Enhanced Feature Extraction for Speech Detection in Media Audio

Jang, Inseon; Ahn, Chang‐Beom; Seo, Jeongil; Jang, Youn-Seon

doi:10.21437/interspeech.2017-792

Cited by 8 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The process is divided into voice signal preprocessing and voice feature extraction. The four steps involved in voice signal preprocessing, (16)(17)(18) digital sampling, pre-emphasis, framing, and windowing, are shown in Fig. 2.…”

Section: Extraction Of Voice Featuresmentioning

confidence: 99%

Speech Processing Based on Hidden Markov Model and Vector Quantization Techniques Applied to the Internet of Vehicles

2018

Sensors and Materials

View full text Add to dashboard Cite

Keywords:Internet of Vehicles (IoV), speech recognition, speaker recognition, mel-frequency cepstral coefficients (MFCC), hidden Markov model (HMM), Viterbi algorithm, vector quantization (VQ) In this study, we develop an intelligence device to apply speech processing function in an Internet of Vehicles (IoV). The voice-based interactions will improve drive safety and in-time awareness of the vehicle status. This interaction can be achieved through speech recognition and response generation between the driver and the smart vehicle. Thus, the driver can focus on the driving. The proposed speech processing can be divided into three portions: (1) voice signal preprocessing, (2) speech recognition, and (3) speaker recognition. Firstly, speech signal preprocessing consists of five steps: sampling, pre-emphasis, frame, window function, and melfrequency cepstral coefficients (MFCC), so as to be able to extract the characteristic parameters in the speech signal. Secondly, the speech model is built via the hidden Markov model (HMM), and the Viterbi algorithm is used to search the best sequence in the model to achieve the function of speech recognition. Finally, we use the Linde-Buzo-Gray (LBG) algorithm in vector quantization (VQ) to train for the speaker model, and then use cosine similarity to achieve the function of speaker recognition. The proposed speech processing function has been validated experimentally, and the experimental results demonstrate its feasibility for drivers to easily control the IoV system via voice-based command. In addition, the system distinguishes different speakers and provides the corresponding usage privileges, which will improve drive safety and in-time awareness of the general vehicle status.

show abstract

Section: Extraction Of Voice Featuresmentioning

confidence: 99%

Speech Processing Based on Hidden Markov Model and Vector Quantization Techniques Applied to the Internet of Vehicles

2018

Sensors and Materials

View full text Add to dashboard Cite

show abstract

“…To tackle speech signals corrupted by noise, in this field, some of previous studies [4,5] tended to recover original signals by removing noise. Some methods [6,7] focused on feature extraction from un-corrupted voices, and some methods [8,9] tried to estimated speech quality by computing signal-to-noise ratio (SNR). Although speech enhancement has been used for speaker recognition, in most of previous studies it was often processed individually.…”

Section: Introductionmentioning

confidence: 99%

Robust Speaker Recognition Using Speech Enhancement And Attention Model

Shi¹,

Huang²,

Hain³

2020

The Speaker and Language Recognition Workshop (Odyssey 2020)

View full text Add to dashboard Cite

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. It aims to improve speaker recognition performance when speech signals are corrupted by noise. Instead of separately processing speech enhancement and speaker recognition, the two modules are integrated into one framework by a joint optimisation using deep neural networks. Furthermore, to increase the robustness against noise, a multi-stage attention mechanism is employed to highlight the speaker related features learned from context information in both time and frequency domains. To evaluate speaker identification and verification performance of the proposed approach, VoxCeleb1, one of mostly used benchmark datasets, is used. Moreover, the robustness evaluation is also conducted on VoxCeleb1 when its being corrupted by three types of interferences, general noise, music, and babble, at different signal-to-noise ratio (SNR) levels. The obtained results show that the proposed approach using speech enhancement and multi-stage attention models outperforms two strong baselines in different acoustic conditions in our experiments.

show abstract

“…Some of previous studies [4,5] tended to recover original signals by removing noise. Some methods [6,7] focused on feature extraction from un-corrupted speech signals, and some methods [8,9] tried to estimated speech quality by computing signal-to-noise ratio (SNR).…”

Section: Introductionmentioning

confidence: 99%

Robust Speaker Recognition Using Speech Enhancement And Attention Model

Shi¹,

Huang²,

Hain³

2020

Preprint

View full text Add to dashboard Cite

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of individually processing speech enhancement and speaker recognition, the two modules are integrated into one framework by a joint optimisation using deep neural networks. Furthermore, to increase robustness against noise, a multi-stage attention mechanism is employed to highlight the speaker related features learned from context information in time and frequency domain. To evaluate speaker identification and verification performance of the proposed approach, we test it on the dataset of VoxCeleb1, one of mostly used benchmark datasets. Moreover, the robustness of our proposed approach is also tested on VoxCeleb1 data when being corrupted by three types of interferences, general noise, music, and babble, at different signal-tonoise ratio (SNR) levels. The obtained results show that the proposed approach using speech enhancement and multi-stage attention models outperforms two strong baselines not using them in most acoustic conditions in our experiments.

show abstract

Enhanced Feature Extraction for Speech Detection in Media Audio

Cited by 8 publications

References 16 publications

Speech Processing Based on Hidden Markov Model and Vector Quantization Techniques Applied to the Internet of Vehicles

Speech Processing Based on Hidden Markov Model and Vector Quantization Techniques Applied to the Internet of Vehicles

Robust Speaker Recognition Using Speech Enhancement And Attention Model

Robust Speaker Recognition Using Speech Enhancement And Attention Model

Contact Info

Product

Resources

About