Efficient empirical determination, computation, and use of acoustic confusability measures

• US 10,748,527 B2
• Filed: 10/12/2018
• Issued: 08/18/2020
• Est. Priority Date: 10/31/2002
• Status: Active Grant

• Current Assignee: Promptu Systems Corporation
• Original Assignee: Promptu Systems Corporation
• Inventors: Printz, Harry, Chittar, Naren
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US16/158,900
• Publication Number:
  US 20190051294A1
• Time in Patent Office: 676 Days
• Field of Search: 704231, 704236, 704240, 704243, 704244, 704255
• CPC Class Codes: G06F 16/95 Retrieval from the web
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/142 Hidden Markov Models [HMMs]
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units

Abstract

Efficient empirical determination, computation, and use of an acoustic confusability measure comprises: (1) an empirically derived acoustic confusability measure, comprising a means for determining the acoustic confusability between any two textual phrases in a given language, where the measure of acoustic confusability is empirically derived from examples of the application of a specific speech recognition technology, where the procedure does not require access to the internal computational models of the speech recognition technology, and does not depend upon any particular internal structure or modeling technique, and where the procedure is based upon iterative improvement from an initial estimate; (2) techniques for efficient computation of empirically derived acoustic confusability measure, comprising means for efficient application of an acoustic confusability score, allowing practical application to very large-scale problems; and (3) a method for using acoustic confusability measures to make principled choices about which specific phrases to make recognizable by a speech recognition application.

Claims

1. A method for generating an acoustic confusability measure, comprising:

recognizing, via a speech recognition system, at least one utterance within a corpus of utterances, said corpus comprising utterances with corresponding reliable transcriptions, each reliable transcription having at least one associated reliable phoneme sequence, to yield at least one recognized word sequence, each said recognized word sequence having at least one associated recognized phoneme sequence; and

generating an empirically derived acoustic confusability measure from analysis of pairs of phoneme sequences, each said pair of phoneme sequences comprising one said associated recognized phoneme sequence and one said associated reliable phoneme sequence, wherein constituents of each said pair of phoneme sequences are associated with a common utterance within said corpus of utterances, said empirically derived acoustic confusability measure comprising a family of probability models over a phoneme alphabet, wherein the family of probability models is based in part on Laplace'"'"'s law of succession.

2. The method of claim 1, wherein said family of probability models over the phoneme alphabet is a family of conditional probability models over a phoneme alphabet.

3. The method of claim 1, wherein said phoneme alphabet includes an empty phoneme.