Title:	Complexity of the TDNN Acoustic Model with Respect to the HMM Topology
Authors:	Psutka, Josef Vaněk, Jan Pražák, Aleš
Citation:	PSUTKA, J., VANĚK, J., PRAŽÁK, A. Complexity of the TDNN Acoustic Model with Respect to the HMM Topology. In: Text, Speech, and Dialogue 23rd International Conference, TSD 2020, Brno, Czech Republic, September 8-11, 2020, Proceedings. Cham: Springer, 2020. s. 465-473. ISBN 978-3-030-58322-4, ISSN 0302-9743.
Issue Date:	2020
Publisher:	Springer
Document type:	konferenční příspěvek conferenceObject
URI:	2-s2.0-85091157003 http://hdl.handle.net/11025/42718
ISBN:	978-3-030-58322-4
ISSN:	0302-9743
Keywords in different language:	Speech recognition, Acoustic modeling, HMM topology, Lattice-free MMI
Abstract in different language:	In this paper, we discuss some of the properties of training acoustic models using a lattice-free version of the maximum mutual information criterion (LF-MMI). Currently, the LF-MMI method achieves state-of-the-art results on many speech recognition tasks. Some of the key features of the LF-MMI approach are: training DNN without initialization from a cross-entropy system, the use of a 3-fold reduced frame rate and the use of a simpler HMM topology. The conventional 3-state HMM topology was replaced in a typical LF-MMI training procedure with a special 1-stage HMM topology, that has different pdfs on the self-loop and forward transitions. In this paper, we would like to discuss both the different types of HMM topologies (conventional 1-, 2- and 3-state HMM topology) and the advantages of using biphone context modeling over using the original triphone or a simpler monophone context. We would also like to mention the impact of the subsampling factor to WER.
Rights:	Plný text není přístupný. © Springer
Appears in Collections:	Konferenční příspěvky / Conference papers (NTIS) Konferenční příspěvky / Conference Papers (KKY) OBD

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.