Patent US5340316A successfully refreshed from Google Patents.
US5340316A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Synthesis-based speech training system
Assignee: Panasonic Corp of North America
•
Filing: 1993-05-28
•
Granted: 1994-08-23
•
Expires: 2013-05-28
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 phonemes. The set of phonemes 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, nasality, and tongue-palate contact 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
2026-11-02 19:31
CPC Classifications
G; G09; G09B; G09B19/00; G09B19/04; G09B5/00; G09B5/06; G09B5/065
Claims Analysis
Total Claims: 22
Claim 1
Independent Claim
202 words
A synthesis-based speech training apparatus, which comprises: input means for entering an utterance to be demonstrated; editing means for converting said utterance to be demonstrated into a set of phonemes; synthesizer means for converting the set of phonemes into a set of acoustic parameters which specify the acoustic characteristics of the utterance to be demonstrated; means for converting the set of acoustic parameters into a set of articulatory parameters; means for displaying the set of articulatory parameters; means for converting the set of acoustic parameters into a synthesized speech output; means for producing the synthesized speech output in an audible sound; means for measuring a tongue contact pattern produced by the operator; means for measuring an acoustic sound produced by the operator; means for measuring an expiratory airflow produced by the operator; means for measuring a nasal vibration produced by the operator; means for measuring a neck vibration produced by the operator; means for evaluating the similarity of the measurements produced by the operator to the set of acoustic parameters of the utterance to be demonstrated; and display means for displaying the similarity between the set of acoustic parameters of the utterance to be demonstrated and the measurements produced by the operator.
Claim 2
Dependent Claim
202 words
A synthesis-based speech training apparatus, which comprises: input means for entering an utterance to be demonstrated; editing means for converting said utterance to be demonstrated into a set of phonemes; synthesizer means for converting the set of phonemes into a set of acoustic parameters which specify the acoustic characteristics of the utterance to be demonstrated; means for converting the set of acoustic parameters into a set of articulatory parameters; means for displaying the set of articulatory parameters; means for converting the set of acoustic parameters into a synthesized speech output; means for producing the synthesized speech output in an audible sound; means for measuring a tongue contact pattern produced by the operator; means for measuring an acoustic sound produced by the operator; means for measuring an expiratory airflow produced by the operator; means for measuring a nasal vibration produced by the operator; means for measuring a neck vibration produced by the operator; means for evaluating the similarity of the measurements produced by the operator to the set of acoustic parameters of the utterance to be demonstrated; and display means for displaying the similarity between the set of acoustic parameters of the utterance to be demonstrated and the measurements produced by the operator.
Claim 3
Dependent Claim
78 words
A synthesis-based speech training apparatus, which comprises: input means for entering an utterance to be demonstrated; editing means for converting the utterance to be demonstrated into a set of phonemes; synthesizer means for converting the set of phonemes into a set of acoustic parameters which specify the acoustic characteristics of the utterance to be demonstrated; means for converting the set of acoustic parameters into a set of articulatory parameters; and means for displaying the set of articulatory parameters.
Claim 4
Dependent Claim
78 words
A synthesis-based speech training apparatus, which comprises: input means for entering an utterance to be demonstrated; editing means for converting the utterance to be demonstrated into a set of phonemes; synthesizer means for converting the set of phonemes into a set of acoustic parameters which specify the acoustic characteristics of the utterance to be demonstrated; means for converting the set of acoustic parameters into a set of articulatory parameters; and means for displaying the set of articulatory parameters.
Claim 5
Dependent Claim
25 words
The synthesizer-based speech training apparatus of claim 2, further comprising formant synthesizer means for converting the set of acoustic parameters into a synthesized speech output.
Claim 6
Dependent Claim
21 words
The synthesizer-based speech training apparatus of claim 2, further comprising means for producing the synthesized speech output in an audible sound.
Claim 7
Dependent Claim
16 words
The synthesizer-based speech training apparatus of claim 2, further comprising means for measuring a spoken utterance.
Claim 8
Dependent Claim
25 words
The synthesizer-based speech training apparatus of claim 5, wherein said means for measuring a spoken utterance includes a means for measuring a tongue contact pattern.
Claim 9
Dependent Claim
23 words
The synthesizer-based speech training apparatus of claim 5, wherein said means for measuring a spoken utterance includes means for measuring an acoustic sound.
Claim 10
Dependent Claim
23 words
The synthesizer-based speech training apparatus of claim 5, wherein said means for measuring a spoken utterance includes means for measuring an expiratory airflow.
Claim 11
Dependent Claim
23 words
The synthesizer-based speech training apparatus of claim 5, wherein said means for measuring a spoken utterance includes means for measuring a nasal vibration.
Claim 12
Dependent Claim
23 words
The synthesizer-based speech training apparatus of claim 5, wherein said means for measuring a spoken utterance includes means for measuring a neck vibration.
Claim 13
Dependent Claim
34 words
The synthesizer-based speech training apparatus of claim 5, further comprising means for evaluating the similarity between the set of acoustic parameters of the utterance to be demonstrated and the measurements of the spoken utterance.
