Cesare Furlanello, Diego Giuliani, Edmondo Trentin  Home/Search
Context Related
| itc.it/pub/n_nets/pape...f_nips94.ps.gz pan.itc.it:8008/doc/f_nips94.ps mpa.itc.it:8008/doc/f_nips94.ps Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: pan.itc.it:8008/papers (more) From: pan.itc.it:8008/papers (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: The paper presents a rapid speaker-normalization technique based on neural network spectral mapping. The neural network is used as a front-end of a continuous speech recognition system (speakerdependent, HMM-based) to normalize the input acoustic data from a new speaker. The spectral difference between speakers can be reduced using a limited amount of new acoustic data (40 phonetically rich sentences). Recognition error of phone units from the acoustic-phonetic continuous speech corpus APASCI... (Update)
Context of citations to this paper: More
.... by Multi Layer Perceptron networks by other researchers [3, 4] A previous paper introduced GRAN networks for speaker normalization [5]. The neural network was applied as a front end preprocessor for a continuous speech recognition system (speaker dependent, HMMbased) to...
.... application environment used to provide voice commands to a mobile robot [5] The use of MLP for this problem is not new [3] 6] [7], 8] 9] but in this work we investigate different network architectures and parameters in order to achieve the best results. Neural...
Cited by: More
Speaker Normalization Improvement by Neural.. - Autiero.. (1999) (Correct)
Combining Local PCA and Radial Basis Function Networks for .. - Furlanello, Giuliani (1995) (Correct)
Similar documents (at the sentence level):
9.2%: Applications of Generalized Radial Basis Functions .. - Furlanello.. (Correct)
Active bibliography (related documents): More All
0.5: Rapid Speaker Adaptation for Neural Network Speech Recognizers - Burnett (1997) (Correct)
0.5: A Codebook Adaptation Algorithm for SCHMM Using Formant.. - Yang, Shin, Kim, Youn (Correct)
0.3: A Bibliography On Nonlinear System Identification - Georgios B. Giannakis.. (2001) (Correct)
Similar documents based on text: More All
0.7: Investigating Recognition Of Children's Speech - Diego Giuliani And (Correct)
0.6: Roberto Battiti - Dipartimento Di Matematica (Correct)
0.6: Tree-based Classifiers and GIS for Biological Risk.. - Furlanello, Merler, Chemini (1997) (Correct)
Related documents from co-citation: More All
2: Speaker normalization for speech recognition (context) - Huang - 1992
2: Fast speaker adaptation for speech recognition system (context) - Class, Kaltenmeier et al. - 1990
2: Speaker normalization and adaptation using secondorder connectionist networks (context) - Watrous - 1994
BibTeX entry: (Update)
C. Furlanello, D. Giuliani, and E. Trentin, "Connectionist speaker normalization with Generalized Resource Allocating Networks," in Advances in Neural Information Processing Systems 7 (D. S. T. G. Tesauro and T. K. Leen, eds.), MIT Press, 1995. in press. http://citeseer.ist.psu.edu/furlanello95connectionist.html More
@inproceedings{ furlanello95connectionist,
author = "Cesare Furlanello and Diego Giuliani and Edmondo Trentin",
title = "Connectionist Speaker Normalization with Generalized Resource Allocating Networks",
booktitle = "Advances in Neural Information Processing Systems",
volume = "7",
publisher = "The {MIT} Press",
editor = "G. Tesauro and D. Touretzky and T. Leen",
pages = "865--874",
year = "1995",
url = "citeseer.ist.psu.edu/furlanello95connectionist.html" }
Citations (may not include all citations):92 A resource-allocating network for function interpolation (context) - Platt - 1991
77 Dynamic programming algorithm optimization for spoken word r.. (context) - Sakoe, Chiba - 1978
71 A theory of networks for approximation and learning - Poggio, Girosi - 1989
41 Statistical learning networks: a unifying view (context) - Barron, Barron - 1988
29 Speaker Independent Continuous Speech Recognition Using an A.. - Angelini, Brugnara et al. - 1994
14 Advances in Speech Signal Processing (context) - Furui, Sondhi - 1991
12 Speaker normalization and adaptation using second-order conn.. (context) - Watrous - 1994
10 Speaker normalization for speech recognition (context) - Huang - 1992
6 Fast speaker adaptation for speech recognition system (context) - Class, Kaltenmeier et al. - 1990
6 A comparative study of spectral mapping for speaker adaptati.. (context) - Nakamura, Shikano - 1990
3 Global convergence of the recursive kernel regression estima.. (context) - Krzyzak - 1992
3 A piecewise linear spectral mapping for supervised speaker a.. (context) - Matsukoto, Inoue - 1992
1 Applied nonparametric regression (context) - Dekker, Hardle - 1990
1 Speech recognition using temporal decomposition and multi-la.. (context) - Montacie, Choukri et al. - 1989
Documents on the same site (http://pan.itc.it:8008/papers.html): More
Combining Local PCA and Radial Basis Function Networks for .. - Furlanello, Giuliani (1995) (Correct)
An Application of the Bootstrap 632+ Rule to Ecological Data - Furlanello Merler (Correct)
Classification Tree Methods for Analysis of.. - Merler.. (1996) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC