Norbert Braunschweiler

Publication Activity (10 Years)

Years Active: 2000-2024
Publications (10 Years): 19

Top Topics

Dialogue System

Speech Synthesis

Question Answering

Top Venues

IEEE J. Sel. Top. Signal Process.

Publications

Abigail Sticha, Norbert Braunschweiler, Rama Sanand Doddipatla, Kate M. Knill
Advancing Faithfulness of Large Language Models in Goal-Oriented Dialogue Question Answering. CUI (2024)
Alexander Frummet, Andrea Papenmeier, Maik Fröbe, Johannes Kiesel, Vaibhav Adlakha, Norbert Braunschweiler, Mateusz Dubiel, Satanu Ghosh, Marcel Gohsen, Christin Kreutz, Milad Momeni, Markus Nilles, Sachin Pathiyan Cherumanal, Abbas Pirmoradi, Paul Thomas, Johanne R. Trippas, Ines Zelch, Oleg Zendel
Report on the 8th Workshop on Search-Oriented Conversational Artificial Intelligence (SCAI 2024) at CHIIR 2024. SIGIR Forum 58 (1) (2024)
Norbert Braunschweiler, Rama Sanand Doddipatla, Simon Keizer, Svetlana Stoyanchev
Enabling Semi-Structured Knowledge Access via a Question-Answering Module in Task-oriented Dialogue Systems. CUI (2023)
Simon Keizer, Caroline Dockes, Norbert Braunschweiler, Svetlana Stoyanchev, Rama Doddipatla
Adversarial learning of neural user simulators for dialogue policy optimisation. CoRR (2023)
Norbert Braunschweiler, Rama Doddipatla, Simon Keizer, Svetlana Stoyanchev
Evaluating Large Language Models for Document-grounded Response Generation in Information-Seeking Dialogues. CoRR (2023)
Daichi Hayakawa, Takehiko Kagoshima, Kenji Iwata, Norbert Braunschweiler, Rama Doddipatla
Robust Recognition of Speaker Emotion With Difference Feature Extraction Using a Few Enrollment Utterances. ASRU (2023)
Simon Keizer, Norbert Braunschweiler, Svetlana Stoyanchev, Rama Doddipatla
Dialogue Strategy Adaptation to New Action Sets Using Multi-dimensional Modelling. CoRR (2022)
Norbert Braunschweiler, Rama Doddipatla, Simon Keizer, Svetlana Stoyanchev
Factors in Emotion Recognition With Deep Learning Models Using Speech and Text on Multiple Corpora. IEEE Signal Process. Lett. 29 (2022)
Svetlana Stoyanchev, Suraj Pandey, Simon Keizer, Norbert Braunschweiler, Rama Sanand Doddipatla
Combining Structured and Unstructured Knowledge in an Interactive Search Dialogue System. SIGDIAL (2022)
Norbert Braunschweiler, Rama Doddipatla, Simon Keizer, Svetlana Stoyanchev
A study on cross-corpus speech emotion recognition and data augmentation. CoRR (2022)
Norbert Braunschweiler, Rama Doddipatla, Simon Keizer, Svetlana Stoyanchev
A Study on Cross-Corpus Speech Emotion Recognition and Data Augmentation. ASRU (2021)
Alexandry Augustin, Alexandros Papangelis, Margarita Kotti, Pavlos Vougiouklis, Jonathon Hare, Norbert Braunschweiler
Open-domain Topic Identification of Out-of-domain Utterances using Wikipedia. CoRR (2021)
Simon Keizer, Norbert Braunschweiler, Svetlana Stoyanchev, Rama Doddipatla
Dialogue Strategy Adaptation to New Action Sets Using Multi-Dimensional Modelling. ASRU (2021)
Norbert Braunschweiler, Panagiotis Papadakos, Margarita Kotti, Yannis Marketakis, Yannis Tzitzikas
Crowd-Sourced Collection of Task-Oriented Human-Human Dialogues in a Multi-domain Scenario. TSD (2019)
Norbert Braunschweiler, Alexandros Papangelis
Comparison of an End-to-end Trainable Dialogue System with a Modular Statistical Dialogue System. INTERSPEECH (2018)
Rama Doddipatla, Norbert Braunschweiler, Ranniery Maia
Speaker Adaptation in DNN-Based Speech Synthesis Using d-Vectors. INTERSPEECH (2017)
Petko Nikolov Petkov, Norbert Braunschweiler, Yannis Stylianou
Automated Pause Insertion for Improved Intelligibility Under Reverberation. INTERSPEECH (2016)
Norbert Braunschweiler, Ranniery Maia
Pause Prediction from Text for Speech Synthesis with User-Definable Pause Insertion Likelihood Threshold. INTERSPEECH (2016)
