ASR for automatic directory assistance: The SMADA project

In this paper we summarise the state-of-the-art for automatic speech recognition in automated Directory Assistance at the start of the 5th Framework project SMADA. Details are given about robust acoustic features for use in Distributed Speech Recognition, especially with respect to noise suppression. Then an overview is given of the confidence measures which are in use today, and their similarities and differences. Finally, work aimed at automatic update of acoustic models and automatic inference of language models is sketched that is becoming possible thanks to the very large amounts of data that can be recorded in operational services. In addition to summarising the state-of-the-art the paper also indicates the lines along which the research in SMADA will develop.

[1]  Denis Jouvet,et al.  Use of a confidence measure based on frame level likelihood ratios for the rejection of incorrect data , 1999, EUROSPEECH.

[2]  Biing-Hwang Juang,et al.  Discriminative utterance verification for connected digits recognition , 1995, IEEE Trans. Speech Audio Process..

[3]  R. McAulay,et al.  Speech enhancement using a soft-decision noise suppression filter , 1980 .

[4]  Renato De Mori,et al.  The Application of Semantic Classification Trees to Natural Language Understanding , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Louis Boves,et al.  Weighting phone confidence measures for automatic speech recognition , 2000 .

[6]  Jean Monné,et al.  Recognition of spelled names over the telephone and rejection of data out of the spelling lexicon , 1999, EUROSPEECH.

[7]  F. Canavesio,et al.  Automation of Telecom Italia directory assistance service: field trial results , 1998, Proceedings 1998 IEEE 4th Workshop Interactive Voice Technology for Telecommunications Applications. IVTTA '98 (Cat. No.98TH8376).

[8]  Tony Vitale,et al.  An Algorithm for High Accuracy Name Pronunciation by Parametric Speech Synthesizer , 1991, Comput. Linguistics.

[9]  Katarina Bartkova,et al.  Usefulness of phonetic parameters in a rejection procedure of an HMM-based speech recognition system , 1997, EUROSPEECH.

[10]  Katarina Bartkova,et al.  Language based phone model combination for ASR adaptation to foreign accent , 1999 .

[11]  Delphine Charlet,et al.  Confidence measure and incremental adaptation for the rejection of incorrect data , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).