Siegfried Kunzmann

Multilingual acoustic models for speech recognition and synthesis

In this paper, we review the design of a common phone alphabet for up to fifteen languages and describe its application in two important components of a seamless multilingual conversational system, namely speech recognition and synthesis. We report on experiments that demonstrate the advantages of multilingual acoustic models both for the recognition of foreign names and non-native speech, and describe the usefulness of a common phone alphabet for the construction of unit selection based mono- and bilingual speech synthesis systems.

Multimodal output for a conversational telephony system

The IBM hotel information system was designed to make information, stored on Internet or enterprise backend servers, available in a natural dialog over the telephone. The system combines robust speech recognition with natural language and dialog components to allow the user to request the information in a human-human-like dialog. A summary of the information provided in the conversation like the address and phone number of a hotel is sent additionally to the users mobile phone as an SMS message. The system design combines spoken and textual output.

French–German Bilingual Acoustic Modeling for Embedded Voice Driven Applications

Multilingual access to information and services is a key requirement in any pervasive or ubiquitous computing environment. In this paper we describe our efforts towards multilingual speech recognition with a focus on applications that are designed to run on embedded devices, like e.g. a commercially available PDA. We give an overview on speech recognition techniques suited for the special requirements of the expected phonetic and acoustic environments and explore the ability to create multilingual acoustic models and applications that are able to run on embedded devices in real-time.

Multi-lingual and multi-modal speech processing and applications

Over the last decade voice technologies for telephony and embedded solutions became much more mature, resulting in applications providing mobile access to digital information from anywhere. Both a growing demand for voice driven applications in many languages and the need for improved usability and user experience now drives the exploration of multi-lingual speech processing techniques for recognition, synthesis and conversational dialog management. In this overview article we discuss our recent activities on multi-lingual voice technologies and describe the benefits of multi-lingual modeling for the creation of multi-modal mobile and telephony applications.

Multilinguale Spracherkennung und Sprachsynthese

Im hinter uns liegenden Kapitel haben wir zunachst den zunehmenden Ein satz von Sprachverarbeitungstechnologien zur ortsungebundenen Interaktion zwischen Mensch und Computer skizziert und die mathematisch-technischen Grundlagen heutiger Spracherkennungs- und -synthesesysteme knapp umrissen. Die Entwicklung von deren Kernkomponenten hat sich uns dabei als ein fur viele Sprachen weitgehend einheitlicher, maschineller Lernprozess dargestellt, bei dem die freien Parameter eines stochastischen Modells der menschlichen Sprachproduktion anhand groser Mengen von sprachen- und anwendungsspezifischen Trainingsdaten ermittelt werden.

Multi-modal voice application design in a multi-client environment

The seamless access to information and services is a key requirement for any pervasive or ubiquitous computing environment, and the access via any client is becoming a more and more feature within this scenario. The paper describes our efforts towards a multi–client voice application with focus on an embedded client, like e.g. a commercially available PDA. We give an overview on speech recognition techniques suited for the special requirements of the expected acoustic environments and explore the ability to design applications that are able to run on different voice and GUI capable devices.