Robustness improvement of ultrasound-based sensor systems for speech communication

Cvijanovic, Nemanja; Kechichian, Patrick; Janse, Kees; Kohlrausch, AG Armin

doi:10.1109/eusipco.2015.7362510

Cited by 2 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These speech sensors capture either certain aspects of the speech production process related to the excitation of speech or speech signals transmitted through anatomical vibrations (Mubeen et al, 2012). A significant number of studies has used these new speech sensors for speech processing, such as Mubeen et al (2012), Zhang et al (2004), Okamoto et al (2007), Lin et al (2016), Otaka et al (2016), Cvijanovic et al (2015), Schultz and Wand (2010), Kechichian and Srinivasan (2012), Quatieri et al (2006), Sahidullah et al (2016) and Patil and Hansen (2010). The ultrasound-based sensor used in a voice activity detector improves the performance of speech recognition in low signal-to-noise-ratio environments in Cvijanovic et al (2015).…”

Section: Introductionmentioning

confidence: 99%

Bone- and air-conduction speech combination method for speaker recognition

Tsuge

Kuroiwa

2019

IJBM

View full text Add to dashboard Cite

In this paper, first, we report speaker recognition performance using bone-conduction speech based on an i-vector-based speaker recognition system, which is the current state-of-the-art method. In addition, we propose three speaker recognition methods combining bone-conduction speech and air-conduction speech: a feature combination method, a speaker model combination method, and a similarity score combination method. To evaluate the proposed methods, we conducted speaker recognition experiments using a part of a large speech corpus constructed by the National Research Institute of Police Science, Japan. Experimental results show the bone-conduction speech performs almost the same as the air-conduction speech when the enrolment data and evaluation data are collected in the same session. In addition, all proposed methods improved the speaker recognition performance of air-and bone-conduction speech in the experiments. From these results, we conclude that fusing air-and bone-conduction speech improves the speaker recognition performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Bone- and air-conduction speech combination method for speaker recognition

Tsuge

Kuroiwa

2019

IJBM

View full text Add to dashboard Cite

show abstract

“…In addition to current speech recognition applications, silent speech recognition can also be applied to communications involving people with speech disorders, in noisy environments, and when greater security is required [2]. To enable speech recognition without sound, a variety of sensors have been utilized, such as electromyography (EMG) [3,4,5], electromagnetic articulography (EMA) [6,7,8,9], non-audible murmur (NAM) microphones [10,11,12], ultrasound transducers with video cameras [13,14,15,16], and ultrasound Doppler sensors [17,18]. …”

Section: Introductionmentioning

confidence: 99%

“…Moreover, it is difficult to miniaturize the sensor module because this system requires two different sensors to detect the movements of both the lips and vocal tract simultaneously. Ultrasonic Doppler sensing for a silent speech interface was proposed in [17,18]. The method’s potential was demonstrated, but its accuracy on a digit recognition task was only 33% [17].…”

Section: Introductionmentioning

confidence: 99%

Towards Contactless Silent Speech Recognition Based on Detection of Active and Visible Articulators Using IR-UWB Radar

Shin

Seo

2016

Sensors

View full text Add to dashboard Cite

People with hearing or speaking disabilities are deprived of the benefits of conventional speech recognition technology because it is based on acoustic signals. Recent research has focused on silent speech recognition systems that are based on the motions of a speaker’s vocal tract and articulators. Because most silent speech recognition systems use contact sensors that are very inconvenient to users or optical systems that are susceptible to environmental interference, a contactless and robust solution is hence required. Toward this objective, this paper presents a series of signal processing algorithms for a contactless silent speech recognition system using an impulse radio ultra-wide band (IR-UWB) radar. The IR-UWB radar is used to remotely and wirelessly detect motions of the lips and jaw. In order to extract the necessary features of lip and jaw motions from the received radar signals, we propose a feature extraction algorithm. The proposed algorithm noticeably improved speech recognition performance compared to the existing algorithm during our word recognition test with five speakers. We also propose a speech activity detection algorithm to automatically select speech segments from continuous input signals. Thus, speech recognition processing is performed only when speech segments are detected. Our testbed consists of commercial off-the-shelf radar products, and the proposed algorithms are readily applicable without designing specialized radar hardware for silent speech processing.

show abstract

Robustness improvement of ultrasound-based sensor systems for speech communication

Cited by 2 publications

References 12 publications

Bone- and air-conduction speech combination method for speaker recognition

Bone- and air-conduction speech combination method for speaker recognition

Towards Contactless Silent Speech Recognition Based on Detection of Active and Visible Articulators Using IR-UWB Radar

Contact Info

Product

Resources

About