D
Dimitrios Dimitriadis
Researcher at Microsoft
Publications - 112
Citations - 2258
Dimitrios Dimitriadis is an academic researcher from Microsoft. The author has contributed to research in topics: Speaker diarisation & Word error rate. The author has an hindex of 24, co-authored 103 publications receiving 1822 citations. Previous affiliations of Dimitrios Dimitriadis include University of California, San Diego & AT&T Labs.
Papers
More filters
Proceedings ArticleDOI
English Conversational Telephone Speech Recognition by Humans and Machines
George Saon,Gakuto Kurata,Tom Sercu,Kartik Audhkhasi,Samuel Thomas,Dimitrios Dimitriadis,Xiaodong Cui,Bhuvana Ramabhadran,Michael Picheny,Lynn-Li Lim,Bergul Roomi,Phil Hall +11 more
TL;DR: In this article, a set of acoustic and language modeling techniques were used to lower the word error rate of a conversational telephone LVCSR system to 5.5%/10.3% on the Switchboard/CallHome subsets of the Hub5 2000 evaluation.
Journal ArticleDOI
Robust AM-FM features for speech recognition
TL;DR: The robustness and discriminability of the AM-FM features is investigated in combination with mel cepstrum coefficients (MFCCs), and it is shown that these hybrid features perform well in the presence of noise, both in terms of phoneme-discrimination and speech recognition performance.
Posted Content
English Conversational Telephone Speech Recognition by Humans and Machines
George Saon,Gakuto Kurata,Tom Sercu,Kartik Audhkhasi,Samuel Thomas,Dimitrios Dimitriadis,Xiaodong Cui,Bhuvana Ramabhadran,Michael Picheny,Lynn-Li Lim,Bergul Roomi,Phil Hall +11 more
TL;DR: An independent set of human performance measurements on two conversational tasks are performed and it is found that human performance may be considerably better than what was earlier reported, giving the community a significantly harder goal to achieve.
Posted Content
Progressive Neural Networks for Transfer Learning in Emotion Recognition
TL;DR: Progressive neural networks provide a way to transfer knowledge and avoid the forgetting effect present when pre-training neural networks on different tasks, and transfer learning can effectively leverage additional datasets to improve the performance of emotion recognition systems.
Proceedings ArticleDOI
Progressive neural networks for transfer learning in emotion recognition
TL;DR: In this article, the authors investigate how knowledge can be transferred between three paralinguistic tasks: speaker, emotion, and gender recognition, using Progressive Neural Networks (PNNs).