Papers by Alex Waibel
ELITR Multilingual Live Subtitling: Demo and Strategy (2021.eacl-demos)
Copied to clipboard
Ondřej Bojar, Dominik Macháček, Sangeet Sagar, Otakar Smrž, Jonáš Kratochvíl, Peter Polák, Ebrahim Ansari, Mohammad Mahmoudi, Rishu Kumar, Dario Franceschini, Chiara Canton, Ivan Simonini, Thai-Son Nguyen, Felix Schneider, Sebastian Stüker, Alex Waibel, Barry Haddow, Rico Sennrich, Philip Williams
| Challenge: | Using a prototype, we present an automatic speech translation system for live subtitling of conference speech . the system is routinely tested in recognizing English, Czech, and German speech - and presenting it simultaneously into 42 target languages. |
| Approach: | They propose an automatic speech translation system aimed at live subtitling of conference presentations. |
| Outcome: | The proposed system is a working prototype that is routinely tested in recognizing English, Czech, and German speech and presenting it translated simultaneously into 42 target languages. |
DaCToR: A Data Collection Tool for the RELATER Project (2020.lrec-1)
Copied to clipboard
| Challenge: | Obtaining sufficient amount of data is often a problem for low-resource languages, such as dialects or non-written languages. |
| Approach: | They propose to collect domain-specific data in Arabic by collecting read texts by speakers in the respective countries and districts in which the dialects are spoken. |
| Outcome: | The proposed tool collects read texts by speakers in the countries and districts in which the dialects are spoken. |
Self-Attentional Models for Lattice Inputs (P19-1)
Copied to clipboard
| Challenge: | Existing work has extended recurrent neural networks to model lattice inputs but these models suffer from slow computation speeds. |
| Approach: | They propose to extend the paradigm of self-attention to handle lattice inputs by adding probabilistic reachability masks that incorporate latticae structure into the model and support lattics if available. |
| Outcome: | The proposed model outperforms baseline models while being much faster to compute than previous models. |
Incremental processing of noisy user utterances in the spoken language understanding task (D19-55)
Copied to clipboard
| Challenge: | triggered actions with high executions times can cause dialog systems to react slowly due to high latency and high latex. |
| Approach: | They propose a model-agnostic method to achieve high quality in processing incrementally produced partial utterances. |
| Outcome: | The proposed method improves the metric F1-score by 47.91 percentage points . the proposed method can be used to create low-latency natural language understanding components on ATIS datasets. |
BULBasaa: A Bilingual Basaa-French Speech Corpus for the Evaluation of Language Documentation Tools (L18-1)
Copied to clipboard
Fatima Hamlaoui, Emmanuel-Moselly Makasso, Markus Müller, Jonas Engelmann, Gilles Adda, Alex Waibel, Sebastian Stüker
| Challenge: | Approximately 50 hours of Bàsàá speech were collected and then carefully re-spoken and orally translated into French . |
| Approach: | They propose to provide an automatic phonetic transcription using a set of derived phone-like units. |
| Outcome: | The proposed method provides an automatic phonetic transcription using a set of derived phone-like units. |
Automated Evaluation of Out-of-Context Errors (L18-1)
Copied to clipboard
| Challenge: | Existing methods to modify text understanding systems use only one sentence at a time . however, considering a larger context can improve performance for text understanding tasks. |
| Approach: | They propose to modify existing text data to insert out-of-context errors . they use a 2016 TEDTalk corpus to evaluate computational models for text understanding . |
| Outcome: | The proposed method targets real-world problems of transcription and translation systems by inserting authentic out-of-context errors. |