Abstract
The problem of text-dependent speaker verification under noisy conditions is becoming ever more relevant, due to increased
usage for authentication in real-world applications.
Classical methods for noise reduction such as spectral subtraction and Wiener filtering introduce distortion and do not perform well in
this setting.
In this work we compare the performance of different noise reduction methods under different noise conditions
in terms of speaker verification when the text is known and the system is trained on clean data (mis-matched conditions).
We furthermore propose a new approach based on dictionary-based noise reduction and compare it to the baseline methods.
usage for authentication in real-world applications.
Classical methods for noise reduction such as spectral subtraction and Wiener filtering introduce distortion and do not perform well in
this setting.
In this work we compare the performance of different noise reduction methods under different noise conditions
in terms of speaker verification when the text is known and the system is trained on clean data (mis-matched conditions).
We furthermore propose a new approach based on dictionary-based noise reduction and compare it to the baseline methods.
Original language | English |
---|---|
Title of host publication | Interspeech 2016 |
Publisher | ISCA |
Publication date | Sept 2016 |
Pages | 1839-1843 |
DOIs | |
Publication status | Published - Sept 2016 |
Event | Interspeech 2016 - San Francisco, CA, United States Duration: 8 Sept 2016 → 12 Sept 2016 http://www.interspeech2016.org/ |
Conference
Conference | Interspeech 2016 |
---|---|
Country/Territory | United States |
City | San Francisco, CA |
Period | 08/09/2016 → 12/09/2016 |
Internet address |
Keywords
- Noise reduction
- speaker verification
- dictionary learning