![[ intranet ]](/images/menu_intranet.png)
![[ festival ]](/images/menu_festival.png)
CSTR News
December 2012
Best Paper Award. Congratulations to Pawel Swietojanski who won the IBM Best Student Paper Award at IEEE Spoken Language Technology workshop (held in Miami) for his paper Unsupervised Cross-lingual Knowledge Transfer in DNN-based LVCSR co-authored with Arnab Ghoshal and Steve Renals.
December 2012
UK and Ireland Speech Meeting. About 10 people from CSTR attended the UK and Ireland Speech Conference in Birmingham.
November 2012
SICSA Distinguished Visiting Fellow. Prof Mari Ostendorf, from the University of Washington, visited for 2 two weeks. She gave a number of seminars and a half-day masterclass on Extraction of Social Meaning from Language.
November 2012
New PhD Student. Welcome to Tom Merritt, who is a new PhD student. He will be part of the NST project, working with Simon King on speech synthesis.
November 2012
SICSA DemoFest. CSTR people demoed speech synthesis, speech recognition and speech translation at the DemoFest.
October 2012
New PhD Student. Welcome to Siva Reddy, who is a new PhD student. He will be part of the uDialogue project, working with Steve Renals and Junichi Yamagishi on distributed and neural network language modelling for speech recognition.
October 2012
Visiting researcher. Welcome to Maria Astrinaki, a PhD student in Thierry Dutoit's group in Mons, who will be working on speech synthesis.
September 2012
Interspeech-2012. Twelve CSTR researchers attended Interspeech-2012 in Portland, Oregon, presenting a total of eighteen papers. There were also papers from CSTR at the SAPA-SCALE and Blizzard workshops.
September 2012
New PhD Student. Welcome to Rasmus Dall, who is a new PhD student. He will be part of the uDialogue project, working with Simon King and Junichi Yamagishi on speech synthesis.
September 2012
New PhD Student. Welcome to Qiong Hu, who is a new PhD student. She will be working with Junichi Yamagishi on speech synthesis.
September 2012
New Research Fellow. Welcome to Joris Driesen, who joins us from KU Leuven. He'll be working part of the EU-Bridge project, working on speech recognition.
September 2012
Farewell. Farewell to Mike Lincoln, who has spun out Quorate Technology which focuses on audio search.
August 2012
Visiting researcher. Welcome to Pierre Lanchantin, visiting CSTR for a week from Cambridge University, part of the NST project. He will be working on speech synthesis.
July 2012
New project. Spoken Interaction with Interpretation in Switzerland (SIWIS) funded by the Swiss National Science Foundation Sinergia programme during 2012-2015, with Idiap, ETH Zürich, and the University of Geneva.
July 2012
New project. Speech synthesis for the blind (SALB - Sprachsynthese von Auditiven Lehrbüchern für Blinde SchülerInnen), funded by the Sparkling Science programme of the Federal Ministry of Science and Research (BMWF), Austria during 2013-2014, with ftw.
July 2012
Visiting researcher. Welcome to Yoshitaka Mamiya, visiting CSTR from the Japan Patent Office. He will be working on speech synthesis.
June 2012
Visiting researcher. Welcome to Sayaka Shiota, research fellow (PD) of the Japan Society for the Promotion of Science (JSPS), who is visiting CSTR for five months from Nagoya Institute of Technology. She will be working on speaker diarization and nonparametric Bayesian approaches.
June 2012
New Book. Multimodal Signal Processing: Human Interactions in Meetings, edited by Steve Renals, Hervé Bourlard, Jean Carletta, and Andrei Popescu-Belis, has been published by Cambridge University Press. Including chapters co-authored by five current or former CSTR researchers, the book presents the most important achievements of the past decade in the field of audio, video and multimodal processing, with an application to meeting recordings. Many of these advances happened in the AMI and AMIDA projects.
June 2012
CSTR Interns. Welcome to three summer intern students: Chris Bryant working on listening tests and speech analysis with Cassie Mayo and Luisa Garcia Lecumberri; Clemens Wolff working with Hiroshi Shimodaira on head motion synthesis from text for animated social agents; and Mona Paun working with Simon King on an Android App for personalised speech synthesis.
May 2011
Oliver Watts' PhD viva. Congratulations to Oliver Watts who successfully defended his thesis, Unsupervised Learning for Text-to-Speech Synthesis at his PhD viva.
May 2012
Visiting researchers. Welcome to Ikerbasque Research Professor Martin Cooke and Dr Luisa Garcia Lecumberri from the Language and Speech Laboratory at the UPV-EHU in Vitoria, who will be visiting for a few months. Martin is coordinator of the LISTA project.
May 2012
The Listening Talker Workshop. CSTR hosts the Listening Talker workshop, bringing together linguistics, psychologists, neuroscientists, engineers and others working on human and machine speech perception and production, to explore new approaches to context-sensitive speech generation.
May 2012
New Research Fellow. Welcome to Catherine Lai, who joins us from University of Pennsylvania. She'll be working on the InEvent project.
April 2012
DMMA.3. Version 3 of the Digital MEMS Microphone Array has been constructed and is under test. Based on the USBPAL from Rigisystems and using eight Analog Devices digital MEMS microphones ADMP441, the DMMA.3 is a circular microphone array with a diameter of 4 cm (ideal to fit onto your pocket size mobile device).
April 2012
NST Annual Meeting. CSTR hosted the annual meeting of the Natural Speech Technology programme grant with the user group and advisory board.
April 2012
New Research Fellow. Welcome to Atef Ben Youssef, who joins us from Grenoble Institute of Technology. He'll be working on SSPNet.
