Open AccessProceedings Article
A new fast algorithm for automatic segmentation of continuous speech.
Iman Gholampour,Kambiz Nayebi +1 more
Reads0
Chats0
TLDR
A new method for automatic segmentation of continuous speech into phone-like units is addressed, based on a very fast presegmentation algorithm which uses a new statistical modeling of speech and searching in a multilevel structure, called Dendrogram, for decreasing insertion rate.Abstract:
In this paper a new method for automatic segmentation of continuous speech into phone-like units is addressed. Our method is based on a very fast presegmentation algorithm which uses a new statistical modeling of speech and searching in a multilevel structure, called Dendrogram, for decreasing insertion rate. In each step the performance of algorithms have been tested over a large set of TIMIT sentences. According to these tests, our final segmentation algorithm is capable of detecting nearly 97% of segments with an average boundary position error of less than 7 msec and average insertion rate of less than 12.6%. The paper will describe the algorithms for determining the acoustic segments. Performance results will also be included.read more
Citations
More filters
Journal ArticleDOI
Automatic phonetic segmentation
TL;DR: The most frequently used approach-based on a modified Hidden Markov Model (HMM) phonetic recognizer is analyzed, and a general framework for the local refinement of boundaries is proposed, and the performance of several pattern classification approaches is compared within this framework.
Automatic time alignment of phonemes using acoustic-phonetic information
Ronald A. Cole,John-Paul Hosom +1 more
TL;DR: The hypothesis is that the integration of acoustic-phonetic information into a state-of-the-art automatic phonetic alignment system will significantly improve its accuracy and robustness.
Journal ArticleDOI
Mapping between acoustic and articulatory gestures
TL;DR: A definition for articulatory as well as acoustic gestures is proposed along with a method to segment the measured articulatory trajectories and acoustic waveforms into gestures and a method based on the error in estimated critical points is suggested.
Proceedings Article
On hierarchical clustering for speech phonetic segmentation
Ciro Gracia,Xavier Binefa +1 more
TL;DR: This paper extends the framework with an unsupervised segmentation algorithm based on a divisive clustering technique and compares both approaches: agglomerative nesting (Bottom-up) against divisive analysis (Top-down).
Journal ArticleDOI
A phonetic labeling method format database processing
TL;DR: A semi‐automatic phonetic labeling method for processing in the MAT (Mandarin across Taiwan) speech database can achieve segmentation accuracy around 90% for an allowed tolerance of 16 ms.
References
More filters
Book
Graph theory with applications
TL;DR: In this paper, the authors present Graph Theory with Applications: Graph theory with applications, a collection of applications of graph theory in the field of Operational Research and Management. Journal of the Operational research Society: Vol. 28, Volume 28, issue 1, pp. 237-238.
Journal ArticleDOI
Graph theory with applications (revised edition), by J. A. Bondy and U.S.R. Murty. Pp x, 264. £5·95 paperback. 1977. SBN 0 333 22694 1 (Macmillan)
Book
Discrete-Time Processing of Speech Signals
TL;DR: The preface to the IEEE Edition explains the background to speech production, coding, and quality assessment and introduces the Hidden Markov Model, the Artificial Neural Network, and Speech Enhancement.
Proceedings ArticleDOI
Multi-level acoustic segmentation of continuous speech
James Glass,Victor W. Zue +1 more
TL;DR: The authors have developed a procedure that describes the acoustic structure of the signal, and the algorithms for determining the acoustic segments and the multi-level structure, and possible use for automatic speech recognition is discussed.