Proceedings ArticleDOI
Use of dynamic programming for automatic synchronization of two similar speech signals
P. Bloom
- Vol. 9, pp 69-72
Reads0
Chats0
TLDR
A further application for time-alignment algorithms is described, in which replacement dialogue for a film soundtrack may be automatically synchronized to reference dialogue recorded during filming, in a digital signal processing system that uses a DP algorithm.Abstract:
A number of applications exist in basic speech research for Dynamic Programming (DP) algorithms that can produce accurate time registration data for aligning one speech signal with a similar speech signal. In this paper, a further application for time-alignment algorithms is described, in which replacement dialogue for a film soundtrack may be automatically synchronized to reference dialogue recorded during filming. This is being carried out in a digital signal processing system that uses a DP algorithm capable of aligning utterances of indeterminate length accurately and efficiently in real-time. The main features of this system and the DP algorithm will be described.read more
Citations
More filters
Patent
Method and apparatus for real-time correlation of a performance to a musical score
TL;DR: In this paper, the authors proposed a method for correlating a performance to a score of a musical score, in real time, using a score processor that accepts a score which a user would like to play and converts it into a useable format.
Patent
Image tracking and substitution system and methodology for audio-visual presentations
TL;DR: In this paper, a system and method for processing a video input signal providing for tracking a selected portion in a predefined audiovisual presentation and integrating selected user images into the selected portion of the predefined audio presentation.
Patent
Image integration with replaceable content
TL;DR: In this article, a video game adapter interface apparatus has a user input device and an associated video display, where the user selects a distinguishable visual image representation for association into a video games audiovisual presentation, such as where that user is identified.
Patent
Image integration, mapping and linking system and methodology
TL;DR: In this article, the user can create an original image or select one of a predetermined set of visual images as the user's identification for use in the audiovisual presentation.
Components of prosodic effects in speech recognition
TL;DR: This paper showed that the prosodic structure of utterances can be used to predict accent location in a predictive fashion in sentence comprehension, to direct attention to accented words and to locate the most important parts of a speaker's message.
References
More filters
Journal ArticleDOI
Isolated and Connected Word Recognition--Theory and Selected Applications
TL;DR: This paper discusses word recognition as a classical pattern-recognition problem and shows how some fundamental concepts of signal processing, information theory, and computer science can be combined to give us the capability of robust recognition of isolated words and simple connected word sequences.
Proceedings ArticleDOI
A digital filter bank for spectral matching
TL;DR: A new digital filter bank design is proposed for the processing of speech waveforms where spectral pattern matching techniques are applicable and a distance metric is proposedfor comparing a spectral frame with previously derived reference patterns.
Journal ArticleDOI
The effects of selected signal processing techniques on the performance of a filter-bank-based isolated word recognizer
TL;DR: Results showed that some fairly simple signal processing operations provided the best overall performance in the noise-free case; in noisy conditions performance degraded significantly for signal-to-noise ratios less than about 24 dB.
Journal ArticleDOI
On temporal alignment of sentences of natural and synthetic speech
TL;DR: It is shown that the dynamic time warping procedures used for isolated word recognition apply almost as well to alignment of sentence length utterances, and one must apply caution in using the time alignment contour for synthesis or recognition applications.
Proceedings ArticleDOI
ZIP: A dynamic programming algorithm for time-aligning two indefinitely long utterances
R. Chamberlain,J. Bridle +1 more
TL;DR: ZIP, a modified DP algorithm designed to compute the time alignment of two utterances of the same text of any length is presented, by using a window and partial traceback.