Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio...
Transcript of Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio...
![Page 1: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/1.jpg)
Evaluation of Multi-user System of Voice Interaction
Using Grammars
Elizabete Munzlinger, Fabricio da Silva Soares,
and Carlos Henrique Quartucci Forster{bety, p2p, forster}@ita.br
ITA – Instituto Tecnológico de AeronáuticaEEC-I – Engenharia Eletrônica e Computação –
InformáticaDivisão de Ciência da Computação
![Page 2: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/2.jpg)
Agend Introduction Grammar Design Tests and Results of Accuracy Conclusion
![Page 3: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/3.jpg)
Introduction Exaustive training
Fig. 1. Train the system to recognize one’s voice through the exhaustive reading of texts
![Page 4: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/4.jpg)
Several contexts
Introduction
Fig. 2. Systems which particular application and contexts
![Page 5: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/5.jpg)
1on
Port [4], Action [true]
Introduction Domotic system
Por favor, ligue a
lâmpada!
Fig. 3. Prototype of Domotic system
![Page 6: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/6.jpg)
Grammar Design Grammar tree Main
Rule2 Rule3Rule1
Rule1
Rule4
Rule5
Rule6
Terminal symbols
Terminal symbols
Terminal symbols
Rule8
Rule7
... ... Terminal symbols
Fig. 4. The grammar tree composed by nodes
![Page 7: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/7.jpg)
Grammar Design Grammar in Java Speech Grammar
Formatgrammar br.ita.domovox;public <command> = [<introdução>] <action> [<complemento>] <object> [<complemento>] [<conclusão>];<introdução> = [<educação>] [<complemento>] [<quem>];<action> = <ação>;<complemento> = [<posse>] [<outros>] [<onde>] [<tempo>] [<educação>] [<outros>];<object> = [<indica>] [<posse>] <dispositivo>;<conclusão> = [<introdução>];<educação> = [<outros>] [<tratamento>] [<sistema>] [<tratamento>] [<complemento>];<quem> = [<sujeito>] [<desejo>];<posse> = [<outros>] [<possessivo>] [<outros>] [<sujeito>] [<outros>];<onde> = [<lugar>] | [<outros>];<tempo> = [<quando>] | [<outros>];<tratamento> = por favor | faz favor | por gentileza | por obséquio | faça a gentileza | faça o favor | fazer o favor | fazer a gentileza;<sistema> = pc | computador | notebook | máquina | sistema | domovox | sistema domovox | sistema de voz | sistema de fala | meu | cara | bicho | mano | maluco;<sujeito> = eu | tu | ele | ela | nós | vós | eles | elas | você | vocês | mim | gente;<desejo> = [<querer>] | [<desejar>] | [<precisar>] | [<necessitar>] | [<ir>] | [<poder>];<querer> = quero | queres | quer | queremos | quereis | querem | querendo;<desejar> = desejo | desejas | deseja | desejamos | desejais | desejam | desejando; <precisar> = preciso | precisas | precisa | precisamos | precisais | precisam | precisando;<necessitar> = necessito | necessitas | necessita | necessitamos | necessitais | necessitam | necessitando;<ir> = vou | vais | vai | vamos | vão;<poder> = pode | podes;<ação> = <verdadeiro> | <falso>;<verdadeiro> = (ligar | ligue | ativar | ative | ascender | ascenda) {true};<falso> = (desligar | desligue | desativar | desative | apagar | apague) {false} <indica>= [<artigo>] | [<indicação>];<artigo> = o | a | os | as;<indicação> = esse | essa | este | esta | aquele | aquela | aquilo | todos | todos os | todas as | tudo;<dispositivo> = <porta00> | <porta01> | <porta02> | <porta03> | <porta04> | <porta05>;<porta00> = (tudo | dispositivos | aparelhos) {0};<porta01> = (luz | lâmpada) {1};<porta02> = (ventilador | aparelho ventilador) {2};<porta03> = (tv | tevê | televisão | televisor | aparelho de tv | aparelho televisor) {3};<porta04> = (abajur | luminária | candelabro) {4};<porta05> = (outros) {5};<quando> = já | agora | nesse momento | nesse minuto | nesse segundo | agora mesmo;<lugar> = aqui | aí | lá | ambiente | quarto | sala | peça | lugar | casa | apartamento | ap;<possessivo> = meu | minha | meus | minhas | nosso | nossa | nossos | nossas | vosso | vossa | vossos | vossas | dele | dela | deles | delas | desse | dessa | desses | dessas | nesse | nessa | nesses | nessas;<outros> = que | da | de | do | mesmo | para | pra | momento | mandando | também | inclusive | estou | aí | ô | é | ã | hum | mas | pode;
![Page 8: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/8.jpg)
Grammar Design Computational
resources
980MB100%
0
200
400
600
800
1000
0 min 0,5 min 1,0 min 1,5 min 2,0 min 2,5 min 3,0 min
CPU
Memory
Graph. 1. Graphic of allocation and processing of the structure of the grammar
100%
50%
![Page 9: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/9.jpg)
Grammar Design Redesign of grammar
Comando
Ação ObjetoComplemento*
FalsoVerdadeiro
Porta 01
Porta 02 ...
ligar, ativar, acender...
desligar, desativar, apagar ...
