Chung-Hsien Yang

Robust Speaker Identification and Verification

Acoustic characteristics have played an essential role in biometrics. In this article, we introduce a robust, text-independent speaker identification/verification system. This system is mainly based on a subspace-based enhancement technique and probabilistic support vector machines (SVMs). First, a perceptual filterbank is created from a psycho-acoustic model into which the subspace-based enhancement technique is incorporated. We use the prior SNR of each subband within the perceptual filterbank to decide the estimators gain to effectively suppress environmental background noises. Then, probabilistic SVMs identify or verify the speaker from the enhanced speech. The superiority of the proposed system has been demonstrated by twenty speaker data taken from AURORA-2 database with added background noises

A Block-Based Architecture for Lifting Scheme Discrete Wavelet Transform

Two-dimensional discrete wavelet transform (DWT) for processing image is conventionally designed by line-based architectures, which are simple and have low complexity. However, they suffer from two main shortcomings – the memory required for storing intermediate data and the long latency of computing wavelet coefficients. This work presents a new block-based architecture for computing lifting-based 2-D DWT coefficients. This architecture yields a significantly lower buffer size. Additionally, the latency is reduced from N2 down to 3N as compared to the line-based architectures. The proposed architecture supports the JPEG2000 default filters and has been realized in ARM-based ALTERA EPXA10 Development Board at a frequency of 44.33 MHz.

Critical Band Subspace-Based Speech Enhancement Using SNR and Auditory Masking Aware Technique

In this paper, a new subspace-based speech enhancement algorithm is presented. First, we construct a perceptual filterbank from psycho-acoustic model and incorporate it in the subspace-based enhancement approach. This filterbank is created through a five-level wavelet packet decomposition. The masking properties of the human auditory system are then derived based on the perceptual filterbank. Finally, the prior SNR and the masking threshold of each critical band are taken to decide the attenuation factor of the optimal linear estimator. Five different types of in-car noises in TAICAR database were used in our evaluation. The experimental results demonstrated that our approach outperformed conventional subspace and spectral subtraction methods.

TAICAR - The Collection and Annotation of an In-Car Speech Database Created in Taiwan

This paper describes a project that aims to create a Mandarin speech database for the automobile setting (TAICAR). A group of researchers from several universities and research institutes in Taiwan have participated in the project. The goal is to generate a corpus for the development and testing of various speech-processing techniques. There are six recording sites in this project. Various words, sentences, and spontaneously queries uttered in the vehicular navigation setting have been collected in this project. A preliminary corpus of utterances from 192 speakers was created from utterances generated in different vehicles. The database contains more than 163,000 files, occupying 16.8 gigabytes of disk space.

Subspace tracking for speech enhancement in car noise environments

A signal subspace speech enhancement based on a subspace tracking algorithm is presented. The proposed method incorporates a perceptual filterbank which is derived from a psycho-acoustic model for subband processing. The experiments were performed using the TAICAR in-car noisy speech database. Subjective and objective tests show that our method outperforms other existing signal subspace methods.

Noise suppression based on approximate KLT with wavelet packet expansion

In this paper, we perform the noise suppression based on approximate Karhunen-Loeve transform (KL T). The discrete cosine transform(DCT) has been a good candidate for approximate KLT when the signal is modeled as an autoregressive process. However, for nonstationary signals, wavelet transform is more capable than DCT while approximating KLT. To calculate approximate KLT, we first represent the signal by using wavelet packet based on a basis search algorithm, then eigenvectors are evaluated from the basis. A linear estimator based on these eigenvectors can be constructed and used to perform noise reduction. We evaluate the performance of this method by using the Aurora-2 database. The SNR improvement is calculated. Some waveforms and spectrograms of enhanced speech are also shown. Finally. the enhanced speech is tested for speech recognition. These experimental results show that this method achieves satisfactory enhancement of speech.

Endometrium estimation in a sequence of ultrasonic images.

In this paper a novel algorithm for motion estimation of the endometrium in a sequence of ultrasonic images is presented. The algorithm used is based on the criterion that a pixel of a motion object at different times has a different gray value. The motion estimation includes motion frequency and thickness; the former one is determined by the detection of change of a pixel value in a sequence of images during a given time period, and the latter is the result of the objects dimension divided by its extended width. The algorithm has been tested on synthetic and real images, and the results are encouraging.

Design and Implementation of Subspace-Based Speech Enhancement Under In-Car Noisy Environments

In this paper, a new subspace-based speech enhancement model is presented for in-car speech enhancement. To effectively suppress background noise, this model incorporates a perceptual filterbank and an auditory gain adaptation derived from a psychoacoustic model into a signal subspace approach. The projection approximation subspace tracking deflation (PASTd) algorithm is used to track the signal subspace. For real-time processing, a system-on-a-programmable-chip architecture and a very large scale integration design of the PASTd algorithm are proposed. To realize a pipeline computation, this paper presents a pipelined PASTd architecture without data-dependent hazards. The maximum clock rate is 9.7 MHz, and the typical clock rate, which achieves the real-time requirement, is 4.6 MHz. The corresponding architecture was experimentally verified via an ALTERA EPXA10 development board.

Robust Speaker Recognition using SNR-Aware Subspace-Based Enhancement and Probabilistic SVMs

In this paper, we present a robust text-independent speaker recognition system. The proposed system mainly includes an SNR-aware subspace-based enhancement technique and probabilistic support vector machines (SVMs). First, we construct a perceptual filterbank from psycho-acoustic model and incorporate it with the subspace-based enhancement approach. The prior SNR of each subband within the perceptual filterbank is taken to decide the estimators gain to effectively suppress environmental background noises. Next, this study uses probabilistic SVMs to identify the speaker from the enhanced speech. The superiority of the proposed system has been demonstrated by twenty speaker recognition from AURORA-2 database with in-car noises

Multiband subspace tracking speech enhancement for in-car human computer speech interaction

In this paper, a new subspace-based speech enhancement algorithm for in-car human computer speech interaction is presented. We first incorporate a perceptual filterbank which is derived from psycho-acoustic model with signal subspace approach to effectively suppress in-car noises of engine. Second, for real-time applications, a new subspace tracking algorithm is derived by modifying PASTd algorithm to solve the data dependent hazard of tacking algorithm. Six different types of in-car noises in TAICAR database are used in our evaluation. The experimental results demonstrate that our approach is superior to conventional subspace and spectral subtraction methods.