Phonetic fragment search in speech data

• US 7,401,019 B2
• Filed: 01/15/2004
• Issued: 07/15/2008
• Est. Priority Date: 01/15/2004
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Chang, Eric I-Chao, Seide, Frank T.
• Primary Examiner(s): Hudspeth; David R.
• Assistant Examiner(s): Neway; Samuel G
• Application Number:
  US10/757,885
• Publication Number:
  US 20050159953A1
• Time in Patent Office: 1,643 Days
• Field of Search: None
• US Class Current: 704/254
• CPC Class Codes: G10L 15/10 using distance or distortion measures between unknown speech and reference templates
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units

Abstract

A method of searching audio data is provided including receiving a query defining multiple phonetic possibilities. The method also includes comparing the query with a lattice of phonetic hypotheses associated with the audio data to identify if at least one of the multiple phonetic possibilities is approximated by at least one phonetic hypothesis in the lattice of phonetic hypotheses.

Claims

1. A method of generating a lattice from audio data, comprising:

recognizing phonetic fragments within the audio data wherein at least some of the phonetic fragments include at least two phones;

accessing a mutual information score for recognized phonetic fragments within the audio data that include at least two phones, wherein the mutual information score for each of the phonetic fragments having at least two phones is a function of a likelihood that phones in the phonetic fragment occur consecutively and a likelihood that each phone in the phonetic fragment occurs independent of other phones in the phonetic fragment; and

determining a score for paths joining adjacent phonetic fragments in the audio data using in part the mutual information score for the phonetic fragments having at least two phones.

2. The method of claim 1 and further comprising:

calculating time values and individual acoustic scores for each phone of each of the phonetic fragments.

3. The method of claim 1 and further comprising:

pruning paths that have a score that does not meet a threshold level.

4. The method of claim 1 and further comprising:

collapsing a plurality of audio frames in the audio data into a single audio frame.