Speaker adaptation of DNN-based ASR with i-vectors: Does it actually adapt models to speakers?

Mickael Rouvier 1, 2 Benoit Favre 3
1 LIA - Laboratoire Informatique d'Avignon
2 LIF - Laboratoire d'informatique Fondamentale de Marseille
3 LIF - Laboratoire d'informatique Fondamentale de Marseille - UMR 6166
Abstract : no abstract
Document type :
Conference papers
Complete list of metadatas
https://hal-amu.archives-ouvertes.fr/hal-01194245
Contributor : Benoit Favre <>
Submitted on : Saturday, September 5, 2015 - 11:12:59 AM
Last modification on : Saturday, March 23, 2019 - 1:22:26 AM

Identifiers

  • HAL Id : hal-01194245, version 1

Collections

UNIV-AMU | EC-MARSEILLE | LIF | LIS-LAB | UNIV-AVIGNON

Citation

Mickael Rouvier, Benoit Favre. Speaker adaptation of DNN-based ASR with i-vectors: Does it actually adapt models to speakers?. Interspeech, Singapore, 2014, Unknown, Unknown Region. ⟨hal-01194245⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

139

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD