Title | ||
---|---|---|
Reduced Complexity and Scaling for Asynchronous HMMS in a Bimodal Input Fusion Application |
Abstract | ||
---|---|---|
The Asynchronous Hidden Markov Model (AHMM) can model the joint likelihood of two observation sequences, even if the streams are not synchronised. Previously this model has been applied to audio- visual recognition tasks. The main drawback of the concept is its rather high training and decoding complexity. In this work we show how the complexity can be reduced significantly with advanced run- ning indices for the calculations. Yet, the AHMM characteristics and its advantages are preserved. The improvement also allows a scal- ing procedure to keep numerical values in a reasonable range. In an experimental section we compare the complexity of the original and the improved concept and validate the theoretical results. Then the model is tested on a bimodal speech and gesture user input fusion task: Compared to a late fusion HMM an improvement of more than 10% absolute recognition performance has been achieved. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/ICASSP.2006.1661386 | Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference |
Keywords | Field | DocType |
audio-visual systems,computational complexity,decoding,gesture recognition,hidden Markov models,image coding,speech coding,speech recognition,asynchronous HMM,asynchronous hidden Markov model,audio-visual recognition tasks,bimodal input fusion application,bimodal speech,decoding complexity,gesture user input fusion task | Asynchronous communication,Speech coding,Pattern recognition,Computer science,Gesture,Gesture recognition,Speech recognition,Artificial intelligence,Decoding methods,Hidden Markov model,Scaling,Computational complexity theory | Conference |
Volume | ISSN | ISBN |
5 | 1520-6149 | 1-4244-0469-X |
Citations | PageRank | References |
2 | 0.41 | 6 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marc Al-Hames | 1 | 116 | 8.75 |
Gerhard Rigoll | 2 | 2788 | 268.87 |