Envíos recientes

  • A neural network approach for automatic detection of acoustic alarms 

    Peiró Lilja, Alexandre; Raboshchuk, Ganna; Nadeu Camprubí, Climent (Scitepress, 2017)
    Comunicación de congreso
    Acceso restringido por política de la editorial
    Acoustic alarms generated by biomedical equipment are relevant sounds in the noisy Neonatal Intensive Care Unit (NICU) environment both because of their high frequency of occurrence and their possible negative effects on ...
  • Non parametric coding of speech by means of a MLP with hints 

    Hernández, G; Monte Moreno, Enrique; Mariño Acebal, José Bernardo (Springer, 1997)
    Texto en actas de congreso
    Acceso restringido por política de la editorial
    This paper presents a non parametric compression system which makes use of the fact that a MLP has an internal representation of the data in the hidden layer. The system that we present makes a compression by using 4 or 8 ...
  • LSTM neural network-based speaker segmentation using acoustic and language modelling 

    India Massana, Miquel Àngel; Rodríguez Fonollosa, José Adrián; Hernando Pericás, Francisco Javier (International Speech Communication Association (ISCA), 2017)
    Comunicación de congreso
    Acceso abierto
    This paper presents a new speaker change detection system based on Long Short-Term Memory (LSTM) neural networks using acoustic data and linguistic content. Language modelling is combined with two different ...
  • The TALP-UPC neural machine translation system for german/finnish-english using the inverse direction model in rescoring 

    Escolano, Carlos; Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (2017)
    Comunicación de congreso
    Acceso restringido por política de la editorial
    In this paper, we describe the TALP- UPC participation in the News Task for German-English and Finish-English. Our primary submission implements a fully character to character neural machine translation architecture with ...
  • Towards large scale multimedia indexing: a case study on person discovery in broadcast news 

    Le, Nam; Bredin, Herve; Sergent, Gabriel; India Massana, Miquel Àngel; López-Otero, Paula; Barras, Claude; Guinaudeau, Camille; Gravier, Guillaume; Barbosa da Fonseca, Gabriel; Lyon Freire, Izabela; Patrocinio Jr., Zenilton; Jamil F. Guimarães, Silvio; Martí Juan, Gerard; Morros Rubió, Josep Ramon; Hernando Pericás, Francisco Javier; Docio-Fernández, Laura; García-Mateo, Carmen; Meignier, Sylvain; Odobez, Jean-Marc (Association for Computing Machinery (ACM), 2017)
    Texto en actas de congreso
    Acceso restringido por política de la editorial
    The rapid growth of multimedia databases and the human interest in their peers make indices representing the location and identity of people in audio-visual documents essential for searching archives. Person discovery ...
  • Spanish dialects: phonetic transcription 

    Moreno Bilbao, M. Asunción; Mariño Acebal, José Bernardo (International Speech Communication Association (ISCA), 1998)
    Texto en actas de congreso
    Acceso abierto
    It is well known that canonical Spanish, the dialectal variant `central' of Spain, so called Castilian, can be transcribed by rules. This paper deals with the automatic grapheme to phoneme transcription rules in several ...
  • A billingual texto-to-speech system in spanish and catalan 

    Bonafonte Cávez, Antonio; Esquerra Llucià, Ignasi; Febrer Godayol, Albert; Vallverdú Bayés, Sisco (Editors: G. Kokkinakis, N. Fakotakis, E. Dermatas; Editorial: WCL, University of Patras, Grece, 1997)
    Texto en actas de congreso
    Acceso abierto
    This paper summarises the text-to-speech system that has been developed during the last years in the Speech Group of the Universitat Politccnica de Catalunya (UPC). The paper emphasises the parts of the system which are ...
  • Two level continuous speech recognition using demisyllable-based HMM word spotting 

    Lleida Solano, Eduardo; Mariño Acebal, José Bernardo; Nadeu Camprubí, Climent; Oliveras Vergés, Albert (1991)
    Texto en actas de congreso
    Acceso abierto
    This paper describes a two level Spanish Continuous Speech Recognition System based on Demisyllable HMM modelling, word-spotting and finite-state lexical and syntactic knowledge. The first level, the word level, is based ...
  • Character-level intra attention networks for natural language inference 

    Yang, Han; Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (2017)
    Comunicación de congreso
    Acceso abierto
    Natural language inference (NLI) is a central problem in language understand- ing. End-to-end artificial neural networks have reached state-of-the-art performance in NLI field recently. In this paper, we propose Character- ...
  • Parametric modeling of PDF using a convolution of one-sided exponentials: application to HMM 

    Vidal Manzano, José; Bonafonte Cávez, Antonio; Rodríguez Fonollosa, José Adrián (European Association for Signal Processing (EURASIP), 1994)
    Texto en actas de congreso
    Acceso abierto
  • Predicción no lineal de voz mediante redes neuronales 

    Faúndez Zanuy, Marcos; Monte Moreno, Enrique (1996)
    Texto en actas de congreso
    Acceso abierto
  • Predicción no lineal de la voz mediante redes neuronales 

    Faundez, Marcos; Monte Moreno, Enrique (1996)
    Texto en actas de congreso
    Acceso abierto

Muestra más