April 2012
JST CREST Symposium on Human-Harmonized Information Technology. Steve Renals gave an invited talk, Natural Speech Technology, at the JST CREST Symposium on Human-Harmonized Information Technology in Kyoto.
March 2012
ICASSP-2012. Several CSTR researchers attended ICASSP-2012 in Kyoto. Cassia Valentini-Botinhao presented a talk (Cepstral Analysis Based on the Glimpse Proportion Measure for Improving the Intelligibility of HMM-Based Synthetic Speech in Noise), Erich Zwyssig presented a talk (On the Effect of SNR and Superdirective Beamforming in Speaker Diarisation in Meetings) and a poster (Determining the Number of Speakers in a Meeting Using Microphone Array Features), and Liang Lu presented a poster (Maximum a Posteriori Adaptation of Subspace Gaussian Mixture Models for Cross-Lingual Speech Recognition).
March 2012
Summer internships.
We have a number of paid internships available during summer 2012. Further details...
March 2012
Workshop on Innovation and Applications in Speech Technology. Steve Renals (keynote, "Natural Speech Technology"), Christophe Veaux (talk on Voice Reconstruction), and Matthew Aylett (talk on Personification using affective speech synthesis) presenting at Workshop on Innovation and Applications in Speech Technology, Dublin.
March 2012
Inaugural Lecture Online. Simon King's inaugural lecture now on University of Edinburgh YouTube channel: Using Speech Synthesis To Give Everyone Their Own Voice.
February 2012
PhD studentships in Speech Technology.
We have a number of fully-funded PhD positions available for September 2012 start (details). For funding reasons, we are particularly interested in strong applicants from the EU.
February 2012
Open Research Positions.
CSTR is recruiting - Two postdoctoral researchers in speech technology (details) and a senior researcher in speech technology (details). We are looking for people with experience in statistical modelling or machine learning for speech recognition or synthesis.
February 2012
Inaugural Lecture. Simon King's inaugural lecture on 6 Feb 2012, Using Speech Synthesis To Give Everyone Their Own Voice.
February 2012
New project - INSPIRE. INSPIRE is a Marie Curie Initial Training Network, concerned with investigating speech processing in realistic environments.
February 2012
Knowledge Transfer Partnership with Orange/France Telecom. The aim of this KTP is to improve automatic voice building through development/integration of novel automatic speech recognition techniques and build commercial-grade systems for bringing personalised speech technology to Orange customers.
February 2012
New project - EU-Bridge. EU-Bridge is a three year project which will develop automatic transcription and translation technology to enable innovative multimedia captioning and translation services of audiovisual documents between European and non-European languages. The project will provide streaming technology that can convert speech from lectures, meetings, and telephone conversations into the text in another language. Within Edinburgh CSTR will work closely with the Statistical Machine Translation Group.
January 2012
Royal Society Industry Fellowship for Matthew Aylett. Matthew Aylett has been awarded a 4-year Royal Society Industry Fellowship, on Personification of embodied conversational agents with regards to expressive voice quality.
January 2012
IEEE technical committee. Korin Richmond, elected to IEEE Signal Processing Society Speech and Language Processing Technical Committee.
December 2011
ASRU 2011. Arnab Ghoshal and Liang Lu presenting at ASRU 2011in Hawaii (Kaldi toolkit presentation, poster on SGMMs for cross-lingual ASR).
December 2011
Workshop on Image and Speech Processing. Steve Renals (invited talk, "Natural Speech Technology") presenting at WISP-2011, Hyderabad.
December 2011
Roberto Barra-Chicote's PhD defence. Congratulations to former CSTR visitor Roberto Barra-Chicote who successfully defended his PhD thesis.
November 2011
New research fellows. Welcome to Arnab Ghoshal who joins us from University of the Saarland and Heng Lu who joins us from USTC. They will be working on the Natural Speech Technology programme grant.
November 2011
EPSRC Fellowship for Junichi Yamagishi. Junichi Yamagishi has been awarded a 5-year EPSRC Career Advancement Fellowship, Deep architectures for statistical speech synthesis.
November 2011
New project - Simple4All. Coordinated by CSTR, Simple4All is a three-year EU project concerned with creating multilingual speech synthesis technology that learns from data with little or no expert supervision and continually improves itself, simply by being used.
November 2011
New project - InEvent. InEvent is a three year project whose main goal is to develop new means to structure, retrieve, and share large archives of networked, and dynamically changing, multimedia recordings, mainly consisting of meetings, video-conferences, and lectures.
October 2011
New project - uDialogue. Joint with Nagoya Institute of Technology, this is a five year project concerned with crowdsourcing multimodal dialogue systems, speech synthesis, and speech recognition.
October 2011
Demo service - PodCastle. CSTR speech recognition used to power the English language version of the AIST PodCastle service which enables searching of speech data such as podcasts, individual audio or video files on the web, and video clips on video sharing services (e.g. YouTube).
September 2011
New PhD students. Welcome to Pawel Swietojanski who will be working on the Natural Speech Technology programme grant, and Benigno Uría working with ANC and CSTR, supported by an EPSRC CASE studentship with Novauris.
August 2011
Radio 4 Word of Mouth. Steve Renals discusses the Natural Speech Technology programme grant on the BBC Radio 4 programme Word of Mouth
July 2011
John Niekrasz's PhD viva. Congratulations to John Niekrasz successfully defending his thesis at his PhD viva.
June 2011
Partha Lal's PhD viva. Congratulations to Partha Lal successfully defending his thesis at his PhD viva.