Zobrazeno 1 - 10
of 311
pro vyhledávání: '"Waibel, Alex"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 7, Pp 313-325 (2019)
Speech translation has traditionally been approached through cascaded models consisting of a speech recognizer trained on a corpus of transcribed speech, and a machine translation system trained on parallel texts. Several recent works have shown the
Externí odkaz:
https://doaj.org/article/ec0209656f3c4c0cb272740ed21cee1d
Publikováno v:
Pol\'ak, P., Yan, B., Watanabe, S., Waibel, A., Bojar, O. (2023) Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff. Proc. INTERSPEECH 2023, 3979-3983
Blockwise self-attentional encoder models have recently emerged as one promising end-to-end approach to simultaneous speech translation. These models employ a blockwise beam search with hypothesis reliability scoring to determine when to wait for mor
Externí odkaz:
http://arxiv.org/abs/2309.11379
Autor:
Bärmann, Leonard, Kartmann, Rainer, Peller-Konrad, Fabian, Niehues, Jan, Waibel, Alex, Asfour, Tamim
Natural-language dialog is key for intuitive human-robot interaction. It can be used not only to express humans' intents, but also to communicate instructions for improvement if a robot does not understand a command correctly. Of great importance is
Externí odkaz:
http://arxiv.org/abs/2309.04316
In many humanitarian scenarios, translation into severely low resource languages often does not require a universal translation engine, but a dedicated text-specific translation engine. For example, healthcare records, hygienic procedures, government
Externí odkaz:
http://arxiv.org/abs/2305.03873
Multilingual speech recognition with supervised learning has achieved great results as reflected in recent research. With the development of pretraining methods on audio and text data, it is imperative to transfer the knowledge from unsupervised mult
Externí odkaz:
http://arxiv.org/abs/2205.12304
Autor:
Zhou, Zhong, Waibel, Alex
Publikováno v:
In Proceedings of the LoResMT Workshop of the 18th Biennial Machine Translation Summit in 2021
We translate a closed text that is known in advance and available in many languages into a new and severely low resource language. Most human translation efforts adopt a portion-based approach to translate consecutive pages/chapters in order, which m
Externí odkaz:
http://arxiv.org/abs/2108.07127
Autor:
Zhou, Zhong, Waibel, Alex
Publikováno v:
In Proceedings of the 3rd Workshop on Research in Computational Typology and Multilingual NLP of the 20th Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technologies in 2021
We translate a closed text that is known in advance into a severely low resource language by leveraging massive source parallelism. In other words, given a text in 124 source languages, we translate it into a severely low resource language using only
Externí odkaz:
http://arxiv.org/abs/2104.05848
Achieving super-human performance in recognizing human speech has been a goal for several decades, as researchers have worked on increasingly challenging tasks. In the 1990's it was discovered, that conversational speech between two humans turns out
Externí odkaz:
http://arxiv.org/abs/2010.03449
Autor:
Constantin, Stefan, Waibel, Alex
We propose a dialog system utility component that gets the last two utterances of a user and can detect whether the last utterance is an error correction of the second last utterance. If yes, it corrects the second last utterance according to the err
Externí odkaz:
http://arxiv.org/abs/2004.04243
Recently sequence-to-sequence models have started to achieve state-of-the-art performance on standard speech recognition tasks when processing audio data in batch mode, i.e., the complete audio data is available when starting processing. However, whe
Externí odkaz:
http://arxiv.org/abs/2003.10022