An approach to continuous speech recognition based on layered self-adjusting decoding graph
2002Vol. 3, pp. 1779–1782
Abstract
In this paper, an approach to continuous speech recognition based on a layered self-adjusting decoding graph is described. It utilizes a scaffolding layer to support fast network expansion and releasing. A two level hashing structure is also described. It introduces self-adjusting capability in dynamic decoding on a general re-entrant decoding network. In stack decoding, the scaffolding layer in the proposed approach enables the decoder to look several layers into the future so that long span inter-word context dependency can be exactly preserved. Experimental results indicate that highly efficient decoding can be achieved with a significant savings on recognition resources.
Related Papers
- → Efficient Sphere Polar Decoding via Synchronous Determination(2020)10 cited
- → Low-Complexity Successive Cancellation List Decoding of Polar Codes Based on Path Metric(2021)3 cited
- → Research of an improved BP decoding arithmetic(2009)
- → Soft decision decoding using the hierarchy of linear block codes(2000)
- Research of modified RA decoding algorithm based on offset approximation(2009)