Sixth European Conference on Speech Communication and Technology

Budapest, Hungary
September 5-9, 1999

Acoustic Modeling Based on a Generalized Laplacian Distribution

Atsushi Nakamura, Tomoko Matsui

ATR Interpreting Telecommunications Research Laboratories, Seika-Cho, Soraku-Gun, Kyoto, Japan

In speech recognition, acoustic modeling mismatches for the shapes of distributions are unavoidable when we use fixed-shape base distributions, such as the Gaussian. This paper proposes a new base distribution called the "generalized Laplacian distribution (GLD)", which offers more flexibility in terms of the distribution shape. The effectiveness of the GLD-based modeling is proven through speech recognition experiments.

Full Paper (PDF)

Bibliographic reference.  Nakamura, Atsushi / Matsui, Tomoko (1999): "Acoustic modeling based on a generalized laplacian distribution", In EUROSPEECH'99, 1347-1350.