Patent US1608789A successfully refreshed from Google Patents.
Patent US5536171A successfully refreshed from Google Patents.
← Back to Patent Explorer
US5536171A Expired / Lapsed US ⏱️ 0.0 years remaining

Synthesis-based speech training system and method

Assignee: Panasonic Corp of North America
•
Filing: 1994-04-12
•
Granted: 1996-07-16
•
Expires: 2014-04-12
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract This invention includes a speech training system that allows a student to enter any utterance to be learned and have the articulatory model movements required to produce the utterance displayed on a CRT screen. The system accepts a typed utterance, breaking it down into a set of speech units which could be phonemes or syllables and the onset and offset of the speech units. The set of speech units is sent to a synthesizer, which produces a set of parameters indicating the acoustic characteristics of the utterance. The acoustic parameters are converted into articulatory parameters emphasizing the frequency and nasality required to produce the typed utterance. The speech units and onset and offset of each are used to generate tongue-palate contact patterns required to produce the typed utterance. The articulatory parameters are displayed on the CRT screen. The acoustic parameters are also sent to a formant synthesizer which converts the parameters into speech output. The system measures a student's production and then evaluates the student's production against the parameters of the typed utterance for its similarity. Feedback on the similarity is displayed on the CRT screen.

Inventors

  • 👤 Hector R. Javkin
  • 👤 Elizabeth G. Keate
  • 👤 Norma Antonanzas-Barroso
  • 👤 Brian A. Hanson

Bibliographic Details

Application Number —
Jurisdiction US
Data Source google_patents
Last Synchronized 2026-11-09 05:40
CPC Classifications
G; G09; G09B; G09B5/00; G09B5/06; G09B5/065; G09B19/00; G09B19/04

Claims Analysis

Total Claims: 12
Claim 1
Independent Claim 75 words
A synthesis-based speech training apparatus, comprising: input means for entering an utterance; editing means for converting the utterance into a set of speech units and the onset and offset of each speech unit; synthesizer means for converting said set of speech units and onset and offset of speech units into a set of tongue-palate contact patterns arranged in a hierarchical order; and means for displaying the set of tongue-palate contact patterns for the entered utterance.
Claim 2
Dependent Claim 75 words
A synthesis-based speech training apparatus, comprising: input means for entering an utterance; editing means for converting the utterance into a set of speech units and the onset and offset of each speech unit; synthesizer means for converting said set of speech units and onset and offset of speech units into a set of tongue-palate contact patterns arranged in a hierarchical order; and means for displaying the set of tongue-palate contact patterns for the entered utterance.
Claim 3
Dependent Claim 26 words
The speech training apparatus of claim 1 wherein said synthesizer means provides the durations of the onset, offset, and contact steady-state portion of each speech unit.
Claim 4
Dependent Claim 25 words
The speech training apparatus of claim 2 wherein the times of onset, offset, and steady-state are assigned for each speech unit by said synthesizer means.
Claim 5
Dependent Claim 41 words
The speech timing apparatus of claim 3 wherein said synthesizer means stores the maximum area of tongue-palate contact for each speech unit along with at least one alternate contact area for each different context in which that speech unit is used.
Claim 6
Dependent Claim 24 words
The speech training apparatus of claim 4 wherein each contact area between the tongue and palate is defined by a set of 63 points.
Claim 7
Dependent Claim 63 words
The speech training apparatus of claim 1 further comprising means for measuring acoustic parameters of a spoken utterance, including measuring the tongue-palate contact pattern for the utterance; means for evaluating the similarity between the utterance being demonstrated and the measured acoustic parameters and measured tongue-palate contact pattern; and display means for displaying the differences between the utterance being demonstrated and the measured utterance.
Claim 8
Dependent Claim 63 words
A synthesis-based speech training method comprising the steps of: determining an utterance to be learned; converting said utterance into a speech unit and the onset and offset of the speech unit; converting said speech unit and onset and offset into a set of tongue-palate contacts; arranged in a hierarchical order; and displaying the set of tongue-palate patterns for the utterance to be learned.
Claim 9
Dependent Claim 63 words
A synthesis-based speech training method comprising the steps of: determining an utterance to be learned; converting said utterance into a speech unit and the onset and offset of the speech unit; converting said speech unit and onset and offset into a set of tongue-palate contacts; arranged in a hierarchical order; and displaying the set of tongue-palate patterns for the utterance to be learned.
Claim 10
Dependent Claim 36 words
The speech training method of claim 7 wherein said speech unit converting step comprises: storing an area of tongue-palate contact for each speech unit; and assigning times of onset, offset, and steady-state for each speech unit.
Claim 11
Dependent Claim 43 words
The speech training method of claim 8 wherein said storing an area of tongue-palate contact step comprises: storing the maximum area of tongue-palate contact along with at least one alternate contact area for each different context in which the speech unit is used.
Claim 12
Dependent Claim 28 words
The speech training method of claim 9 wherein said storing step comprises: storing each contact area between the tongue and palate by a specific set of 63 points.

References Cited (Backward Citations)

US4641343A Cited
US5061186A Cited
US5340316A Cited

USPTO Annuity & Maintenance Windows

Annuity Stage Window Opens Payment Deadline Surcharge Period Until Estimated Fee Status
3.5 Years (Year 4) 1999-07-16 2000-01-15 2000-07-16 $2000.00 Window Closed / Lapsed
7.5 Years (Year 8) 2003-07-16 2004-01-15 2004-07-16 $3760.00 Window Closed / Lapsed
11.5 Years (Year 12) 2007-07-16 2008-01-15 2008-07-16 $7700.00 Window Closed / Lapsed

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag