In ICASSP 2017, MINI@Sheffield together with the Chinese University of Hong Kong and the University of Hong Kong make publicly available ShefCE — a Cantonese English bilingual parallel speech corpus. Please see our corpus page.
Read more10 papers on domain identification, RNNLM, language recognition, speaker diariasation, ASR error analysis, spoken dialogue system, noise compensation, Arabic ASR and our release of speech data and speech technology system were accepted to Interspeech 2016. The papers are:- Doulaty M., Saz, O., Ng, R. W. M., and Hain, T., “Automatic Genre and Show Identification of…
Read moreMINI will be represented with 4 papers at the IEEE Automatic Speech Recognition and Understanding (ASRU) workshop that will take place in Arizona on December 2015 (http://asru2015.org/). ASRU brings together some of the most forefront researchers in speech recognition to discuss new ideas for research in several topics. The contributions of MINI will be focused…
Read moreThe homeService paper “Speech-Enabled Environmental Control in an AAL setting for people with Speech Disorders: a Case Study” has been accepted at TechAAL 2015 (IET International Conference on Technologies for Active and Assisted Living) for an oral presentation. Heidi Christensen is going to present this work on the 5th of November at Kingston University London’s…
Read moreRaymond represented MINI and introduced our research on speech recognition and machine translation to general public in Sheffield Mobile University 2015 held on 26/Sep Refer to the Sheffield mobile university homepage.
Read moreYesterday Sarah passed her viva with minor corrections. Her thesis topic is “Conversational Arabic Automatic Speech Recognition”. Congratulations Dr Al-Shareef!
Read moreThe paper Knowledge transfer between speakers for personalised dialogue management has been accepted on the 16th Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL 2015) which will be held on September 2-4 in Prague, Czech Republic.
Read more[metaslider id=526] Looking at a blank canvas always kindles a small part of your mind to mess it up and draw something on it.. Well .. thanks to the snow last Thursday (29 Jan), we had four very large white canvases in the Regent court to fill up. We used them all ^_^ .. Just…
Read moreWe invite applications for a position as Research Associate in the Speech and Hearing (SpandH) research group at Sheffield University to work on research into novel algorithms with application to automatic speech recognition, and possibly to speaker identification or language recognition. The post holder will work in the context of several projects, most notably the…
Read moreHerman Kamper, Febe de Wet, Thomas Hain and Thomas Niesler (2014). Capitalising on North American speech resources for the development of a South African English large vocabulary speech recognition system. To appear in CSL.
Read more
