[PDF][PDF] Prominence: acoustic and lexical/syntactic correlates
BM Streefkerk - 2002 - dare.uva.nl
Thiss chapter deals with the marking of'prominent'parts in speech utterances. Prominencee
marking looks easy, but it is rather complex. The notion of prominence iss not clearly defined …
marking looks easy, but it is rather complex. The notion of prominence iss not clearly defined …
Development and comparison of three syllable stress classifiers
KL Jenkin, MS Scordilis - Proceeding of Fourth International …, 1996 - ieeexplore.ieee.org
The paper describes the development of three alternative techniques for the classification of
syllable stress in fluent speech. They are based on:(1) neural networks that use contextual …
syllable stress in fluent speech. They are based on:(1) neural networks that use contextual …
[PDF][PDF] Use of acoustic sentence level and lexical stress in HSMM speech recognition.
JL Hieronymus, D McKelvie, FR McInnes - icassp, 1992 - Citeseer
In this paper, we describe the results of an experiment to study the e ectiveness of using
acoustic stress to improve automatic speech recognition. The CSTR speech recognition …
acoustic stress to improve automatic speech recognition. The CSTR speech recognition …
An investigation of acoustic events related to sentential stress and pitch accents, in English
PC Bagshaw - Speech Communication, 1993 - Elsevier
An algorithm is described which abstracts acoustic parameters of a speech waveform to
automatically transcribe sentential stress and pitch movements. The waveform acoustics …
automatically transcribe sentential stress and pitch movements. The waveform acoustics …
Criteria for labelling prosodic aspects of English speech
PC Bagshaw, B Williams - 1992 - era.ed.ac.uk
We report a set of labelling criteria which have been developed to label prosodic events in
clear, continuous speech, and propose a scheme whereby this information can be …
clear, continuous speech, and propose a scheme whereby this information can be …
[PS][PS] Modelling Prosodic and Dialogue Information for Automatic Speech Recognition
HF Wright - 2000 - cstr.ed.ac.uk
There are two main goals of the work presented in this thesis. The rst is to provide a system
for automatically classifying utterances into di erent types known as moves. In order to do …
for automatically classifying utterances into di erent types known as moves. In order to do …
An investigation of the relation between perceived pitch accent and automatically-located accent in british english
JL Hieronymus, BJ Williams - Proc. Eurospeech 1991, 1991 - isca-archive.org
Previous work on the prosodic analysis of British English has used a purely perceptual
analysis of the data, the results being stated in terms of structural features of the prosodic …
analysis of the data, the results being stated in terms of structural features of the prosodic …
Automatic classification of pitch movements via MLP-based estimation of class probabilities
LFM ten Bosch - … Conference on Acoustics, Speech, and Signal …, 1995 - ieeexplore.ieee.org
In this paper, we study to what extent pitch movements in utterances can be classified
automatically by using acoustical information and an intonation grammar. It will be shown …
automatically by using acoustical information and an intonation grammar. It will be shown …
[PDF][PDF] APA: An object-oriented system for automatic prosodic analysis.
M Petrillo - 2003 - Citeseer
La prosodia è uno degli argomenti su cui gli specialisti di sintesi e riconoscimento del
parlato si dovranno confrontare nei prossimi anni. Gli attuali sistemi di sintesi vocale sono in …
parlato si dovranno confrontare nei prossimi anni. Gli attuali sistemi di sintesi vocale sono in …
[PDF][PDF] Department of Electrical and Electronic Engineering The University of Melbourne ABSTRACT-This paper addresses the task of classifying syllables from …
KL Jenkin, MS Scordilis - assta.org
This paper addresses the task of classifying syllables from continuous speech into primary
stress, secondary stress and zero stress categories using artificial neural networks. The …
stress, secondary stress and zero stress categories using artificial neural networks. The …