Search Results - "Stuker, Sebastian"

Linguistic Unit Discovery from Multi-Modal Inputs in Unwritten Languages: Summary of the "Speaking Rosetta" JSALT 2017 Workshop by Scharenborg, Odette, Besacier, Laurent, Black, Alan, Hasegawa-Johnson, Mark, Metze, Florian, Neubig, Graham, Stuker, Sebastian, Godard, Pierre, Muller, Markus, Ondel, Lucas, Palaskar, Shruti, Arthur, Philip, Ciannella, Francesco, Du, Mingxing, Larsen, Elin, Merkx, Danny, Riad, Rachid, Wang, Liming, Dupoux, Emmanuel

“…We summarize the accomplishments of a multi-disciplinary workshop exploring the computational and scientific issues surrounding the discovery of linguistic…”
Get full text

Multilingual shifting deep bottleneck features for low-resource ASR by Quoc Bao Nguyen, Gehring, Jonas, Muller, Markus, Stuker, Sebastian, Waibel, Alex

“…In this work, we propose a deep bottleneck feature architecture that is able to leverage data from multiple languages. We also show that tonal features are…”
Get full text

Training time reduction and performance improvements from multilingual techniques on the BABEL ASR task by Stuker, Sebastian, Muller, Markus, Quoc Bao Nguyen, Waibel, Alex

“…In the IARPA sponsored program BABEL we are faced with the challenge of training automatic speech recognition systems in sparse data conditions in very little…”
Get full text

Improving Sequence-To-Sequence Speech Recognition Training with On-The-Fly Data Augmentation by Nguyen, Thai-Son, Stuker, Sebastian, Niehues, Jan, Waibel, Alex

“…Sequence-to-Sequence (S2S) models recently started to show state-of-the-art performance for automatic speech recognition (ASR). With these large and deep…”
Get full text

Speech Technology for Unwritten Languages by Scharenborg, Odette, Ondel, Lucas, Palaskar, Shruti, Arthur, Philip, Ciannella, Francesco, Du, Mingxing, Larsen, Elin, Merkx, Danny, Riad, Rachid, Wang, Liming, Dupoux, Emmanuel, Besacier, Laurent, Black, Alan, Hasegawa-Johnson, Mark, Metze, Florian, Neubig, Graham, Stuker, Sebastian, Godard, Pierre, Muller, Markus

“…Speech technology plays an important role in our everyday life. Among others, speech is used for human-computer interaction, for instance for information…”
Get full text

Neural Codes to Factor Language in Multilingual Speech Recognition by Muller, Markus, Stuker, Sebastian, Waibel, Alex

“…In the past, we adapted neural network based multilingual acoustic models using language codes. In this work, we study the extracted language codes and the…”
Get full text

Speech interaction strategies for a humanoid assistant by Stüker, Sebastian, Constantin, Stefan, Niehues, Jan, Nguyen, Thai-Son, Müller, Markus, Pham, Ngoc Quan, Rüde, Robin, Waibel, Alex

“…The goal of SecondHands, a H2020 project, is to design a robot that can offer help to a maintenance technician in a proactive manner. The robot is to act as a…”
Get full text

Towards phoneme inventory discovery for documentation of unwritten languages by Muller, Markus, Franke, Jorg, Waibel, Alex, Stuker, Sebastian

“…Documenting unwritten languages is a challenging task, even for trained specialists. To help linguists in better and faster documenting new languages is the…”
Get full text

Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition by Huber, Christian, Hussain, Juan, Stuker, Sebastian, Waibel, Alexander

“…Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition (ASR). When using appropriate modeling units, e.g.,…”
Get full text

An automatic system for the simultaneous translation of lectures by Stüker, Sebastian

Get full text

Semi-supervised training in low-resource ASR and KWS by Metze, Florian, Gandhe, Ankur, Yajie Miao, Sheikh, Zaid, Yun Wang, Di Xu, Hao Zhang, Jungsuk Kim, Lane, Ian, Won Kyum Lee, Stuker, Sebastian, Muller, Markus

“…In particular for "low resource" Keyword Search (KWS) and Speech-to-Text (STT) tasks, more untranscribed test data may be available than training data. Several…”
Get full text

Multi-stage Large Language Model Correction for Speech Recognition by Pu, Jie, Nguyen, Thai-Son, Stüker, Sebastian

“…In this paper, we investigate the usage of large language models (LLMs) to improve the performance of competitive speech recognition systems. Different from…”
Get full text

Modified polyphone decision tree specialization for porting multilingual Grapheme based ASR systems to new languages by Stuker, S.

“…Automatic speech recognition (ASR) systems have been developed only for a very limited number of the estimated 7,000 languages in the world. In order to avoid…”
Get full text

Toward Cross-Domain Speech Recognition with End-to-End Models by Nguyen, Thai-Son, Stüker, Sebastian, Waibel, Alex

“…In the area of multi-domain speech recognition, research in the past focused on hybrid acoustic models to build cross-domain and domain-invariant speech…”
Get full text

Research Opportunities In Automatic Speech-To-Speech Translation by Stuker, S., Herrmann, T., Kolss, M., Niehues, J., Wolfel, M.

“…The field of speech-to-speech translation is a "well-established area of research that has a noteworthy tradition. It addresses a problem-the communication…”
Get full text

Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition by Huber, Christian, Hussain, Juan, Stüker, Sebastian, Waibel, Alexander

“…Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition (ASR). When using appropriate modeling units, e.g.,…”
Get full text

A hybrid phonotactic language identification system with an SVM back-end for simultaneous lecture translation by Heck, M., Stuker, S., Waibel, A.

“…In this paper we describe our work in constructing a language identification system for use in our simultaneous lecture translation system. We first built PPR…”
Get full text

Neural Language Codes for Multilingual Acoustic Models by Müller, Markus, Stüker, Sebastian, Waibel, Alex

“…Multilingual Speech Recognition is one of the most costly AI problems, because each language (7,000+) and even different accents require their own acoustic…”
Get full text

Multilingual Adaptation of RNN Based ASR Systems by Müller, Markus, Stüker, Sebastian, Waibel, Alex

“…In this work, we focus on multilingual systems based on recurrent neural networks (RNNs), trained using the Connectionist Temporal Classification (CTC) loss…”
Get full text

Phonemic and Graphemic Multilingual CTC Based Speech Recognition by Müller, Markus, Stüker, Sebastian, Waibel, Alex

“…Training automatic speech recognition (ASR) systems requires large amounts of data in the target language in order to achieve good performance. Whereas large…”
Get full text