A voice activity detection system based on FPGA

Jung, Junhee; Jin, Seunghun; Kim, Dongkyun; Kim, Hyung Soon; Choi, Jong Suk; Jeon, Jae Wook

doi:10.1109/iccas.2010.5669913

Cited by 5 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A design presented by [5] uses 2 additional features (Harmonicity and Modulation Frequency) apart from signal energy as the main features. Degree of Voicing (DoV) [59] along with Quantile-SNR (QSNR) [60] are used by [13] as features of the VAD. DoV represents periodicity of a speech signal and is considered as a good representation for speech but it suffers from periodic noise.…”

Section: [5][8] [14][21]mentioning

confidence: 99%

“…DoV represents periodicity of a speech signal and is considered as a good representation for speech but it suffers from periodic noise. To avoid this, [13] makes use of QSNR to compensate for the performance degradation.…”

Section: [5][8] [14][21]mentioning

confidence: 99%

“…This mechanism can be implemented in multiple ways, e.g. to look at the VAD decisions over past and future frames (also known as hangover time) to get a better result [9], [13], [17], [25] or make use of a low-pass filter (LPF) with very small bandwidth to get a smooth VAD output [10]. Both of these approaches result in additional latency.…”

Section: Classifiersmentioning

confidence: 99%

“…Covering the last 12 years (Jan 2010 -Dec 2021), we found several hardware implementations of VAD (either mea- sured or simulated at the device level using foundry PDKs) [5]- [25]. This includes digital ( [5], [7], [16], [18], [20], [21]), analog ( [8], [10]), and mixed-signal ( [6], [9], [17], [19], [22]- [25]) designs along with some implementations on Field Programmable Gate Array (FPGA) ( [13], [14]), Field Programmable Analog Array (FPAA) ( [12]), Digital Signal Processor (DSP) ( [15]), and Neuromorphic platforms (e.g. Intel Loihi [26]) ( [11]), see Fig.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Hardware Implementations for Voice Activity Detection: Trends, Challenges and Outlook

Yadav

Legaspi

Alink

et al. 2023

IEEE Trans. Circuits Syst. I

View full text Add to dashboard Cite

Voice Activity Detection (VAD) is a technique used to identify the presence of human voice in an audio signal. It is implemented as an always-on component in most speech processing applications. As speech is absent most of the time, this component typically dominates the overall average power consumption of the system (excluding microphone). The widespread usage in speech applications and the need for ultra low power VAD have led to a plethora of algorithms and implementations in the hardware domain, necessitating a comprehensive study and analysis to understand (real-time) requirements, different design parameters, testing strategies, but also to identify design trends, challenges and guidelines for future implementations and testing of VAD devices. A scoping review was conducted to identify the articles for hardware implementations of VAD from January 2010 -December 2021, the results of which are presented in this article. The results highlight a big design space being used for VAD along with a lack of standard testing methodology and usage of application-dependent performance metrics. An increased usage of filter-based feature extractors along with neural-networkbased classifiers is observed. Due to lack of standardisation, no other trends can be established from the results. A set of rules and guidelines are therefore provided to facilitate the future development and benchmarking of VADs.

show abstract

Section: [5][8] [14][21]mentioning

confidence: 99%

Section: [5][8] [14][21]mentioning

confidence: 99%

Section: Classifiersmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Hardware Implementations for Voice Activity Detection: Trends, Challenges and Outlook

Yadav

Legaspi

Alink

et al. 2023

IEEE Trans. Circuits Syst. I

View full text Add to dashboard Cite

show abstract

“…The system uses the combination of software and hardware to realize the function of anti-omission. The SCM is widely used because of its superior performance and low price [5][6][7][8][9][10][11][12][13]. It is the core processor in this system.…”

Section: Introductionmentioning

confidence: 99%

Design of the Anti-Omission Shared Lockers System Based on the Single Chip Microcomputer

Pan¹

2018

CSSP

View full text Add to dashboard Cite

In recent years, shared lockers have been widely used in supermarkets, libraries, exhibition halls and other places due to their features of high safety, reliability and convenience. However, existing lockers, because of their depth, tend to lose small items and are difficult to find. In addition, traditional barcode lockers are also easy to lose barcode. Based on this background, this paper presents a design scheme of the system for anti-omission of the shared locker based on the single chip microcomputer (SCM). In the scheme, STC89C52 single chip microcomputer is used as the main control chip, and the pressure sensor is used to detect whether there are things in the shared lockers and send the information to STC89C52 single chip microcomputer to achieve anti-omission function. Supplemented by relevant keyboard module, which is the input module of the system. Furthermore, display module and voice module are the output module of the system. The fingerprint module is used to input the user's information and used the information to open the door of shared lockers. GSM (global system for mobile communication) module is used to get help from administrator when the user needs to help, and so forth. This system can realize the function of preventing omission and it is simple to operation, high security, easy to manage by the administrator.

show abstract

Improvement unvoiced replacement techniques base on real time processing using FPGA board

Sutacha

Srinonchat

2016

2016 13th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technolo

View full text Add to dashboard Cite

A voice activity detection system based on FPGA

Cited by 5 publications

References 13 publications

Hardware Implementations for Voice Activity Detection: Trends, Challenges and Outlook

Hardware Implementations for Voice Activity Detection: Trends, Challenges and Outlook

Design of the Anti-Omission Shared Lockers System Based on the Single Chip Microcomputer

Improvement unvoiced replacement techniques base on real time processing using FPGA board

Contact Info

Product

Resources

About