Search PubMed⌕ Search
Home/Archive/PubMed

PubMed · 7240574

Segmenting speech using dynamic programming.

J R Cohen
View original source ↗Export metadata ↓

Abstract

Speech is modeled as a Markov chain. Scoring is developed to convert observations of the speech signal into estimated probabilities of the locations of segment boundaries. Dynamic programming is then used to compute a most-probable segmentation for the speech. The process automatically adjusts to speakers and incorporates a priori information in a probabilistic and systemic fashion. The performance of the algorithm appears to be state-of-the-art, independent of speaker.

Explore related subjects

ComputersHumansMarkov ChainsMethodsModels, PsychologicalPhoneticsProbabilitySpeech PerceptionJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

J R Cohen. 1981. Segmenting speech using dynamic programming.. https://doi.org/10.1121/1.385826

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed1995

Seeing motion behind occluders.

The visual system has no difficulty maintaining the identity of an object as it disappears and reappears behind stationary occluders. In the natural world, a moving object may differ from occluders by many characteristics (colour, depth, shape and so on). Scene segmentation based on these characteristics is thought to happen early in visual processing, and to influence how objects, including moving objects, are identified. What happens if the only characteristic distinguishing an object is its direction of motion? Experiments with random dot displays show that one dot moving in a constant trajectory is readily detected among identical dots in brownian motion. Detection declines sharply if the trajectory is intermittently broken, but improves if occluders obscure the breaks in the trajectory. It is not sufficient that these occluders be perceived as segmented from the rest of the display (such as by colour or depth). Rather, it is critical that the occluders do not contain motion that is similar in direction to that of the target trajectory. We conclude that detection of the trajectory is due to the integration of information within a network of low-level motion detectors and is not dependent on segmentation processes.

Computers↗
PubMed1995

Commercial applications of speech interface technology: an industry at the threshold.

Speech interface technology, which includes automatic speech recognition, synthetic speech, and natural language processing, is beginning to have a significant impact on business and personal computer use. Today, powerful and inexpensive microprocessors and improved algorithms are driving commercial applications in computer command, consumer, data entry, speech-to-text, telephone, and voice verification. Robust speaker-independent recognition systems for command and navigation in personal computers are now available; telephone-based transaction and database inquiry systems using both speech synthesis and recognition are coming into use. Large-vocabulary speech interface systems for document creation and read-aloud proofing are expanding beyond niche markets. Today's applications represent a small preview of a rich future for speech interface technology that will eventually replace keyboards with microphones and loud-speakers to give easy accessibility to increasingly intelligent machines.

Computers↗
PubMed1995

Speech technology in the year 2001.

This paper introduces the session "Technology in the Year 2001" and is the first of four papers dealing with the future of human-machine communication by voice. In looking to the future it is important to recognize both the difficulties of technological forecasting and the frailties of the technology as it exists today--frailties that are manifestations of our limited scientific understanding of human cognition. The technology to realize truly advanced applications does not yet exist and cannot be supported by our presently incomplete science of speech. To achieve this long-term goal, the authors advocate a fundamental research program using a cybernetic approach substantially different from more conventional synthetic approaches. In a cybernetic approach, feedback control systems will allow a machine to adapt to a linguistically rich environment using reinforcement learning.

Computers↗