VERBMOBIL: the evolution of a complex large speech-to-speech translation system

Bub, Thomas; Schwinn, Johannes

doi:10.21437/icslp.1996-564

Cited by 6 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Integrating ChatGPT into existing design and engineering software poses another challenge (Bub and Schwinn, 1996;Bub and Schwinn, 1999;Alpers et al, 2019;Tang et al, 2021;Abler et al, 2023;Karunasena et al, 2022). Professionals often use specialized tools like Computer-Aided Design (CAD) and Building Information Modeling (BIM).…”

Section: Challenges Of Integrating Chatgpt In Architectural Design An...mentioning

confidence: 99%

Integrating ChatGPT, Bard, and Leading-Edge Generative Artificial Intelligence in Architectural Design and Engineering: Applications, Framework, and Challenges

Rane,

Choudhary,

Rane

2023

IJARP

View full text Add to dashboard Cite

This research paper investigates the integration of advanced generative artificial intelligence (AI) models, such as ChatGPT, Bard, and similar architectures, in architectural design and engineering. The comprehensive study explores various aspects, including applications, frameworks, challenges, and prospective developments in the context of architectural design and architectural engineering. In architectural design, the paper investigates the transformative impact on Architectural Theory, highlighting how generative AI fosters creativity and innovation in design thinking. The Design Process is scrutinized, showcasing how AI models streamline ideation, iteration, and collaboration among design teams. Furthermore, the research examines the influence of generative AI in Interior Design, Urban Design and Planning, and considers nuanced aspects of Cultural and Social factors, elucidating how these technologies contribute to inclusive and context-sensitive design practices. In architectural engineering, the study assesses the integration of generative AI in Structural Engineering, demonstrating its potential to optimize and innovate structural analysis and designs for enhanced safety and efficiency. It explores applications in Building Systems and Construction Management, illustrating how AI can streamline project workflows and resource allocation. The impact of generative AI on compliance with Building Codes and Regulations is analyzed, emphasizing its potential for error reduction and adherence to standards. Additionally, the research probes into the influence of AI in Materials and Construction Technology, highlighting advancements in material selection and construction methodologies. The paper also investigates the role of generative AI in promoting Sustainability and Environmental Design, showcasing its potential to optimize energy efficiency, reduce environmental impact, and enhance overall sustainability. Finally, the paper outlines the challenges and future directions for development to fully harness the potential of generative AI in shaping the future of architectural design and engineering.

show abstract

Section: Challenges Of Integrating Chatgpt In Architectural Design An...mentioning

confidence: 99%

Integrating ChatGPT, Bard, and Leading-Edge Generative Artificial Intelligence in Architectural Design and Engineering: Applications, Framework, and Challenges

Rane,

Choudhary,

Rane

2023

IJARP

View full text Add to dashboard Cite

show abstract

“…Phase one of the German VERBMOBIL project (see [2] and [8]) already had very ambitious goals: a translation system for spontaneous human-to-human business appointment scheduling dialogues was to be developed. A first prototype was presented in 1995.…”

Section: The Scenariomentioning

confidence: 99%

Dovetailing of acoustics and prosody in spontaneous speech recognition

Buckow¹,

Batliner²,

Huber³

et al. 1998

5th International Conference on Spoken Language Processing (ICSLP 1998)

View full text Add to dashboard Cite

Prosody can be applied to improve the performance of spontaneous speech translation systems like VERBMOBIL. In VERB-MOBIL we previously augmented the output of a word recognizer with prosodic information. Here we present a new approach of interleaving word recognition and prosodic processing. While we still use the output of a word recognizer to determine phrase boundaries, we do not wait until the end of the utterance before we start processing. Instead we intercept chunks of word hypotheses during the forward search of the recognizer. Neural networks and language models are used to predict phrase boundaries. Those boundary hypotheses, in turn, are used by the recognizer to cut the stream of incoming speech into syntactic-prosodic phrases. Thus, incremental processing is possible. We investigate which features are suited for incremental prosodic processing and compare them w.r.t. classification performance and efficiency. We show that with a set of features that can be computed efficiently classification results are achieved which are almost as good as those with the previously used computationally more expensive features.

show abstract

Dialogue Intent Classification with Long Short-Term Memory Networks

Lian

Huang

2018

Natural Language Processing and Chinese Computing

View full text Add to dashboard Cite

VERBMOBIL: the evolution of a complex large speech-to-speech translation system

Cited by 6 publications

References 0 publications

Integrating ChatGPT, Bard, and Leading-Edge Generative Artificial Intelligence in Architectural Design and Engineering: Applications, Framework, and Challenges

Integrating ChatGPT, Bard, and Leading-Edge Generative Artificial Intelligence in Architectural Design and Engineering: Applications, Framework, and Challenges

Dovetailing of acoustics and prosody in spontaneous speech recognition

Dialogue Intent Classification with Long Short-Term Memory Networks

Contact Info

Product

Resources

About