Linxue Bai

Research activity per year

Fingerprint

Dive into the research topics where Linxue Bai is active. These topic labels come from the works of this person. Together they form a unique fingerprint.

1 Similar Profiles

7 Conference contribution
1 Paper

Exploring how phone classification neural networks learn phonetic information by visualising and interpreting bottleneck features
Bai, L., Weber, P., Jancovic, P. & Russell, M., 3 Sept 2018, Proceedings of Interspeech 2018. Hyderabad, India: ISCA, p. 1472-1476 5 p. (Interspeech; vol. 2018).
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Open Access
File
5 Citations (Scopus)

388 Downloads (Pure)
Phone recognition using a non-linear manifold with broad phone class dependent DNNs
Qian, M., Bai, L., Jancovic, P. & Russell, M., 3 Sept 2018, Proceedings of Interspeech 2018. Hyderabad, India: ISCA, p. 3753-3757 5 p. (Interspeech; vol. 2018).
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Open Access
File
1 Citation (Scopus)

213 Downloads (Pure)
Phone classification using a non-linear manifold with broad phone class dependent DNNs
Bai, L., Jancovic, P., Russell, M., Weber, P. & Houghton, S., 24 Aug 2017, Proceedings of Interspeech 2017. 5 p.
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Open Access
File
3 Citations (Scopus)

217 Downloads (Pure)
Interpretation of low dimensional neural network bottleneck features in terms of human perception and production
Weber, P., Bai, L., Russell, M., Jancovic, P. & Houghton, S., 10 Jun 2016, (Accepted/In press) Proceedings of Interspeech. ISCA, 5 p.
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
4 Citations (Scopus)
Progress on Phoneme Recognition with a Continuous-State HMM
Weber, P., Bai, L., Houghton, S., Jancovic, P. & Russell, M., 19 May 2016, (E-pub ahead of print) 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): Proceedings. IEEE Xplore, 5 p.
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
3 Citations (Scopus)

Linxue Bai

Fingerprint

Research output

Exploring how phone classification neural networks learn phonetic information by visualising and interpreting bottleneck features

Phone recognition using a non-linear manifold with broad phone class dependent DNNs

Phone classification using a non-linear manifold with broad phone class dependent DNNs

Interpretation of low dimensional neural network bottleneck features in terms of human perception and production

Progress on Phoneme Recognition with a Continuous-State HMM