Title | ||
---|---|---|
Exploring the robustness of features and enhancement on speech recognition systems in highly-reverberant real environments. |
Abstract | ||
---|---|---|
This paper evaluates the robustness of a DNN-HMM-based speech recognition system in highly-reverberant real environments using the HRRE database. The performance of locally-normalized filter bank (LNFB) and Mel filter bank (MelFB) features in combination with Non-negative Matrix Factorization (NMF), Suppression of Slowly-varying components and the Falling edge (SSF) and Weighted Prediction Error (WPE) enhancement methods are discussed and evaluated. Two training conditions were considered: clean and reverberated (Reverb). With Reverb training the use of WPE and LNFB provides WERs that are 3% and 20% lower in average than SSF and NMF, respectively. WPE and MelFB provides WERs that are 11% and 24% lower in average than SSF and NMF, respectively. With clean training, which represents a significant mismatch between testing and training conditions, LNFB features clearly outperform MelFB features. The results show that different types of training, parametrization, and enhancement techniques may work better for a specific combination of speaker-microphone distance and reverberation time. This suggests that there could be some degree of complementarity between systems trained with different enhancement and parametrization methods. |
Year | Venue | Field |
---|---|---|
2018 | arXiv: Audio and Speech Processing | Complementarity (molecular biology),Reverberation,Parametrization,Computer science,Filter bank,Matrix decomposition,Robustness (computer science),Speech recognition,Non-negative matrix factorization,Signal edge |
DocType | Volume | Citations |
Journal | abs/1803.09013 | 0 |
PageRank | References | Authors |
0.34 | 0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
José Novoa | 1 | 10 | 3.92 |
Juan Pablo Escudero | 2 | 1 | 2.04 |
Jorge Wuth | 3 | 12 | 4.79 |
Víctor Poblete | 4 | 10 | 2.30 |
Simon King | 5 | 19 | 5.11 |
Richard M. Stern | 6 | 1663 | 406.79 |
Néstor Becerra Yoma | 7 | 50 | 18.84 |