Interspeech is the world‘s largest and most renowned conference on the science and technology of speech processing. The conference features world-class speakers, tutorials, oral and poster sessions, challenges, exhibitions and satellite events, gathering around thousands of attendees from all over the world.
Four dissertations of Clova AI have been accepted at the Interspeech 2019 conference. Please refer to the following for further details:
| Who Said that: Audio-Visual Speaker Diarisation of Real-World Meeting | Joon Son Chung, Bong-Jin Lee, Icksang Han | Audio-visual speaker diarisation of the automatic recording of the proceedings | arXiv Github |
| My Lips are Concealed: Audio-Visual Speech Enhancement through Obstructions | Triantafyllos Afouras, Joon Son Chung, Andrew Zisserman | Audio-visual speech enhancement for lip reading in the lip-concealed situation | arXiv Github |
| Probability Density Distillation with Generative Adversarial Networks for High-Quality Parallel Waveform Generation | Ryuichi Yamamoto, Eunwoo Song, Jae-Min Kim | A new distillation method using GAN for a high-quality parallel WaveNet vocoder | arXiv Github |
| Parameter Enhancement for MELP Speech Codec in Noisy Communication Environment | Min-Jae Hwang, Hong-Goo Kang | The proposed parameter enhancement method directly enhances the noise-corrupted vocoder parameters of 2.4 kbit/s mixed excitation linear prediction (MELP) coder system without any pre-processing speech enhancement module. As a result, the proposed parameter enhancement achieves a much simpler and faster speech enhancement method than the conventional time-frequency (T-F) mask-based speech enhancement methods, whereas its enhancement quality remains high. | arXiv Github |
NAVER and LINE will run an exhibition booth as a gold-level sponsor. Please pay us a visit to our booth and get to know more about us.
We hope to see you soon in Graz.