CSTR Project Archive

(this is an incomplete list)

• AMI: Augmented Multiparty Interaction: AMI is an EU Integrated Project about computer enhanced multi-modal interaction in the context of meetings
• AMIDA: Augmented Multiparty Interaction with Distance Access: AMIDA is an EU Integrated Project, following on from AMI, about computer enhanced multi-modal interaction in the context of meetings
• The Articulatory Database Registry: A directory of articulatory data resources
• BARKS: The BARKS project is exploring the use of switching linear dynamic models for automatic speech recognition.
• Cougar: The Cougar project investigates using an articulatory(-like) domain for the calculation of join costs in conjunction with smoothing unit transitions in unit selection speech synthesis.
• EMIME: Enhanced Multilingual Interaction in Mobile Environments: EMIME is an EU project about personalised speech synthesis and speech-to-speech translation
• ESLASR: ESLASR aims to improve the quality of automatic speech recognition using loosely-coupled HMMs with articulatory-acoustic features.
• Espresso: Novel acoustic models for ASR
• Expressions: Expressions aims to improve the quality of prosody and intonation for unit selection speech synthesis.
• EUSTACE: Edinburgh University Speech Timing Archive and Corpus of English: The EUSTACE corpus comprises 4608 spoken sentences designed to examine a number of durational effects in speech.
• Feature MLPs: A freely available set of articulatory feature MLPs trained on 2000 hours of conversational telephone speech.
• Evaluating pitch determination algorithms: Paul Bagshaw's database for evaluating pitch determination algorithms
• ID4S: Intonation in Dialogue for Speech Recognition
• Instrumented Meeting Room (AMIDA WP3): Smart room environments for communication scene analysis
• M4: Multimodal Meeting Manager: M4 was concerned with the construction of a demonstration system to enable structuring, browsing and querying of an archive of automatically analysed meetings.
• SABLE: The Sable Consortium
• Satissfy: Statistical Analysis of Text In Speech Synthesis
• Sole: The Spoken Output Labelling Explorer
• SVitchboard: Small vocabulary tasks from Switchboard
• TESS: Testing Evaluation of Speech Synthesis: TESS is a project designed to investigate the psychoacoustic processes underlying human auditory evaluation of synthetic speech, with the goal of developing more perceptually principled evaluation methods.
• Unisyn Lexicon: A keysymbol lexicon
• Voice transformation: Transforming the quality and intonation of the speech of one speaker so that it sounds like another speaker
• Welsh: Welsh Speech Database