Recognition of spelled names over the telephone and rejection of data out of the spelling lexicon

This paper deals with the recognition of spelled names over the telephone. It introduces an efficient way of handling the spelling grammar, that is the lexicon of the allowed spelled names. The proposed approach is based on a forward-backward algorithm. The constraints on the sequences of letters are derived from the lexicon and are used by the A* algorithm in the backward pass. This forward-backward approach is compared to a 2-pass approach, which relies on a discrete HMM based retrieval procedure. The rejection of incorrect data is also investigated, based on the comparison of a lexicon constrained solution with an unconstrained decoding. The approaches are compared on field data collected from a vocal directory service. Results are presented for the recognition of valid spelled names and for the rejection of incorrect data (non-spelling and noise tokens and spellings not in the lexicon). The results show the efficiency of the proposed forward-backward procedure.

[1]  Jean Monné,et al.  Speaker-independent spelling recognition over the telephone , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Jean-François Mari,et al.  An N-best strategy, dynamic grammars and selectively trained neural networks for real-time recognition of continuously spelled names over the telephone , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[3]  Alexander H. Waibel,et al.  Recognition of spelled names over the telephone , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[4]  Jean-Claude Junqua,et al.  Robustness improvements in continuously spelled names over the telephone , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Jean Monné,et al.  Application of the n-best solutions algorithm to speaker-independent spelling recognition over the telephone , 1993, EUROSPEECH.