Projects per year
Fingerprint Fingerprint is based on mining the text of the person's scientific documents to create an index of weighted terms, which defines the key subjects of each individual researcher.
- 7 Similar Profiles
Speech intelligibility
Engineering & Materials Science
Speech enhancement
Engineering & Materials Science
intelligibility
Physics & Astronomy
Mean square error
Engineering & Materials Science
augmentation
Physics & Astronomy
estimators
Physics & Astronomy
envelopes
Physics & Astronomy
education
Physics & Astronomy
Network
Dive into details by clicking on the dots.
Projects 2015 2017
- 1 Finished
OCTAVE: Objective Control for TAlker VErification
Tan, Z., Sarkar, A. K., Thomsen, D. A. L., Yu, H., Kolbæk, M. & Thomsen, N. B.
01/06/2015 → 31/07/2017
Project: Research
Research Output 2016 2019
On the Relationship Between Short-Time Objective Intelligibility and Short-Time Spectral-Amplitude Mean-Square Error for Speech Enhancement
Kolbæk, M., Tan, Z-H. & Jensen, J., Feb 2019, In : IEEE/ACM Transactions on Audio, Speech, and Language Processing. 27, 2, p. 283-295 13 p., 8509159.Research output: Contribution to journal › Journal article › Research › peer-review
Speech intelligibility
Speech enhancement
intelligibility
Mean square error
augmentation
Monaural Speech Enhancement using Deep Neural Networks by Maximizing a Short-Time Objective Intelligibility Measure
Kolbæk, M., Tan, Z-H. & Jensen, J., 2018, International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, p. 5059-5063 (I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings).Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review
Single-Microphone Speech Enhancement and Separation Using Deep Learning
Kolbæk, M., 2018, Aalborg Universitetsforlag. 233 p. (Ph.d.-serien for Det Tekniske Fakultet for IT og Design, Aalborg Universitet).Research output: Book/Report › Ph.D. thesis › Research
Open Access
File
7
Citations
(Scopus)
Joint separation and denoising of noisy multi-talker speech using recurrent neural networks and permutation invariant training
Kolbæk, M., Yu, D., Tan, Z-H. & Jensen, J., 2017, International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, 6 p. (IEEE International Workshop on Machine Learning for Signal Processing (MLSP). Proceedings.).Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review
Multitalker Speech Separation With Utterance-Level Permutation Invariant Training of Deep Recurrent Neural Networks
Kolbæk, M., Yu, D., Tan, Z-H. & Jensen, J., 13 Jul 2017, In : I E E E Transactions on Audio, Speech and Language Processing. 25, 10, p. 1901-1913 13 p.Research output: Contribution to journal › Journal article › Research › peer-review
Activities 2018 2018
- 1 Internal examination
Single-Microphone Speech Enhancement and Separation Using Deep Learning
Thomas Arildsen (Opponent)30 Nov 2018
Activity: Examination › Internal examination
Press / Media
Kunstige neurale netværk skal gøre livet lettere for høreapparatbrugere
Morten Kolbæk, Jesper Jensen & Zheng-Hua Tan
04/01/2019 → 07/01/2019
17 items of media coverage, 1 media contribution
Press/Media: Press / Media