Regional Language Speech Recognition from Bone-Conducted Speech Signals through Different Deep Learning Architectures

Table 1

Related works.

Reference	Sensor	Problem	Method
[8]	Stethoscope and acoustic sensor	Lombard reflex on nonaudible murmur recognition in the presence of noise	Evaluation of nonaudible murmur microphone robustness with real and simulated noisy data
[9]	Softband bone conducted hearing device	Analyze auditory, speech development of bilateral microtia-affected children	The speech development of children assesses with a meaningful auditory integration scale and speech intelligibility rating
[10]	Throat, acoustic microphone	Improve throat acoustic microphone speech recognition	The throat and acoustic microphone correlate to extract acoustic feature vector for speech recognition
[11]	Baha attract bone hearing system	Speech recognition of wireless bluetooth device in patients using a baha attract bone hearing system and traditional hearing aid	Speech perception, recognition of Korean sentences were performed in quiet and noisy conditions
[12]	Bonebridge™ MED-EL	Speech recognition performance comparison of semiimplanted bonebridge MED-EL and adhesive bone-conduction device	Free-field audiometry test was conducted with speech, noise produced through loud speaker
[13]	Air and bone conduction microphone	Evaluate enhanced speech quality signal	The equalised bone conducted speech produced by maximum likelihood and bone conducted estimator for high and low SNR conditions, respectively. The equalised bone conducted speech quality evaluates with wiener gain and priori SNR estimator
[14]	Bone conducted microphone	Nonstationary noise suppression of speech signal	Supress noise in speech signal by selection of speech codebook based on noise free bone conducted microphone reference signal
[15]	Bone conducted microphone	Low frequency noise suppression	Supress low frequency noise namely colour, multitasker babble, and car from speech signal with bone conducted speech. The low noise frequency signal present in air-conducted speech is replaced with bone-conducted speech
Proposed	MEMS acoustic vibration transducer	Tamil word recognition	One syllable, two-syllable, and three-syllable Tamil speech recognize with CapsuleNet, UNet, and S-Net