Mostrando 6 resultados de: 6
Publisher
Communications in Computer and Information Science(1)
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings(1)
IEEE Latin America Transactions(1)
Odyssey 2016: Speaker and Language Recognition Workshop(1)
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH(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:googlescopusLanguage Recognition using phonotactic-based Shifted Delta Coefficients and multiple phone recognizers
Conference ObjectAbstract: A new language recognition technique based on the application of the philosophy of the Shifted DeltaPalabras claves:Language recognition, Parallel phone recognizers, Phone-log likelihood ratios, SDCAutores:Christian Salamea-Palacios, D'Haro L.F., De Córdoba R., Ferreiros J.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 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:googlescopusIncorporation 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:googlescopus