A dynamic, feature-based approach to the interface between phonology and phonetics for speech modeling and recognition

This article is a general idea of a statistical model for speech recognition given where phonetic and phonological knowledge sources are drawn from the current understanding of the global characteristics of human speech communication. They are effortlessly incorporated into the structure of a stochastic model of speech. A steady statistical formalism is presented in which the associated models for the discrete, feature-based phonological process and the continuous, dynamic phonetic process in human speech production are calculations at a crossing point. Two primary ways of executing the speech model and recognizer are presented, one based on the trended hidden Markov model (HMM) or explicitly defined trajectory model, and the other on the state-space or recursively defined trajectory model. Both executions build into their respective recognition and model-training, production affiliated trajectories across feature defined phonological units. The continuity and the constraint structure in the dynamic speech model permit a joint characterization of the contextual and speaking style variations manifested in speech sounds, in so doing holding promises to overcome some key limitations of the current speech recognition technology.

A dynamic, feature-based approach to the interface between phonology and phonetics for speech modeling and recognition. vol 24. ISS 4, Li Deng

The Illustration of Phonetics

The Journal of Phonetic is about the illustration of sociophonetic variation within speech, stressing both its frequency and also the moderately minor role it has played in the development of phonetic and phonological theory. Evaluating evidence from studies of adults and children, the article advocates that cognitive illustrations of words combine linguistic and directorial information. Both types of information are present from the first stages of acquisition. It advocates that an exemplar-based model of phonological knowledge offers the most useful means of modeling sociophonetic variation. Some of the characteristics of an exemplar-based account of sociophonetic variability and highlight some strands of investigation which would facilitate its further development are also discussed. In this article they found that the exemplar-based framework provides a basis for understanding the integration of lexical and indexical information within memory. They say the key element in accounting for the sociophonetic properties of speech is to reason in an understanding of how individuals make their social world and how they use language to position themselves within it.

Journal of Phonetics, Volume 34, Issue 4, October 2006, Pages 409-438Paul Foulkes, Gerard Docherty