Robust Voice Activity Detection Algorithm Based on Feature of Frequency Modulation of Harmonics and Its DSP Implementation

Hsu, Chung Chien; Cheong, Kah Meng; Chi, Tai-Shih; Tsao, Yu

doi:10.1587/transinf.2015edp7138

Cited by 22 publications

(5 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When using this practice method, we must use our strengths and avoid weaknesses to maximize the advantages of group practice. Literature [7] not only divides the exercises into three types: "imitation memory, association creation, and task communication," but also points out the characteristics of these three exercises. Literature [8] divides classroom exercises into four categories: "understanding, imitating memory, intellectual development, and communicative."…”

Section: Related Workmentioning

confidence: 99%

The Spoken English Practice System Based on Computer English Speech Recognition Technology

Gao

2022

Mobile Information Systems

View full text Add to dashboard Cite

Spoken English practice requires a combination of listening, speaking, reading, and writing, among which listening and speaking are the most difficult. In order to improve the speaking ability of the practitioner, the pronunciation of spoken English needs to be corrected in time. However, the workload of manual evaluation is too large, so it is necessary to combine intelligent methods for spoken language recognition. Based on the needs of spoken English pronunciation correction, this paper combines the computer English speech recognition technology to construct the spoken English recognition and correction model and combines the coding technology to study the English speech recognition technology. Moreover, this article constructs the spoken English practice system based on the actual needs of spoken English practice. Finally, this paper verifies the reliability of this system through experimental research, which provides a reliable means for the subsequent intelligent learning of spoken English.

show abstract

Section: Related Workmentioning

confidence: 99%

The Spoken English Practice System Based on Computer English Speech Recognition Technology

Gao

2022

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…Traditional statistical models, widely used in speech enhancement due to their simplicity, often rely only on the nonstationarity of speech [5]- [7]. Better accuracy can be achieved by integrating models of features like pitch, harmonicity [8], [9], modulation [10], spectral shape [11], [12], etc. [13].…”

Section: Introductionmentioning

confidence: 99%

On training targets for noise-robust voice activity detection

Braun¹,

Tashev²

2021

Preprint

View full text Add to dashboard Cite

The task of voice activity detection (VAD) is an often required module in various speech processing, analysis and classification tasks. While state-of-the-art neural network based VADs can achieve great results, they often exceed computational budgets and real-time operating requirements. In this work, we propose a computationally efficient real-time VAD network that achieves state-of-the-art results on several public real recording datasets. We investigate different training targets for the VAD and show that using the segmental voice-to-noise ratio (VNR) is a better and more noise-robust training target than the clean speech level based VAD. We also show that multi-target training improves the performance further.

show abstract

“…For different audio types, different audio features are used. e literature used two acoustic characteristics of zerocrossing rate and short-term energy to classify voice and music in broadcast signals [13]. e literature first divided the audio signal in the TV into mute, signal with music component and signal without music component by using four audio characteristics of short-term energy, zerocrossing rate, pitch frequency, and spectral peak trajectory [14].…”

Section: Related Workmentioning

confidence: 99%

Simulation of English Speech Recognition Based on Improved Extreme Random Forest Classification

Hao

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Existing speech recognition systems are only for mainstream audio types; there is little research on language types; the system is subject to relatively large restrictions; and the recognition rate is not high. Therefore, how to use an efficient classifier to make a speech recognition system with a high recognition rate is one of the current research focuses. Based on the idea of machine learning, this study combines the computational random forest classification method to improve the algorithm and builds an English speech recognition model based on machine learning. Moreover, this study uses a lightweight model and its improved model to recognize speech signals and directly performs adaptive wavelet threshold shrinkage and denoising on the generated time-frequency images. In addition, this study uses the EI strong classifier to replace the softmax of the lightweight AlexNet model, which further improves the recognition accuracy under a low signal-to-noise ratio. Finally, this study designs experiments to verify the model effect. The research results show that the effect of the model constructed in this study is good.

show abstract

Robust Voice Activity Detection Algorithm Based on Feature of Frequency Modulation of Harmonics and Its DSP Implementation

Cited by 22 publications

References 46 publications

The Spoken English Practice System Based on Computer English Speech Recognition Technology

The Spoken English Practice System Based on Computer English Speech Recognition Technology

On training targets for noise-robust voice activity detection

Simulation of English Speech Recognition Based on Improved Extreme Random Forest Classification

Contact Info

Product

Resources

About