1, luz, lâmpada...
Por favor, eu você, sistema, do, preciso, meu, pode, de, quarto, a, o...
2, TV, televisor, televisão...
Fig. 5. The new grammar tree
Computational resources
Graph. 2. Graphic of allocation and processing of the structure of the grammar
423MB
5%0
200
400
600
800
1000
0 min 0,5 min 1,0 min 1,5 min 2,0 min 2,5 min 3,0 min
CPU
Memory
100%
50%
![Page 10: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/10.jpg)
Grammar Design Representation of grammar
Fig. 6. Grammar represented through a state machine with a recursivity rule
Accepted commands
Table 1. Examples of simple and complex commands based in the rules of grammar
![Page 11: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/11.jpg)
Tests and Results of Accuracy Domotic system
Por favor, ligue a
lâmpada!
Fig. 7. Comparison between registered spoken words and the log system
registered
logged
![Page 12: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/12.jpg)
Tests and Results of Accuracy General rates of acceptation
98%
85,70%
24,10%
0%10%20%30%40%50%60%70%80%90%
100%
All commands (simples and complex)
Accepted withoutlog analysis
Disregardingdefinite articles
Exactly commandswith log analysis
Graph. 3. Rates of acceptation of all commands
![Page 13: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/13.jpg)
Tests and Results of Accuracy Rates of acceptation by simple and
complex commands
10,98,9
35,333,0
0%
5%
10%
15%
20%
25%
30%
35%
40%
Simple commands Complex commands
Definite articlesaccepted
Definite articesright
Graph. 4. Rates of definite articles acceptation by simple and complex commands
![Page 14: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/14.jpg)
Tests and Results of Accuracy Rates of acceptation by numbers from 1 to
32
33,20%
66,80%
0%
34%
0%
10%
20%
30%
40%
50%
60%
70%
Number from 1 to 32
Word form
Numeral form
Just word form
Just numeral form (6, 7,14, 19, 23, 24, 25, 26, 28,29, 32)
Graph. 5. Rates of acceptation by numbers from 1 to 32
![Page 15: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/15.jpg)
Tests and Results of Accuracy Rates of errors in the numbers recognition
Highest rates of error: 21, 27 and 31
Mistook words with similar sound: 21 “20 eu” 31 “30 aí eu” “30 aí vou”
“30 aí o” “30 aí os”“30 aqui os” “30 aqui eu”“30 eu” “30 em”This happened in 70% of the cases
![Page 16: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/16.jpg)
Conclusion Behavior of a voice interface system Design of grammar Experiments with users Redesign of grammar
![Page 17: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/17.jpg)
References1. Burstein, A., Stolzle, A., Brodersen, R.W.: Using
Speech Recognition in a Personal Communications System. In: Communications, 1992. ICC 92, Conference record, SUPERCOMM/ICC ’92, IEEE, Los Alamitos (1992)
2. Pfaff, G.E.: User Interface Management Systems, p. 72. Springer, New York (1985)
3. Seneff, S.: TINA: A Natural Language System for Spoken Language Applications. Comput. Linguist. 18, 61–86 (1992)
4. Sun Microsystems Ltd, Java Speech API Programmer’s Guide Version 1.0, [online at], http://java.sun.com/products/javamedia/speech/
5. Vieira, R., Lima, V.L.: Lingüística Computacional: Princípios e Aplicações. In: JAIA – ENIA, 2001, Fortaleza (2001)
![Page 18: Evaluation of Multi-user System of Voice Interaction Using Grammars Elizabete Munzlinger, Fabricio da Silva Soares, and Carlos Henrique Quartucci Forster.](https://reader035.fdocuments.net/reader035/viewer/2022070311/552fc120497959413d8cb5bf/html5/thumbnails/18.jpg)
Evaluation of Multi-user System of Voice Interaction
Using Grammars
Elizabete Munzlinger, Fabricio da Silva Soares,
and Carlos Henrique Quartucci Forster{bety, p2p, forster}@ita.br
ITA – Instituto Tecnológico de AeronáuticaEEC-I – Engenharia Eletrônica e Computação –
InformáticaDivisão de Ciência da Computação