Statistical Model-Based Noise Reduction Approach for Car Interior Applications to Speech Recognition

Abstract

This paper presents a statistical model‐based noise suppression approach for voice recognition in a car environment. In order to alleviate the spectral whitening and signal distortion problem in the traditional decision‐directed Wiener filter, we combine a decision‐directed method with an original spectrum reconstruction method and develop a new two‐stage noise reduction filter estimation scheme. When a tradeoff between the performance and computational efficiency under resource‐constrained automotive devices is considered, ETSI standard advance distributed speech recognition font‐end (ETSI‐AFE) can be an effective solution, and ETSI‐AFE is also based on the decision‐directed Wiener filter. Thus, a series of voice recognition and computational complexity tests are conducted by comparing the proposed approach with ETSI‐AFE. The experimental results show that the proposed approach is superior to the conventional method in terms of speech recognition accuracy, while the computational cost and frame latency are significantly reduced.

Intra- and Inter-frame Features for Automatic Speech Recognition

“…As shown in Table 1, we think that the proposed intra-frame feature set contains relatively good phoneme discriminability. Since most modern speech-recognition systems employ speech enhancement technology for environmental robustness, we also evaluate the speech-recognition rate in the presence of speech enhancement technology using a Wiener filter [8]. The speech-recognition results over the enhanced speech data are described in Table 2.…”

Wearable Hearing Device Spectral Enhancement Driven by Non-Negative Sparse Coding-Based Residual Noise Reduction

“…Such statistical techniques can reduce the noise in speech under stationary noise conditions, using techniques such as the decision-directed (DD) approach [ 7 , 8 ]. However, it is difficult to reliably estimate the noise PSDs when speech is corrupted by non-stationary noise such as babble noise; in such cases, the a priori SNR estimations are often inaccurate because the noise components remain in the enhanced speech spectrum even after being processed through the Wiener filter [ 9 , 10 ].…”

“…Considering these aspects, this paper proposes an improved NNSC-based speech enhancement algorithm that reduces the residual noise based on the principle that the residual noise components remaining after processing through the DD-based Wiener filter tend to be whitened [ 9 , 10 ]. Furthermore, the NNSC approaches, as a statistical approach, aim to identify the basis and activation components by minimizing the Gaussian independent identically distributed noise [ 18 ].…”

“…Section 4 describes the NNSC–Wiener filter for speech enhancement. Section 5 describes the efficiency validation of the proposed approach, through the perceptual evaluation of the speech quality (PESQ) [ 27 ] and comparison with the NNSC [ 18 ], a two-stage Mel-warped Wiener filter [ 9 ], and a model-based Wiener filter [ 10 ]. Section 6 presents the concluding remarks.…”

Research on the vibration characteristics of the commercial-vehicle cabin based on experimental design and genetic algorithm

“…Most of the published researches on the vibration isolation performance for commercial vehicles focus on in the suspension system and the powertrain system, and few of them focus on the cabin. Moreover, the researches on the cabin mostly focus on how to reduce the interior noise [1][2][3][4], and the vibration characteristics of the cabin have not received adequate attention. Since the cabin mount system can simultaneously reduce the excitation from both the powertrain and the road, the research on the cabin mount system can effectively reduce the vibration in the cabin.…”