Method and system for creating frugal speech corpus using internet resources and conventional speech corpus
S Kopparapu, IA Sheikh - US Patent 8,756,064, 2014 - Google Patents
A speech corpus creation method and system are disclosed. The method comprising
identifying a publicly accessible first source of the first speech data and its corresponding …
identifying a publicly accessible first source of the first speech data and its corresponding …
[PDF][PDF] Unsupervised language model adaptation for automatic speech recognition of broadcast news using web 2.0.
We improve the automatic speech recognition of broadcast news using paradigms from Web
2.0 to obtain time-and topicrelevant text data for language modeling. We elaborate an …
2.0 to obtain time-and topicrelevant text data for language modeling. We elaborate an …
Towards the automatic processing of language registers: Semi-supervisedly built corpus and classifier for french
Abstract Language registers are a strongly perceptible characteristic of texts and speeches.
However, they are still poorly studied in natural language processing. In this paper, we …
However, they are still poorly studied in natural language processing. In this paper, we …
Construction conjointe d'un corpus et d'un classifieur pour les registres de langue en français
Les registres de langue sont un trait stylistique marquant dans l'appréciation d'un texte ou
d'un discours. Cependant, il sont encore peu étudiés en traitement automatique des …
d'un discours. Cependant, il sont encore peu étudiés en traitement automatique des …
Adaptation thématique non supervisée d'un système de reconnaissance automatique de la parole
G Lecorvé - 2010 - theses.hal.science
Les systèmes actuels de reconnaissance automatique de la parole (RAP) reposent sur un
modèle de langue (ML) qui les aide à déterminer les hypothèses de transcription les plus …
modèle de langue (ML) qui les aide à déterminer les hypothèses de transcription les plus …
Toward robust information extraction models for multimedia documents
AR Ebadat - 2012 - theses.hal.science
During the last decade, huge amounts of multimedia documents have been generated. It is
therefore important to find a way to manage this data. Every approach to facilitate this …
therefore important to find a way to manage this data. Every approach to facilitate this …
[PDF][PDF] Towards the Automatic Processing of Language Registers: Semi-supervisedly Built Corpus and Classifier for French
Language registers are a strongly perceptible characteristic of texts and speeches.
However, they are still poorly studied in natural language processing. In this paper, we …
However, they are still poorly studied in natural language processing. In this paper, we …
[PDF][PDF] Unsupervised Language Model Adaptation for Automatic Speech Recognition of Broadcast News Using Web 2.0
IT Schultz, L Gren, DIT Schlippe, DINT Vu - csl.uni-bremen.de
We improve the automatic speech recognition of broadcast news using paradigms from Web
2.0 to obtain time-and topic-relevant text data for language modeling. We elaborate an …
2.0 to obtain time-and topic-relevant text data for language modeling. We elaborate an …
Recherche d'information textuelle et phonétique pour le contrôle de l'étiquetage automatique d'émissions dans un flux télévisuel
C Guinaudeau - 4es rencontres des jeunes chercheurs en recherche d' …, 2009 - hal.science
En 2007, Naturel (Naturel, 2007) a proposé un système qui associe automatiquement une
étiquette, c'est-à-dire un titre, à des émissions issues du découpage d'un flux TV …
étiquette, c'est-à-dire un titre, à des émissions issues du découpage d'un flux TV …