A Comparison Between Deep Neural Nets and Kernel Acoustic Models for Speech Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

A Comparison Between Deep Neural Nets and Kernel Acoustic Models for Speech Recognition

Abstract

We study large-scale kernel methods for acoustic modeling and compare to DNNs on performance metrics related to both acoustic modeling and recognition. Measuring perplexity and frame-level classification accuracy, kernel-based acoustic models are as effective as their DNN counterparts. However, on token-error-rates DNN models can be significantly better. We have discovered that this might be attributed to DNN's unique strength in reducing both the perplexity and the entropy of the predicted posterior probabilities. Motivated by our findings, we propose a new technique, entropy regularized perplexity, for model selection. This technique can noticeably improve the recognition performance of both types of models, and reduces the gap between them. While effective on Broadcast News, this technique could be also applicable to other tasks.
Fichier principal
Vignette du fichier
icassp16.pdf (2.19 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01329772 , version 1 (10-06-2016)

Identifiers

Cite

Zhiyun Lu, Dong Guo, Alireza Bagheri Garakani, Kuan Liu, Avner May, et al.. A Comparison Between Deep Neural Nets and Kernel Acoustic Models for Speech Recognition. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), Mar 2016, Shanghai, China. ⟨hal-01329772⟩
207 View
209 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More