Namgook Cho

Enhanced voice activity detection using acoustic event detection and classification

We examine user-friendly voice interface that requires the hands-free speech acquisition in the continuously listening environment. The traditional voice activity detection (VAD) algorithms cannot successfully identify potential acoustic event sounds from speech. This makes the speech recognition system frequently or incorrectly activated. In this paper, we propose a novel voice activity detection technique that consists of two major modules: 1) classification and 2) detection module. In the classification module, we label the successive audio segments based on the training models. Then, in the detection module, we remove the acoustic event sounds and make decision of the explicit utterance boundary from the input audio stream. As a result, the proposed technique enables the efficient operation of speech recognition in the continuously listening environment without any touch and/or key input. Experiments in a real-world environment and performance comparison with state-of-the-art techniques are conducted to demonstrate the effectiveness of the proposed technique.

Sparse Music Representation With Source-Specific Dictionaries and Its Application to Signal Separation

We propose a source-specific dictionary approach to efficient music representation, and apply it to separation of music signals that coexist with background noise such as speech or environmental sounds. The basic idea is to determine a set of elementary functions, called atoms, that efficiently capture music signal characteristics. There are three steps in the construction of a source-specific dictionary. First, we decompose basic components of musical signals (e.g., musical notes) into a set of source-independent atoms (i.e., Gabor atoms). Then, we prioritize these Gabor atoms according to their approximation capability to music signals of interest. Third, we use the prioritized Gabor atoms to synthesize new atoms to build a compact dictionary. The number of atoms needed to represent music signals using the source-specific dictionary is much less than that of the Gabor dictionary, resulting in a sparse music representation. For the single-channel music signal separation, we project the mixture signal onto source-specific atoms. Experimental results are given to demonstrate the efficiency and applications of the proposed approach.

Voice activation system using acoustic event detection and keyword/speaker recognition

We study user-friendly voice interface to consumer electronics and propose a voice activation system that can make speech recognition activated only when voice sounds from legitimate users are detected. The proposed system enables efficient operation of speech recognition in a continuous listening environment without any touch and/or key input.

Multi-stage speech enhancement for automatic speech recognition

In this paper, we propose a multi-stage speech enhancement technique for speech recognition. At first, a multi-channel speech enhancement method takes advantage of the spatial information of speech source. Then, in the second stage, single-channel speech enhancement based on data-driven approach is adopted to improve performance of speech recognition at server side. This method can improve the quality of speech signal which maximizes the advantage of each speech enhancement technique. The experimental result shows that the proposed technique is superior to conventional multi-stage speech enhancement algorithms.

Stereophonic acoustic echo cancellation using spatial decorrelation

One of the main challenges for a stereophonic acoustic echo canceller is that it suffers from poor convergence which is caused by strong correlation between the input signals. In this paper, we propose a new decorrelation technique which adopts spatial decorrelation to address the problem without altering the input signals. In the scheme, the input signals are decomposed and projected into the signal subspace and the noise subspace. When the decorrelated signals are fed to the adaptive filters, the interchannel coherence between the input signals decreases significantly. The output signals of the adaptive filters are then combined together to yield the estimate of the microphone signal. Experiments in a real-world environment and performance comparison with state-of-the-art techniques are conducted to demonstrate the effectiveness of the proposed technique.