Very few linguistic resources have been developed so far for Amazighe and we believe that the development of a POS tagger tool is the first step needed for automatic text processing. In order to achieve this endeavor, we have trained two sequence classification models using Support Vector Machines (SVMs) and Conditional Random F...

In this paper, we describe a novel two-pass search strategy for large vocabulary continuous speech recognition. The first-pass of this strategy uses a regular time-synchronous beam search with rough models to generate a word lattice. Then, the second-pass search derives exact results from the word lattice using more accurate models. This search is “time-asynchronous shortest-first beam search”,...

Advances in speech technology and computing power have created a surge of interest in the practical application of speech recognition. However, the most accurate speech recognition systems in the research world are still far too slow and expensive to be used in practical, large vocabulary continuous speech applications. Their main goal has been recognition accuracy, with emphasis on acoustic an...

Existing works on 2D pose estimation mainly focus a certain category, e.g. human, animal, and vehicle. However, there are lots of application scenarios that require detecting the poses/keypoints unseen class objects. In this paper, we introduce task Category-Agnostic Pose Estimation (CAPE), which aims to create model capable any object given only few samples with keypoint definition. To achieve...

A planet's surface conditions can significantly impact its climate and habitability. In this study, we use the 3D general circulation model ExoPlaSim to systematically vary dayside land cover on a synchronously rotating, temperate rocky planet under two extreme opposite continent configurations, in which either all of or ocean is centred at substellar point. We identify water vapour sea ice as ...