Publication Details
Analysis Of DNN Approaches To Speaker Identification
Glembek Ondřej, Ing., Ph.D. (DCGM FIT BUT)
Novotný Ondřej, Ing., Ph.D. (DCGM FIT BUT)
Plchot Oldřich, Ing., Ph.D. (DCGM FIT BUT)
Grézl František, Ing., Ph.D. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
automatic speaker identification, deep neural networks, bottleneck features, i-vector
This work studies the usage of the Deep Neural Network (DNN) Bottleneck (BN) features together with the traditional MFCC features in the task of i-vector-based speaker recognition. We decouple the sufficient statistics extraction by using separate GMM models for frame alignment, and for statistics normalization and we analyze the usage of BN and MFCC features (and their concatenation) in the two stages. We also show the effect of using full-covariance GMM models, and, as a contrast, we compare the result to the recent DNN-alignment approach. On the NIST SRE2010, telephone condition, we show 60% relative gain over the traditional MFCC baseline for EER (and similar for the NIST DCF metrics), resulting in 0.94% EER.
We have analyzed the i-vector based systems with Deep Neural Network (DNN) Bottleneck (BN) features together with the traditional MFCC features, and we have demonstrated substantial gain for NIST SRE 2010, telephone condition.
@INPROCEEDINGS{FITPUB11140, author = "Pavel Mat\v{e}jka and Ond\v{r}ej Glembek and Ond\v{r}ej Novotn\'{y} and Old\v{r}ich Plchot and Franti\v{s}ek Gr\'{e}zl and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}", title = "Analysis Of DNN Approaches To Speaker Identification", pages = "5100--5104", booktitle = "Proceedings of the 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), 2016", year = 2016, location = "Shanghai, CN", publisher = "IEEE Signal Processing Society", ISBN = "978-1-4799-9988-0", doi = "10.1109/ICASSP.2016.7472649", language = "english", url = "https://www.fit.vut.cz/research/publication/11140" }