Method and apparatus for teaching prosodic features of speech

• US 6,358,054 B1
• Filed: 06/06/2000
• Issued: 03/19/2002
• Est. Priority Date: 05/24/1995
• Status: Expired due to Fees

• Current Assignee: Syracuse Language Systems
• Original Assignee: Syracuse Language Systems
• Inventors: Rothenberg, Martin
• Primary Examiner(s): Cheng, Joe H.
• Application Number:
  US09/587,799
• Time in Patent Office: 651 Days
• Field of Search: 434/118, 434/156-158, 434/167, 434/169, 434/185, 434/307.R, 434/308, 434/365, 434/362, 381/48-53, 381/41-43, 704/200, 704/206, 704/207, 704/225, 704/277, 704/251, 704/257, 704/258, 704/260, 704/268, 704/267, 704/770, 704/770.1, 704/275, 705/17, 607/57, 623/10
• US Class Current: 434/185
• CPC Class Codes: G09B 19/04 Speaking with audible presentation of the material to be studied G09B5/04

Abstract

A system and apparatus for teaching prosodic features of speech senses and extracts prosodic or suprasegmental variables of a user'"'"'s speech segment. Prosodic features of speech include pitch and loudness variations, as opposed to articulatory or sequential features of speech which are the primary determinants of phoneme variations. Once prosodic variables have been extracted from a speech segment, the variables are used to modulate a quasiperiodic waveform such as a sinusoid, a pulse-train, or a synthesized vowel-like waveform, or the parameters can be used to modulate a random-noise-like waveform. A modulated waveform can be played acoustically, and the user can hear the variation of the prosodic parameters without interference from the articulatory parameters of a complete waveform. This auditory feedback can be combined with visual feedback of the speech segment to teach proper prosodic speech formation. Auditory feedback for teaching prosodic features can also be formed without a modulation process by removing articulatory information from a speech segment, and non-acoustic measures sensors of prosodic feature, such as an electroglottograph, can also be employed.

Claims

1. A method for teaching prosodic features of speech comprising the steps of:

sensing parameters of a speech segment;

extracting prosodic parameters of the speech segment;

modulating a waveform with the extracted prosodic parameters of the speech segment; and

playing a waveform modulated with the extracted prosodic parameters of the speech segment.

2. A method for teaching prosodic features of speech according to claim 1, further comprising the step of:

displaying the extracted prosodic parameters of the speech segment after the step of extracting.

3. A method for teaching the prosodic features of speech according to claim 2, further comprising the step of:

displaying a model pattern in close proximity to the display of the extracted prosodic parameters of the speech segment after the step of playing.

4. A method for teaching prosodic features of speech according to claim 1, further comprising the step of:

storing the extracted prosodic parameters of the speech segment after the step of extracting.