Automated hotel attendant using speech recognition

Details Automated hotel attendant using speech recognition Automated hotel attendant using speech recognition

1998-04-30

2001-11-06

Tsang, Fan (Department: 2645)

Telephonic communications

Audio message storage, retrieval, or synthesis

Voice activation or recognition

C379S216010, C704S258000, C704S266000

Reexamination Certificate

active

06314165

ABSTRACT:

BACKGROUND AND SUMMARY OF THE INVENTION
The present invention relates generally to an automated hotel attendant system, and more particularly to an automated hotel attendant system that utilizes a lexicon training system to automatically train a speech recognizer as well as to maintain a hotel guest database.
Automatic attendants are commonly being implemented in office type environments. Typically, these automatic attendants are using phonetic-based recognizers to perform call routing functions in conjunction with a private branch exchange (PBX).
In speech recognition applications, phonetic transcriptions for each word in the dictionary are needed to build the models for the speech recognizer prior to use. Traditionally, phonetic transcriptions are manually created by lexicographers who are skilled in the nuances of phonetic pronunciation of the particular language of interest. Developing a good phonetic transcription for each word in the dictionary is time consuming and requires a great deal of skill. Moreover, a dictionary for use in an automatic attendant would not generally be complete with respect to surnames. Although phonetic transcriptions for each surname could possible be generated for each person in the relatively static office type environment, this approach is not feasible for implementing an automated attendant in a constantly changing application, such as the surnames in a hotel guest database.
Much of the labor and specialized expertise for generating phonetic transcriptions can be dispensed with by using a lexicon training system to automatically build the models for the speech recognizer of an automated attendant. The lexicon training system of the present invention extends current recognition systems to recognize words, such as surname and geographic locations, that are not currently found in existing dictionaries. A robust and reliable phoneticizer for generating multiple pronunciations from the written form of a name is one important aspect of this lexicon training system. Once the pronunciation of a surname is known, it is then possible to build a speaker-independent speech recognition model that can be used to automatically train and/or update a speech recognizer for use in an automated attendant.
Accordingly, the automated attendant of the present invention incorporates the above-described principles and is ideally suited for incorporation with hotel registration and telephone systems. The automated hotel attendant provides call routing functions along with other additional services to hotel guests without the need to be connected to a hotel operator. A hotel registration system receives and stores the spelled names of hotel guests as well as assigns each guest an associated telephone extension. A lexicon training system is connected to the hotel registration system for generating pronunciations for each spelled name by converting the characters that spell those names into word-phoneme data. This word-phoneme data is in turn stored in a lexicon that is used by a speech recognition system. An automated attendant is coupled to the speech recognition system for converting a spoken name of a hotel guest entered from one of the telephone extensions into a predefined hotel guest name that can be used to retrieve an assigned telephone extension from the hotel registration system. Next, the automated attendant causes the telephone switching system to call the requested telephone extension in response to the entry of the spoken name from one of the telephone extensions.


REFERENCES:
patent: 5212730 (1993-05-01), Wheatley et al.
patent: 5752230 (1998-05-01), Alonso-Cedo
patent: 5930336 (1999-07-01), Junqua et al.
patent: 6016471 (2000-01-01), Kuhn et al.
patent: 6029132 (2000-02-01), Kuhn et al.
patent: 6049594 (2000-04-01), Furman et al.
patent: 6092044 (2000-07-01), Baker et al.
patent: 6230131 (2001-05-01), Kuhn et al.
patent: 6233553 (2001-05-01), Contolini et al.
patent: WO 99/26232 (1999-05-01), None
patent: 0 562 138 A1 (1993-09-01), None
patent: 0 568 979 A1 (1993-11-01), None
Asadi, Schwartz & Makhoul “Automatic Modeling for Adding New Words to a Large-Vocabulary Continuous Speech Recognition System” 1991 IEEE Publications pp. 305-308.

Affiliated with

Also associated with

Rating

Automated hotel attendant using speech recognition does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Automated hotel attendant using speech recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Automated hotel attendant using speech recognition will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2603966