Speech analytics system and system and method for determining structured speech

• US 9,401,145 B1
• Filed: 05/05/2014
• Issued: 07/26/2016
• Est. Priority Date: 04/07/2009
• Status: Active Grant

• Current Assignee: Verint Systems Incorporated
• Original Assignee: Verint Systems Limited (Verint Systems Incorporated)
• Inventors: Ziv, Omer, Achituv, Ran, Shapira, Ido
• Primary Examiner(s): Saint Cyr, Loenard
• Application Number:
  US14/270,280
• Time in Patent Office: 813 Days
• Field of Search: 704/9, 704/235, 704/246, 704/247, 704/251, 704/252, 704/260
• US Class Current: 1/1
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/197 Probabilistic grammars, e.g. word n-grams
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A method for converting speech to text in a speech analytics system is provided. The method includes receiving audio data containing speech made up of sounds from an audio source, processing the sounds with a phonetic module resulting in symbols corresponding to the sounds, and processing the symbols with a language module and occurrence table resulting in text. The method also includes determining a probability of correct translation for each word in the text, comparing the probability of correct translation for each word in the text to the occurrence table, and adjusting the occurrence table based on the probability of correct translation for each word in the text.

Claims

1. A method for generating a database index for a transcript based on automatic identification by a communication processing system of different types of structured speech in the transcript, the method comprising:

receiving, by a communication processing system, a transcript of an audio recording created by a speech analytics system;

analyzing, by the communication processing system, text in the transcript to determine repetitions within the text that are indicative of structured speech;

calculating, by the communication processing system, a duration distribution of the repetitions within the text to ascertain, by the communication processing system, whether a first segment of the transcript comprises a first type of structured speech, wherein the first type of structured speech includes interactive voice response (IVR) generated speech;

calculating, by the communication processing system, a length of the repetitions within the text to ascertain, by the communication processing system, whether a second segment of the transcript comprises a second or third type of structured speech, wherein the communication processing systems determines that the second segment comprises the third type of structured speech as opposed to the second type of structured speech when the length of the repetitions found in the text is greater than a predetermined threshold, wherein the second type of structured speech includes scripts spoken by agents and the third type of speech includes figures of speech; and

generating, by the communication processing system, a database index for the transcript such that the first segment is marked in a transcript database as comprising the first type of structured speech and the second segment is marked in the transcript database as comprising the second or third type of structured speech.

2. The method of claim 1, further comprising applying a distance threshold to determine contacts that contain the second type of structured speech.

3. The method of claim 2, wherein the distance threshold is approximately 18.

4. The method of claim 1, further comprising analyzing the second type of speech to determine one of compliance, quality management, and categories.

5. The method of claim 4, further comprising:

defining the second type of speech as a category; and

evaluating a contact to determine if the contact contains the category.

6. The method of claim 4, further comprising using the second type of speech as a filter in a query.