Structural design of hidden Markov model speech recognizer using multivalued phonetic features: comparison with segmental speech units.

By Li Deng, K. Erler. 1992

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Switching Dynamic System Models for Speech Articulation and Acoustics (2004, methodology): “Some earlier work used [16, 22] either quantized articulatory features or articulatory data to design speech recognizers, employing highly simplistic models for the underlying articulatory dynamics.”
Deep Belief Networks for phone recognition (2009, background): “Substantial research effo rt has been devoted to going beyond the “beads-on-a-string” view of speech to representing str uctu e in speech above the level of the phonetic segment [5, 6, 7].”