Langzhou Chen, Norbert Braunschweiler, Mark J. F. Gales
Speaker and Expression Factorization for Audiobook Data: Expressiveness and Transplantation. IEEE ACM Trans. Audio Speech Lang. Process. 23 (4) (2015)
Langzhou Chen, Norbert Braunschweiler
Enabling controllability for continuous expression space. INTERSPEECH (2014)
Langzhou Chen, Norbert Braunschweiler, Mark J. F. Gales
Speaker dependent expression predictor from text: Expressiveness and transplantation. ICASSP (2014)
Langzhou Chen, Mark J. F. Gales, Norbert Braunschweiler, Masami Akamine, Kate Knill
Integrated Expression Prediction and Speech Synthesis From Text. IEEE J. Sel. Top. Signal Process. 8 (2) (2014)
Vincent Wan, Javier Latorre, Kayoko Yanagisawa, Norbert Braunschweiler, Langzhou Chen, Mark J. F. Gales, Masami Akamine
Building HMM-TTS Voices on Diverse Data. IEEE J. Sel. Top. Signal Process. 8 (2) (2014)
Langzhou Chen, Norbert Braunschweiler
Unsupervised speaker and expression factorization for multi-speaker expressive synthesis of ebooks. INTERSPEECH (2013)
Vincent Wan, Robert Anderson, Art Blokland, Norbert Braunschweiler, Langzhou Chen, BalaKrishna Kolluru, Javier Latorre, Ranniery Maia, Björn Stenger, Kayoko Yanagisawa, Yannis Stylianou, Masami Akamine, M. J. F. Gales, Roberto Cipolla
Photo-realistic expressive text to talking head synthesis. INTERSPEECH (2013)
Langzhou Chen, Mark J. F. Gales, Norbert Braunschweiler, Masami Akamine, Kate Knill
Integrated automatic expression prediction and speech synthesis from text. ICASSP (2013)
Norbert Braunschweiler, Langzhou Chen
Automatic detection of inhalation breath pauses for improved pause modelling in HMM-TTS. SSW (2013)
Heiga Zen, Norbert Braunschweiler, Sabine Buchholz, Mark J. F. Gales, Kate Knill, Sacha Krstulovic, Javier Latorre
Statistical Parametric Speech Synthesis Based on Speaker and Language Factorization. IEEE Trans. Speech Audio Process. 20 (6) (2012)
Florian Eyben, Sabine Buchholz, Norbert Braunschweiler, Javier Latorre, Vincent Wan, Mark J. F. Gales, Kate Knill
Unsupervised clustering of emotion and voice styles for expressive TTS. ICASSP (2012)
Norbert Braunschweiler, Sabine Buchholz
Automatic Sentence Selection from Speech Corpora Including Diverse Speech for Improved HMM-TTS Synthesis Quality. INTERSPEECH (2011)
Masatsune Tamura, Norbert Braunschweiler, Takehiko Kagoshima, Masami Akamine
Unit selection speech synthesis using multiple speech units at non-adjacent segments for prosody and waveform generation. ICASSP (2010)
Norbert Braunschweiler, Mark J. F. Gales, Sabine Buchholz
Lightly supervised recognition for automatic alignment of large coherent speech recordings. INTERSPEECH (2010)
Heiga Zen, Norbert Braunschweiler, Sabine Buchholz, Kate Knill, Sacha Krstulovic, Javier Latorre
HMM-based polyglot speech synthesis by speaker and language adaptive training. SSW (2010)
Heiga Zen, Norbert Braunschweiler
Context-dependent additive log f_0 model for HMM-based speech synthesis. INTERSPEECH (2009)
Gabriel Webster, Norbert Braunschweiler
An evaluation of non-standard features for grapheme-to-phoneme conversion. INTERSPEECH (2008)
Tanya Lambert, Norbert Braunschweiler, Sabine Buchholz
How (not) to select your voice corpus: random selection vs. phonologically balanced. SSW (2007)
Antje Schweitzer, Norbert Braunschweiler, Grzegorz Dogil, Bernd Möbius
Assessing the acceptability of the Smartkom speech synthesis voices. SSW (2004)
Antje Schweitzer, Norbert Braunschweiler, Tanja Klankert, Bernd Möbius, Bettina Säuberlich
Restricted unlimited domain synthesis. INTERSPEECH (2003)
Norbert Braunschweiler
Automatic Labeling of Prosodic Events. KONVENS (2000)