Jesper Högberg  Home/Search
Context Related
| speech.kth.se/ctt/publica...ES97_565.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: speech.kth.se/ctt/publications... (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: In this study we introduce combined data driven and rule based methods to synthesise speech. The aim is to improve on the coarticulatory modelling by adapting the KTH TTS system to data from one speaker. Regression trees are trained on a manually corrected speech database to provide predictions for vowel formant frequencies. At runtime, the TTS system produces formant frequency trajectories that are derived from weighted contributions from both the rules and the regression trees. The weighting... (Update)
Context of citations to this paper: More
.... measuring speech naturalness is to ask the subjects for an indication whether one utterance was better, equal, or worse than another [2, 4]. Even though this relative scale reliably indicates differences, it fails to show magnitude of improvement. In this work we implement a...
Cited by: More
On The Relative Importance Of Different Prosodic Factors .. - Bulyko, Ostendorf, Price (Correct)
Active bibliography (related documents): More All
0.5: Automatic Derivation Of Phonetic Rules By An Iterated.. - Högberg (Correct)
0.2: DTW-based Phonetic Alignment Using Multiple Acoustic Features - Ergio Paulo Lu (2003) (Correct)
0.2: Improving the Accuracy of the Speech Synthesis Based.. - Acoustic Features Sergio (2003) (Correct)
Similar documents based on text: More All
0.4: Cross Phone State Clustering Using Lexical Stress And Context - Högberg, Sjölander (Correct)
0.3: Trying to Improve Phone and Word Recognition Using Finely.. - Sjölander, Högberg (Correct)
0.3: Recent Advances in Multilingual Text-To-Speech Synthesis - Möbius, Schroeter, van.. (1996) (Correct)
BibTeX entry: (Update)
Hogberg, J. 1997, Data driven formant synthesis. Proceedings EuroSpeech. Rhodes, Greece. 565-568. http://citeseer.ist.psu.edu/hogberg97data.html More
@inproceedings{ hogberg97data,
author = "Jesper Hogberg",
title = "Data Driven Formant Synthesis",
booktitle = "Proc. Eurospeech '97",
address = "Rhodes, Greece",
pages = "565--568",
year = "1997",
url = "citeseer.ist.psu.edu/hogberg97data.html" }
Citations (may not include all citations):1262 Classification and regression trees (context) - Breiman, Friedman et al. - 1984
97 Pitch synchronous Waveform Processing Techniques for Text-to.. (context) - Moulines, Charpentier - 1990
24 Explaining phonetic variation: A sketch of the H&H theory (context) - Lindblom - 1990
19 Context dependent modeling of phones in continuous speech re.. (context) - Bahl, Souza et al. - 1991
10 Improvements in an HMM-Based Speech Synthesiser (context) - Donovan, Woodland - 1995
9 Multilingual text-to-speech development and applications (context) - Carlson, Granstr et al. - 1991
5 Entropics Research Laboratories Inc (context) - waves, manuals - 1993
2 A phonetic investigation using binary regression trees (context) - gberg - 1994
1 Vowel dynamics in a text to speech system - some considerati.. (context) - Carlson, Nord - 1993
1 Frying to improve phone and word recognition using finely tu.. (context) - ander, gberg - 1997
Documents on the same site (http://www.speech.kth.se/ctt/publications/): More
Evaluation Of A System For Concatenative Articulatory Visual.. - Engwall (Correct)
A Phoneme Recognizer for the Hearing Impaired - Johansson, Blomberg, Elenius, .. (2002) (Correct)
SYNFACE - a project presentation - Granström, Karlsson, Spens (2002) (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