Multi-lingual translation of spontaneously spoken language in a limited domain (1996) [21 citations — 9 self]
Abstract:
JANUS is a multi-lingual speech-tospeech translation system designed to facilitate communication between two parties engaged in a spontaneous conversation in a limited domain. In an attempt to achieve both robustness and translation accuracy we use two different translation components: the GLR module, designed to be more accurate, and the Phoenix module, designed to be more robust. We analyze the strengths and weaknesses of each of the approaches and describe our work on combining them. Another recent focus has been on developing a detailed endto-end evaluation procedure to measure the performance and effectiveness of the system. We present our most recent Spanish-to-English performance evaluation results.
Citations
| 54 | Understanding Spontaneous Speech: the Phoenix System – Ward - 1991 |
| 45 | An efficient augmented context-free parsing algorithm – Tomita - 1987 |
| 40 | Discourse processing of dialogues with multiple threads – Rosé, Eugenio, et al. - 1995 |
| 31 | GLR* - An Efficient Noise Skipping Parsing Algorithm for Context Free Grammars – Lavie, Tomita - 1993 |
| 27 | An Integrated Heuristic Scheme for Partial Parse Evaluation – Lavie - 1994 |
| 24 | Extracting Information in Spontaneous Speech – Ward - 1994 |
| 18 | End-to-end Evaluation in JANUS: a Speech-to-speech Translation System – Gates, Lavie, et al. - 1996 |
| 17 | The Generalized LR Parser/Compiler - Version 8.4 – Tomita - 1990 |
| 7 | Nyberg 3rd. Generation Kit and Transformation Kit, Version 3.2: User's Manual – Tomita, H - 1988 |
| 2 | Discourse processing of dialogues with multiple threads – ykema - 1995 |
| 1 | GLR* - An EJficient Noise ,5'kippmg Parsing Algorithm for Context Free Grammars – l, avie, et al. - 1993 |
| 1 | Understanding Spontaneous Speech: tile Phoenix System – Ward - 1991 |

