Speech recognition algorithms for connectionist hybrids

Projektinformationen

SPRACH

ID Finanzhilfevereinbarung: FP4_20077

Projekt abgeschlossen

Startdatum 15 Dezember 1995

Enddatum 14 Dezember 1998

Finanziert unter

• Specific research and technological development programme in the field of information technologies, 1994-1998

Gesamtkosten

€ 1 909 000,00

EU-Beitrag

€ 1 620 000,00

Koordiniert durch

FACULTE POLYTECHNIQUE DE MONS
Belgium

CORDIS bietet Links zu öffentlichen Ergebnissen und Veröffentlichungen von HORIZONT-Projekten.

Links zu Ergebnissen und Veröffentlichungen von RP7-Projekten sowie Links zu einigen Typen spezifischer Ergebnisse wie Datensätzen und Software werden dynamisch von OpenAIRE abgerufen.

Verwertbare Ergebnisse

Speech recognition algorithms for connectionist hybrids

The basic theme of this project, referred to as SPRACH (SPeech Recognition Algorithms for Connectionist Hybrids), is to further develop new theories, algorithms, hardware and software tools for the extension of hybrid Hidden Markov Models (HMM) and artificial neural network (ANN) methods for different continuous speech recognition systems. The project also extends the results to new languages (UK English, French and Portuguese) and to flexible speech recognition systems that can easily be adapted to new domains with new lexica and new syntaxes. On top of substantial theoretical results, it was demonstrated, using standard international reference databases, that the hybrid HMM/ANN approaches lead to competitive state-of-the-art systems. Furthermore, the investigated hybrid approach was shown to have additional advantages in terms of central processing unit (CPU) utilization and memory bandwidth and has proven to be more flexible and more robust. In addition to building on the WERNICKE project a large vocabulary continuous speech recognition system, SPRACH investigates the development of systems for smaller, task independent applications, with no need to retrain the system or develop a new lexicon or grammar when moving from one task to another. Applications that are developed in this project include: very large vocabulary (64K words) continuous speech recognition of read speech (this is an essential enabling technology for many multimedia and telematics applications); voice-driven typewriter (a dictation system running in real time with simple editing commands; flexible continuous speech recognizer in which lexica and grammars can be defined on the spot, without the need of training.; smaller (but realistic) tasks, including for example, robust recognition of free format numbers; recognition of broadcast speech (transcription of radio or television speech).