2010
DOI: 10.1016/j.specom.2009.12.002
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: This paper discusses the use of surface electromyography for automatic speech recognition. Electromyographic signals captured at the facial muscles record the activity of the human articulatory apparatus and thus allow to trace back a speech signal even if it is spoken silently. Since speech is captured before it gets airborne, the resulting signal is not masked by ambient noise. The resulting Silent Speech Interface has the potential to overcome major limitations of conventional speech-driven interfaces: it i… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

3
106
0
5

Year Published

2012
2012
2023
2023

Publication Types

Select...
4
4

Relationship

0
8

Authors

Journals

citations
Cited by 151 publications
(114 citation statements)
references
References 22 publications
3
106
0
5
Order By: Relevance
“…Recent results include advances in acoustic modeling using a clustering scheme on phonetic features, which represent properties of a given phoneme, such as the place or the manner of articulation. Schultz and Wand [SW10] reported that a recognizer based on such bundled phonetic features outperforms phoneme-based models by more than 30 %. Approaches with a direct transformation of EMG signals to speech will be described in Section 3.3.…”
Section: Emg-based Speech Communicationmentioning
confidence: 99%
“…Recent results include advances in acoustic modeling using a clustering scheme on phonetic features, which represent properties of a given phoneme, such as the place or the manner of articulation. Schultz and Wand [SW10] reported that a recognizer based on such bundled phonetic features outperforms phoneme-based models by more than 30 %. Approaches with a direct transformation of EMG signals to speech will be described in Section 3.3.…”
Section: Emg-based Speech Communicationmentioning
confidence: 99%
“…El registro de la actividad eléctrica muscular se hace mediante electrodos GH VXSHU¿FLH HVWD VHxDO HOpFWULFD HV DPSOL¿FDGD \ VH obtiene a partir de la medición de la tensión a través del tiempo. La señal eléctrica muscular puede ser transmitida directamente a los dispositivos electró-nicos para su posterior procesamiento [3]. Hasta la fecha, el procesamiento de estas señales se hace por medio de sistemas experimentales llamados Interfaz de Habla Silenciosa o Silent Speech Interface (SSI), que se basan en siete tipos de tecnologías.…”
Section: La Vozunclassified
“…A pesar de los enormes esfuerzos aún no hay un sistema de procesamiento del hablaque proporcione buenos resultados en lugares ruidosos. La segunda radica en que las interfaces convencionales del habla se basan en el discurso en voz alta, que presenta el inconveniente de exponer al S~EOLFR FRPXQLFDFLRQHV FRQ¿GHQFLDOHV \ SHUWXUEDU a las personas que las escuchan [3].…”
Section: Introductionunclassified
See 1 more Smart Citation
“…Many different SSIs have been proposed so far, mainly differing in the type of biosignal they rely on. Thus, we can find SSIs that exploit the electrical signals generated by the neurons in the brain [23] or in the articulator muscles [31,42,49] or the movement of the speech articulators themselves [40,44,9,29,18,14,26,21]. In our work we use a magnetic sensing technique known as Permanent Magnet Articulography (PMA) [13,18] for capturing the movement of the speech articulators.…”
Section: Introductionmentioning
confidence: 99%