International audienceDeveloping high-quality transcription systems for very large vocabulary corpora is a challenging task. Proper names are usually key to understanding the information contained in a document. One approach for increasing the vocabulary coverage of a speech transcription system is to automatically retrieve new proper names from contemporary diachronic text documents. In recent years, neural networks have been successfully applied to a variety of speech recognition tasks. In this paper, we investigate whether neural networks can enhance word representation in vector space for the vocabulary extension of a speech recognition system. This is achieved by using high-quality word vector representation of words from large amounts...
We investigate whether word embeddings using deep neural networks can assist in the analysis of text...
International audienceMany Proper Names (PNs) are Out-Of-Vocabulary (OOV) words for speech recogniti...
Vector based word representation models are often developed from very large corpora. However, we oft...
International audienceThe problem of out-of-vocabulary words, more precisely proper names retrieval ...
International audienceDeveloping high-quality transcription systems for very large vocabulary corpor...
International audienceThis paper deals with the problem of high-quality transcription systems for ve...
International audienceProper names are usually keys to understand the information contained in a doc...
International audienceProper names are usually key to understanding the information contained in a d...
International audienceProper name recognition is a challenging task in information retrieval in larg...
International audienceThe diachronic nature of broadcast news data leads to the problem of Out-Of-Vo...
International audienceDespite recent progress in developing Large Vocabulary Continuous Speech Recog...
International audienceProper name recognition is a challenging task in information retrieval from la...
The diachronic nature of broadcast news causes frequent variations in the linguisticcontent and voca...
We propose two novel model architectures for computing continuous vector representations of words fr...
International audienceThis paper introduces a new approach based on neural networks for selecting th...
We investigate whether word embeddings using deep neural networks can assist in the analysis of text...
International audienceMany Proper Names (PNs) are Out-Of-Vocabulary (OOV) words for speech recogniti...
Vector based word representation models are often developed from very large corpora. However, we oft...
International audienceThe problem of out-of-vocabulary words, more precisely proper names retrieval ...
International audienceDeveloping high-quality transcription systems for very large vocabulary corpor...
International audienceThis paper deals with the problem of high-quality transcription systems for ve...
International audienceProper names are usually keys to understand the information contained in a doc...
International audienceProper names are usually key to understanding the information contained in a d...
International audienceProper name recognition is a challenging task in information retrieval in larg...
International audienceThe diachronic nature of broadcast news data leads to the problem of Out-Of-Vo...
International audienceDespite recent progress in developing Large Vocabulary Continuous Speech Recog...
International audienceProper name recognition is a challenging task in information retrieval from la...
The diachronic nature of broadcast news causes frequent variations in the linguisticcontent and voca...
We propose two novel model architectures for computing continuous vector representations of words fr...
International audienceThis paper introduces a new approach based on neural networks for selecting th...
We investigate whether word embeddings using deep neural networks can assist in the analysis of text...
International audienceMany Proper Names (PNs) are Out-Of-Vocabulary (OOV) words for speech recogniti...
Vector based word representation models are often developed from very large corpora. However, we oft...