M.Woszczyna, N.Coccaro, A.Eisele, A.Lavie, A.McNair, T.Polzin, I.Rogina, C.P.Rose, T.Sloboda, M.Tomita, J.Tsutsumi, N.Aoki-Waibel, A.Waibel, W.Ward: Recent Advances in JANUS, a Speech to Speech Translation System, Proceedings of the EUROSPEECH, Berlin, 1993. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Modelling Unknown Words in Spontaneous Speech - Kemp, Jusek (1996) (6 citations) (Correct)
....triphones can be employed, however, in the experiments described in this paper no cross word models were used. After recognition, a maximum likelihood codebook adaptation using the recognition result and an additional recognition run are performed. For a more detailed description, refer to [5] [11] 12] 9] The JANUS 2 decoder achieved a word error rate of 28.6 in the VERBMOBIL June 95 evaluation. This was the lowest error rate of the 5 participating institutions. For reasons of efficiency, in the experiments described we skipped the final adaptation step and reduced the number of ....
M. Woszczyna, N. Coccaro, A. Eisele, A. Lavie, A. McNair, T. Polzin, I. Rogina, C.P. Rose, T. Sloboda, M. Tomita, J. Tsutsumi, N. Aoki-Waibel, A. Waibel, W. Ward, Recent Advances in Janus, a Speech-to-Speech Translation System, Proc. EUROSPEECH 1993, pp. 1295-1298
Dictionary Learning For Spontaneous Speech Recognition - Sloboda, Waibel (1996) (12 citations) Self-citation (Sloboda Waibel) (Correct)
No context found.
M.Woszczyna, N.Coccaro, A.Eisele, A.Lavie, A.McNair, T.Polzin, I.Rogina, C.P.Rose, T.Sloboda, M.Tomita, J.Tsutsumi, N.Aoki-Waibel, A.Waibel, W.Ward: Recent Advances in JANUS, a Speech to Speech Translation System, Proceedings of the EUROSPEECH, Berlin, 1993.
Dictionary Learning For Spontaneous Speech Recognition - Tilo Sloboda (1996) (12 citations) Self-citation (Sloboda Waibel) (Correct)
No context found.
M.Woszczyna, N.Coccaro, A.Eisele, A.Lavie, A.McNair, T.Polzin, I.Rogina, C.P.Rose, T.Sloboda, M.Tomita, J.Tsutsumi, N.Aoki-Waibel, A.Waibel, W.Ward: Recent Advances in JANUS, a Speech to Speech Translation System, Proceedings of the EUROSPEECH, Berlin, 1993.
Inferring Linguistic Structure In Spoken Language - Woszczyna, Waibel (1994) (6 citations) Self-citation (Woszczyna Waibel) (Correct)
....70.0 400 classes 73.9 400 hand build classes 74.1 Table 1. Classification of the current state 3.2. Modeling Speech Acts with Markov Chains The experiment of section 3. 1 was repeated for the speech acts used in the translation component of JANUS, our speech to speech translation system [1, 2]. The training and test data for this experiment was taken form handwritten Interlingua structures used for parserevaluation. The Interlingua structure contains a semantic representation for a sentence, including speech acts to represent the global intention. For this task, 15 speech acts were ....
M. Woszczyna, N. Coccaro, A. Eisele, A. Lavie, A. McNair, T. Polzin, I. Rogina, C.P. Rose, T. Sloboda, M. Tomita, J. Tsutsumi, N. Aoki-Waibel, A. Waibel, and W. Ward, Recent Advances in Janus, a Speech to Speech Translation System, EUROSPEECH 1993, volume 2, pp 1295--1299.
JANUS 93: Towards Spontaneous Speech Translation - Woszczyna, Aoki-Waibel, Buĝ, .. (1994) (3 citations) Self-citation (Woszczyna Coccaro Lavie Mcnair Polzin Rogina Rose Tomita Aoki-waibel) (Correct)
....Engine have been upgraded to deal with requirements introduced by spontaneous human to human dialogs. To allow for development and evaluation of our system on adequate data, a large database with spontaneous scheduling dialogs is being gathered for English, German and Spanish. 1. OVERVIEW JANUS [1, 2] has been among early systems to attempt the translation of spoken dialogs. It had initially been built based on a speech database of 12 read dialogs of the conference registration task, encompassing a vocabulary of around 500 words. It was designed as a speaker independent system which translates ....
M. Woszczyna, N. Coccaro, A. Eisele, A. Lavie, A. McNair, T .Polzin, I. Rogina, C.P. Rose, T. Sloboda, M. Tomita, J. Tsutsumi, N. Aoki-Waibel, A. Waibel, and W. Ward, Recent Advances in Janus, a Speech to Speech Translation System, EUROSPEECH 1993.
Dictionary Learning: Performance through Consistency - Sloboda (1995) (18 citations) Self-citation (Sloboda) (Correct)
....that they model the given occurrences of words in the database. We show how even a simple approach can lead to significant improvements in recognition performance. First experiments have been performed on the German Spontaneous Scheduling Task (GSST) using the speech recognition engine of JANUS 2 [4, 5, 6], the spontaneous speech to speech translation system of the Interactive Systems Laboratories at Carnegie Mellon and Karlsruhe University. 1. INTRODUCTION The phonetic dictionary is one of the main knowledgesources for a speech recognizer, to lead it to valid hypotheses in the recognition ....
....amount of new data is added to the database will also help to keep the dictionary consistent. 2.1. Outline of Algorithm A We modified a pre trained speech recognizer for the given task to run as a phoneme recognizer with smoothed phoneme bigrams (e.g. based on our JANUS speech recognition engine [4, 5, 6] in context independent mode 1 ) Using this setup, Dictionary Learning can be performed by the following algorithm: 1. create word labels for the whole training set and a phoneme confusion matrix for the underlying speech recognizer 2. collect all appearances of each word in the database, run ....
M.Woszczyna, N.Coccaro, A.Eisele, A.Lavie, A.McNair, T.Polzin, I.Rogina, C.P.Rose, T.Sloboda, M.Tomita, J.Tsutsumi, N.Aoki-Waibel, A.Waibel, W.Ward: Recent Advances in Janus, a Speech to Speech Translation System, Proceedings of the EUROSPEECH, Berlin, 1993.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC