Converting partial word lists into a phoneme tree for speech recognition

• US 8,620,656 B2
• Filed: 03/04/2012
• Issued: 12/31/2013
• Est. Priority Date: 11/30/2010
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Fu, Guo Kang, Han, Zhao Bing, Jia, Bin, Liu, Ying
• Primary Examiner(s): Smits, Talivaldis Ivars
• Application Number:
  US13/411,614
• Publication Number:
  US 20120166197A1
• Time in Patent Office: 667 Days
• Field of Search: None
• US Class Current: 704/242
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams

Abstract

The present invention discloses converting a text form into a speech. In the present invention, partial word lists of a data source are obtained by parsing the data source in parallel or in series. The partial word lists are then compiled to obtain phoneme graphs corresponding, respectively, to the partial word lists, and then the obtained phoneme graphs are combined. Speech recognition is then conducted according to the combination results. According to the present invention, computational complexity may be reduced and recognition efficiency may be improved during speech recognition.

Claims

1. A computer implemented method of converting a text form into a phoneme tree, comprising:

parsing a data source in the text form to obtain a plurality of partial word lists of the data source, the data source comprising content of a web page;

compiling the plurality of partial word lists to create a plurality of phoneme graphs, each phoneme graph corresponding to a respective partial word list, each phoneme graph including a root node, a plurality of phonemes, and an end node;

combining the plurality of phoneme graphs to form the phoneme tree, wherein the phoneme tree includes at least a first phoneme graph and a second phoneme graph sharing a common root node and a common end node.

2. The method according to claim 1, further comprising:

judging whether the phoneme tree has sufficient information to conduct speech recognition; and

responsive to judging that there is sufficient information, conducting the speech recognition using the phoneme tree.

3. The method according to claim 1, wherein under a circumstance that the data source changes responsive to a user clicking on a link of a rendering of the web page, continuing the combination of the created phoneme graphs into the phoneme tree and caching the phoneme tree for use by the speech recognizer while a data parser parses the changed data source to obtain updated partial word lists, one or more compilers compile the updated partial word lists to create updated phoneme graphs corresponding, respectively, to the updated partial word lists, and a combiner combines the created updated phoneme graphs into an updated phoneme tree that is then used by the speech recognizer to conduct the speech recognition of the text form in the changed data source.

4. The method according to claim 1, wherein parsing a data source in the text form to obtain the plurality of partial word lists of the data source comprises:

segmenting the data source to obtain segments of the data source, and

parsing the data source segments, in parallel, to obtain the plurality of partial word lists of the data source segments for use in the compiling.

5. The method according to claim 1, wherein parsing a data source in the text form to obtain the plurality of partial word lists of the data source comprises:

parsing the data source, in series, to obtain the plurality of partial word lists of the data source for use in the compiling.

6. The method according to claim 1, further comprising:

optimizing the phoneme tree responsive to determining that at least two branches of the phoneme tree contain identical nodes.

7. The method according to claim 1, wherein compiling the plurality of partial word lists to create the plurality of phoneme graphs corresponding, respectively, to the plurality of partial word lists comprises:

applying a grammar template with respect to a selected one of the partial word lists to create a grammar corresponding to the selected partial word list, the created grammar specifying a sequence of words determined to be present in the selected partial word list;

determining a phoneme list of the grammar, the phoneme list specifying, for each of at least one pronunciation of each word in the specified sequence of words, a list of phonemes corresponding to the each pronunciation;

creating the phoneme graph corresponding to the determined phoneme list; and

optimizing the phoneme graph.

8. The method according to claim 1, further comprising:

when combining the plurality of phoneme graphs to form the phoneme tree, optimizing the phoneme tree by eliminating from the second phoneme graph a list of phonemes appearing in the first phoneme graph; and

creating, at either the first or last phoneme in the list, a common intermediate node between the first phoneme graph and the second phoneme graph in the phoneme tree.