Claim 14
Dependent Claim
35 words
The synthesizer-based speech training apparatus of claim 11, further comprising display means for displaying the similarities between the set of acoustic parameters of the utterance to be demonstrated and the measurements of the spoken utterance.
Claim 15
Dependent Claim
150 words
A synthesizer-based speech training method, which comprises: entering an utterance to be demonstrated; converting the utterance to be demonstrated into a set of phonemes; converting the set of phonemes into a set of acoustic parameters which specify the acoustic characteristics of the utterance to be demonstrated; converting the set of acoustic parameters into synthesized speech output; producing the synthesized speech output in an audible sound; converting the acoustic parameters into a set of articulatory parameters; displaying the set of articulatory parameters; measuring a tongue contact pattern; measuring an acoustic sound; measuring an expiratory airflow; measuring a nasal vibration; measuring a neck vibration; evaluating the similarity between the set of acoustic parameters of the utterance to be demonstrated and the measurements produced by the operator; and displaying the evaluation of the similarity between the set of acoustic parameters of the utterance to be demonstrated and the measurements produced by the operator.
Claim 16
Dependent Claim
150 words
A synthesizer-based speech training method, which comprises: entering an utterance to be demonstrated; converting the utterance to be demonstrated into a set of phonemes; converting the set of phonemes into a set of acoustic parameters which specify the acoustic characteristics of the utterance to be demonstrated; converting the set of acoustic parameters into synthesized speech output; producing the synthesized speech output in an audible sound; converting the acoustic parameters into a set of articulatory parameters; displaying the set of articulatory parameters; measuring a tongue contact pattern; measuring an acoustic sound; measuring an expiratory airflow; measuring a nasal vibration; measuring a neck vibration; evaluating the similarity between the set of acoustic parameters of the utterance to be demonstrated and the measurements produced by the operator; and displaying the evaluation of the similarity between the set of acoustic parameters of the utterance to be demonstrated and the measurements produced by the operator.
Claim 17
Dependent Claim
63 words
A synthesizer-based speech training method, which comprises: entering an utterance to be demonstrated; converting the utterance to be demonstrated into a set of phonemes; converting the set of phonemes into a set of acoustic parameters which specify the acoustic characteristics of the utterance to be demonstrated; converting the acoustic parameters into a set of articulatory parameters; and displaying the set of articulatory parameters.
Claim 18
Dependent Claim
63 words
A synthesizer-based speech training method, which comprises: entering an utterance to be demonstrated; converting the utterance to be demonstrated into a set of phonemes; converting the set of phonemes into a set of acoustic parameters which specify the acoustic characteristics of the utterance to be demonstrated; converting the acoustic parameters into a set of articulatory parameters; and displaying the set of articulatory parameters.
Claim 19
Dependent Claim
98 words
The synthesizer-based speech training method of claim 14, further comprising: converting the set of acoustic parameters into synthesized speech output; producing the synthesized speech output in an audible sound; measuring a spoken utterance, which includes measuring a tongue contact pattern, an acoustic sound, an expiratory airflow, a nasal vibration, and a neck vibration; evaluating the similarity between the set of acoustic parameters of the utterance to be demonstrated and the measurements of the spoken utterance; and displaying the similarity between the set of acoustic parameters of the utterance to be demonstrated and the measurements of the spoken utterance.
Claim 20
Dependent Claim
82 words
A synthesizer-based speech training method, which comprises: entering text of the language to be learned; converting the entered text into a set of phonemes; converting the set of phonemes into a set of acoustic parameters which specify the acoustic characteristics of the entered text in a preset foreign language; converting the acoustic parameters into a set of articulatory parameters which specify the articulatory model movements required to produce the entered text in the foreign language; and displaying the set of articulatory parameters.
Claim 21
Dependent Claim
82 words
A synthesizer-based speech training method, which comprises: entering text of the language to be learned; converting the entered text into a set of phonemes; converting the set of phonemes into a set of acoustic parameters which specify the acoustic characteristics of the entered text in a preset foreign language; converting the acoustic parameters into a set of articulatory parameters which specify the articulatory model movements required to produce the entered text in the foreign language; and displaying the set of articulatory parameters.
Claim 22
Dependent Claim
106 words
The synthesizer-based speech training method of claim 16, further comprising: converting the set of acoustic parameters into synthesized speech output; producing the synthesized speech output in the foreign language in an audible sound; measuring a spoken utterance, which includes measuring a tongue contact pattern, an acoustic sound, an expiratory airflow, a nasal vibration, and a neck vibration; evaluating the similarity between the set of acoustic parameters of the entered text in the foreign language and the measurements of the spoken utterance; and displaying the similarity between the set of acoustic parameters of the entered text in the foreign language and the measurements of the spoken utterance.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1997-08-22 | 1998-02-21 | 1998-08-23 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2001-08-22 | 2002-02-21 | 2002-08-23 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2005-08-22 | 2006-02-21 | 2006-08-23 | $7700.00 | Window Closed / Lapsed |