Mostrando 9 resultados de: 9
Filtros aplicados
Publisher
Communications in Computer and Information Science(2)
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings(2)
4th International Conference, IberSPEECH 2018(1)
IEEE Latin America Transactions(1)
Lecture Notes in Electrical Engineering(1)
Área temáticas
Lengua(5)
Lingüística(4)
Programación informática, programas, datos, seguridad(3)
Lenguajes de señas(2)
Funcionamiento de bibliotecas y archivos(1)
Extended phone log-likelihood ratio features and acoustic-based i-vectors for language recognition
Conference ObjectAbstract: This paper presents new techniques with relevant improvements added to the primary system presentedPalabras claves:Dimensionality reduction, Phone Log-Likelihood Ratios, SDCAutores:Christian Salamea-Palacios, D'Haro L.F., De Córdoba R., Echeverry J.D.Fuentes:googlescopusFactors that Affect i-Vectors Based Language Identification Systems
Conference ObjectAbstract: The performance of a language identification (LID) system that uses i-vectors as features depends onPalabras claves:DATA, i-Vector, Language IdentificationAutores:Christian Salamea-Palacios, David Romero, Erick Narvaez, Fernando ChicaFuentes:scopusIncorporation of Language Discriminative Information into Recurrent Neural Networks Models to LID Tasks
Conference ObjectAbstract: Language Identification (LID) is an essential research topic in the Automatic Recognition Speech arePalabras claves:Automatic Recognition Speech, Language discriminative information, Language Identification, Recurrent neural networksAutores:Christian Salamea-Palacios, David Romero, De Córdoba R., D’Haro L.Fuentes:scopusIncorporation of discriminative n-grams to improve a phonotactic language recognizer based on i-vectors
ArticleAbstract: This paper describes a novel technique that allows the combination of the information from two diffePalabras claves:Discriminate rankings, i-Vectors, N-grams, Phonotactic, PosteriorgramAutores:Caraballo M.A., Christian Salamea-Palacios, D'Haro L.F., De Córdoba R.Fuentes:googlescopusLanguage recognition using neural phone embeddings and RNNLMs
ArticleAbstract: New advances in Language Identification (LID) using Recurrent Neural Networks (RNNs) and Neural EmbePalabras claves:Language recognition, Neural Embedding, Phone-grams, Phonotactic approach, Recurrent Neural NetworkAutores:Christian Salamea-Palacios, D'Haro L.F., De Córdoba R.Fuentes:googlescopusOn the Use of Phonotactic Vector Representations with FastText for Language Identification
Conference ObjectAbstract: This paper explores a better way to learn word vector representations for language identification (LPalabras claves:Autores:Christian Salamea-Palacios, David RomeroFuentes:scopusOn the use of Phone-based Embeddings for Language Recognition
Conference ObjectAbstract: Language Identification (LID) can be defined as the process of automatically identifying the languagPalabras claves:Language Identification, neural embeddings, PhonotacticAutores:Christian Salamea-Palacios, D'Haro L.F., De Córdoba R., Ferreiros J., Segundo R.S.Fuentes:googlescopusOn the use of phone-gram units in recurrent neural networks for language identification
Conference ObjectAbstract: In this paper we present our results on using RNN-based LM scores trained on different phone-gram orPalabras claves:Autores:Christian Salamea-Palacios, D'Haro L.F., De Córdoba R., San-Segundo R.Fuentes:googlescopusPHONOTACTIC LANGUAGE RECOGNITION USING A UNIVERSAL PHONEME RECOGNIZER AND A TRANSFORMER ARCHITECTURE
Conference ObjectAbstract: In this paper, we describe a phonotactic language recognition model that effectively manages long anPalabras claves:acoustic systems, Language recognition, phonotactic information, TRANSFORMERSAutores:Christian Salamea-Palacios, D'Haro L.F., David Romero, Estecha-Garitagoitia M.Fuentes:scopus