The Centre for Speech Technology Research, The university of Edinburgh

CSTR News



April 2014

Young Scientist's Prize. Congratulations to Junichi Yamagishi, who has been awarded the Japanese Ministry of Education, Culture, Sports, Science and Technology Young Scientists’ Prize.

March 2014

NICT collaboration. Peter Bell and Pawel Swietojanski are invited scientific visitors at NICT Spoken Language Communications Laboratory in Kyoto, Japan for one month.

February 2014

U-STAR. CSTR is now a member of the U-STAR Consortium. U-STAR, the Universal Speech Translation Advanced Research, currently comprises 28 institutes from 23 countries, and has been conducting various workshops around the world and ongoing research on speech translation.

February 2014

Kate Knill visit. Kate Knill (University of Cambridge) visited and gave a talk entitled Investigation of multilingual speech-to-text systems for use in spoken term detection.

January 2014

Farewell. SSPNet researcher Atef Ben Youssef has moved on to LIMSI-CNRS in Paris.

January 2014

Tony Robinson visit. Tony Robinson (Cantab Research) visited and gave a talk entitled Will recurrent neural network language models scale?.

December 2013

Best Paper Award. Congratulations to Liang Lu who won the IBM Best Paper Award at the IEEE ASRU workshop (held in Olomouc) for his paper Acoustic Data-driven Pronunciation Lexicon for Large Vocabulary Speech Recognition co-authored with Arnab Ghoshal and Steve Renals.

December 2013

New Project. ROCKIT, the Roadmap for Conversational Interaction Technologies, is a new EC Support Action coordinated by CSTR. Its main goal is the construction of a research and innovation roadmap for natural spoken and multimodal interaction.

November 2013

Farewell. NST researchers Arnab Ghoshal and Heng Lu have moved on to Apple and Nuance respectively.

November 2013

PhD Studentships in Data Science. Ten fully funded PhD studentships available in data science as part of a new Centre for Doctoral Training in Data Science. Topics include machine learning, databases, natural language processing, speech processing, and other areas. This is a 4-year PhD programme that includes MSc-level coursework, and so is suitable for students coming directly from a Bachelor’s degree. Funded by EPSRC and the University of Edinburgh.

November 2013

IEEE Fellow. Steve Renals elevated to IEEE Fellow.

November 2013

Tatsuya Kawahara visit. Prof Tatsuya Kawahara (Kyoto University) visited and gave a talk entitled Automatic transcription system for the Japanese Parliament (Diet).

November 2013

Ultrafest. We hosted Ultrafest VI in the Informatics Forum. This was the sixth Ultrafest meeting of researchers working with Ultrasound imaging technology for linguistic analysis. Tanja Schultz gave a keynote talk entitled Silent Speech Interfaces.

October 2013

Jeff Adams visit. Jeff Adams (Amazon) visited and gave a talk entitled Speech and NLP at Amazon - Unique Challenges, Unique Resources.

October 2013

Marie Curie Fellow. Welcome to Gustav Henter, a new Marie Curie Fellow on the INSPIRE Initial Training Network. Gustav will be working on controllable speech synthesis aimed at speech perception research, and has just finished his PhD at KTH.

October 2013

Visiting researcher. Welcome to Santi Pascual, just graduated from UPC, Barcelona, who is visiting for 3 months to work on a proof-of-concept project about incremental / real-time speech synthesis for communication aids.

October 2013

Senior Area Editor. Steve Renals was appointed Senior Area Editor of the IEEE Transactions on Audio, Speech, and Language Processing.

September 2013

Naohiro Tawara and Tetsuji Ogawa visit. Naohiro Tawara and Tetsuji Ogawa from Waseda University visited, and Naohiro Tawara gave a talk entitled Sampling-based fully Bayesian speaker modeling for hierarchical data

September 2013

New PhD Student. Welcome to Sam Ribeiro, a new PhD student working with Rob Clark on the SIWIS project.

September 2013

New PhD Student. Welcome to Kathrin Haag, a new PhD student working with Hiroshi Shimodaira.

September 2013

New PhD Student. Welcome to Leimin Tian, a new PhD student working with Johanna Moore and Catherine Lai.

September 2013

New PhD Student. Welcome to Herman Kamper, a new PhD student working with Sharon Goldwater and Simon King.

September 2013

Visiting researcher. Welcome to Tuomo Raitio, a PhD student from Aalto University, Finland (a partner on Simple4All) who is visiting for 6 months. Tuomo works on vocoding for HMM synthesis (the GlottHMM system).

September 2013

Visiting researcher. Welcome to Shinji Takaki, a PhD student from Nagoya Institute of Technology (a partner on uDialogue), who is visiting for 6 months. Shinji works on acoustic modelling for HMM synthesis and is part of the HTS team.

