Front-end Processing Technique Research Articles

Performance evaluation of psycho-acoustically motivated front-end compensator for TIMIT phone recognition

Wavelet-based front-end processing technique has gained popularity for its noise removing capability. In this paper, a robust automatic speech recognition system is proposed by utilizing the advantages of psycho-acoustically motivated wavelet-based front-end compensator. In the front-end compensator block, voiced speech probability-based voice activity detector system is designed to separate voiced and unvoiced frames and to update noise statistics. The wavelet packet decomposition tree is designed according to equal rectangular bandwidth (ERB) scale. Wavelet decomposition based on ERB scale is utilized here as the central frequency of the ERB distribution resembles frequency response of human cochlea. Voiced and unvoiced frames are separately decomposed into 24 sub-bands to estimate average sub-band energy (ASE) of each frame. ASE is then used to calculate threshold value. Lastly, Wiener filtering is employed for reducing the residual noise before final reconstruction stage. The proposed system is evaluated on TIMIT database under various noise conditions. The phoneme recognition accuracy of the proposed system is compared with different baseline and robust features as well as with existing front-end compensation techniques. Additionally, the proposed front-end compensator is evaluated in terms of phoneme classification accuracy. Performance improvement is observed in all above experiments.

Guest Editorial: Special issue on flexible sensors and sensing systems

This special issue focuses on the sensors and sensing systems having features like flexibility, bendability, conformability, stretchability, and presence over large areas and 3D surfaces. Like conventional sensors, flexible sensors are also used to measure parameters and agents like pH, temperature, humidity, force, gasses, velocity, flow etc. In addition, they possess the ability to bend. This requires special front-end processing techniques compatible with the flexible materials that these sensors are made of. In response to the call for papers for this special issue, 114 manuscripts were received. Of those, 39 were found not to fit to the scope of the special issue and were separated to be handled by the permanent editors of the Journal. The peer review process resulted in 29 innovative manuscripts to be published here submitted from over 45 institutions, with a few trailing manuscripts to be published at a later issue due to time constraints. Of the work presented here, nine papers describe sensors for health and medical applications. Five papers detail sensors for the general fields of environmental and structural health monitoring. Four are on robotic applications. Although majority of the manuscripts focus on a single sensing function such as fluidic flow, force, pH, temperature or presence of a specific gas, four papers present multifunctional flexible sensors.

Noise robust voice activity detection based on periodic to aperiodic component ratio

This paper proposes a noise robust voice activity detection (VAD) technique called PARADE (PAR based Activity DEtection) that employs the periodic component to aperiodic component ratio (PAR). Conventional noise robust features for VAD are still sensitive to non-stationary noise, which yields variations in the signal-to-noise ratio, and sometimes requires a priori noise power estimations, although the characteristics of environmental noise change dynamically in the real world. To overcome this problem, we adopt the PAR, which is insensitive to both stationary and non-stationary noise, as an acoustic feature for VAD. By considering both periodic and aperiodic components simultaneously in the PAR, we can mitigate the effect of the non-stationarity of noise. PARADE first estimates the fundamental frequencies of the dominant periodic components of the observed signals, decomposes the power of the observed signals into the powers of its periodic and aperiodic components by taking account of the power of the aperiodic components at the frequencies where the periodic components exist, and calculates the PAR based on the decomposed powers. Then it detects the presence of target speech signals by estimating the voice activity likelihood defined in relation to the PAR. Comparisons of the VAD performance for noisy speech data confirmed that PARADE outperforms the conventional VAD algorithms even in the presence of non-stationary noise. In addition, PARADE is applied to a front-end processing technique for automatic speech recognition (ASR) that employs a robust feature extraction method called SPADE (Subband based Periodicity and Aperiodicity DEcomposition) as an application of PARADE. Comparisons of the ASR performance for noisy speech show that the SPADE front-end combined with PARADE achieves significantly higher word accuracies than those achieved by MFCC (Mel-frequency Cepstral Coefficient) based feature extraction, which is widely used for conventional ASR systems, the SPADE front-end without PARADE, and other standard noise robust front-end processing techniques (ETSI ES 202 050 and ETSI ES 202 212). This result confirmed that PARADE can improve the performance of front-end processing for ASR.

A feature extraction method using subband based periodicity and aperiodicity decomposition with noise robust frontend processing for automatic speech recognition

This paper proposes a frontend processing technique that employs a speech feature extraction method called Subband based Periodicity and Aperiodicity DEcomposition (SPADE), and examines its validity for automatic speech recognition in noisy environments. SPADE divides speech signals into subband signals, which are then decomposed into their periodic and aperiodic features, and uses both features as speech feature parameters. SPADE employs independent periodicity estimation within each subband and periodicity–aperiodicity decomposition design based on a parallel distributed processing technique motivated by the human speech perception process. Unlike other speech features, this decomposition of speech into two characteristics provides information about periodicities and aperiodicities, and thus allows the utilization of the robustness exhibited by periodic features without losing certain essential information included in aperiodic features. This paper first introduces an implementation of SPADE that operates in the frequency domain, and then examines the validity of combining SPADE with speech enhancement methods. For this examination, we combine SPADE with noise compensation methods that operate in the frequency domain and cepstral normalization methods. In addition, we employ an energy parameter calculation method based on the SPADE framework. An evaluation with the AURORA-2J noisy continuous digit speech recognition database (Japanese AURORA-2) shows that SPADE combined with adaptive Wiener filtering, cepstral normalization, and the energy parameter achieves average word accuracy rates of 82.58% with clean training and 92.55% with multicondition training. These rates are higher than those achieved with ETSI WI008 advanced DSR frontend processing (77.98% and 91.01%, respectively) whose speech feature parameter is based on conventional Mel-frequency cepstral coefficients. By comparison with ETSI WI008 advanced DSR frontend, the proposed method reduces word error rates by 20.9% with clean training and 17.2% with multicondition training. These results confirmed that SPADE combined with noise reduction methods can increase robustness in the presence of noise.

Super-self-aligned back-gate∕double-gate planar transistors: Novel fabrication approach

This work presents a reproducible, super-self-aligned approach for fabricating back-gate∕double-gate transistors with a thin silicon channel and thick doped source∕drain polysilicon access regions. Such a device structure can lead to ultimate electrostatic control of the channel without sacrificing source∕drain series resistance in a deeply scaled field effect transistor. The approach consists of a unique combination of silicon complementary-metal-oxide-semiconductor front-end processing techniques, along with wafer bonding, sidewall spacer formation (in oxide and nitride), solid-state junction diffusion, and multistage chemical mechanical polishing for wafer-level planarization. The authors further demonstrate the formation of a reliable contact at the source∕drain junction interface between doped polysilicon and the undoped silicon channel. In the design, through oxidation, the authors are able to introduce strain in the structure, as well as buried interconnects in a plane below the device. Both n-chan...

High-voltage n-channel metal-oxide-semiconductor technology

High-voltage devices have been integrated into a standard silicon-gate NMOS IC fabrication process utilizing a novel front-end processing technique. Fabrication-process steps and modelling results are described in this paper. Driver transistors are characterized in terms of drift-region implant dose, design parameters, and substrate resistivities. Present work has optimized process parameters and device structures to yield "off" state breakdown up to 270 V for 6–10 Ω∙cm, p-type, [Formula: see text] substrates.