September 2013

New Project. Reel Lives: personal documentaries constructed from digital data, funded by EPSRC Ideas Factory Sandpit.

September 2013

SSW-2013. Several CSTR researchers attended the 8th ISCA Speech Synthesis Workshop, presenting 11 papers in all. Simon King and Junichi Yamagishi were on the programme committee, and Simon King co-chaired the Blizzard Challenge workshop.

August 2013

Interspeech-2013. Several CSTR researchers attended Interspeech, presenting about 16 papers in total. Cassie Mayo, Korin Richmond, and Junichi Yamagishi all co-organised special sessions.

August 2013

Visiting researcher. Welcome to Soheil Khorram, a PhD student from Sharif University of Technology, Iran who is visiting for 6 months and is working on HMM speech synthesis.

August 2013

Visiting researcher. Welcome to Wei Zhang from Ocean University, China who is visiting for a year and is working on speech synthesis.

August 2013

IVA conference. IVA 2013, the Thirteenth International Conference on Intelligent Virtual Agents, takes place during 29-31 August 2013 in the Informatics Forum.

August 2013

uDialogue workshop. A number of colleagues from Nagoya Institute of Technology visit CSTR for a 2-day uDialogue workshop.

August 2013

Ranniery Maya visit. Ranniery Maya (Toshiba Research Europe, Cambridge) visited and gave a talk entitled Complex cepstrum-based speech representation and application to statistical parametric speech synthesis

August 2013

Michael Wand visit. Michael Wand (Karlsruhe Institute of Technology) visited and gave a talk entitled Advances in Signal Processing and Modeling for Electromyographic Speech Processing and Recognition

August 2013

Cassia Valentini-Botinhao's PhD viva. Congratulations to Cassia Valentini-Botinhao who successfully defended her thesis, Intelligibility Enhancement of Synthetic Speech in Noise at her PhD viva.

July 2013

Speech Graphics. CSTR spinout Speech Graphics provide the facial animation for Kanye West's interactive Black Skinhead music video - see the article in Wired.

July 2013

Maurizio Omologo visit. Maurizio Omologo (FBK, Trento) visited and gave a talk entitled The DIRHA project: goals and preliminary results

July 2013

Erich Zwyssig's PhD viva. Congratulations to Erich Zwyssig who successfully defended his thesis, Speech Processing using Digital MEMS Microphones at his PhD viva.

June 2013

NOLISP. Steve Renals gave an invited keynote at the Non-linear Speech Processing Workshop in Mons entitled Neural Networks for Speech Recognition.

June 2013

Kiyasu Award. Congratulations to Junichi Yamagishi who has won the 2012 Kiyasu Special Industrial Achievement Award from the Information Processing Society of Japan for Establishment of a Next-Generation Approach to Speech Synthesis Based on Hidden Markov Models. The award was shared with the four other core developers of HTS.

June 2013

CSTR Interns. Welcome to two summer intern students: Xin Yun Suzanna Sia working on meeting browsing with Jonathan Kilgour and Steve Renals, and Richard Williams working on Idlak speech synthesis with Matthew Aylett and Arnab Ghoshal.

May 2013

NST Annual Meeting. CSTR hosted the annual meeting of the Natural Speech Technology programme grant with the user group and advisory board.

May 2013

Mike Seltzer visit. Mike Seltzer (Microsoft Research, Redmond) visited and gave a talk entitled Improving the Performance of Deep Neural Network Acoustic Models using Side Information

May 2013

Liang Lu's PhD viva. Congratulations to Liang Lu who successfully defended his thesis, Subspace Gaussian Mixture Models for Automatic Speech Recognition at his PhD viva.

May 2013

New Project. Delivering personalised voices for patients with MND, funded by the MRC Confidence in Concept programme.

April 2013

Microsoft Research Machine Learning Summit. Steve Renals gave a talk at the Microsoft Research Machine Learning Summit in Paris entitled Multi-domain Acoustic Modelling for Speech Recognition.

March 2013

New Software Developer. Welcome to Gergely Bakos, who joins us from the University of East Anglia. He'll be working in the Voice Bank project.

March 2013

New Research Fellow. Welcome to Qiang Huang, who joins us from the University of East Anglia. He'll be working as part of the uDialogue project, working on spoken language processing.

February 2013

Joint faculty position. Congratulations to Junichi Yamagishi who has been appointed to a joint position between the University of Edinburgh and the National Institute of Informatics in Tokyo.

February 2013

Rogier van Dalen visit. Rogier van Dalen (University of Cambridge) visited and gave a talk entitled The expectation semiring in speech recognition

January 2013

Old News