A new speech enhancement: speech stream segregation
نویسندگان
چکیده
Speech stream segregation is presented as a new speech enhancement for automatic speech recognition. Two issues are addressed: speech stream segregation from a mixture of sounds, and interfacing speech stream segregation with automatic speech recognition. Speech stream segregation is modeled as a process of extracting harmonic fragments, grouping these extracted harmonic fragments, and substituting non-harmonic residue for non-harmonic parts of groups. The main problem in interfacing speech stream segregation with HMM-based speech recognition is how to improve the degradation of recognition performance due to spectral distortion of segregated sounds, which is caused mainly by transfer function of a binaural input. Our solution is to re-train the parameters of HMM with training data binauralized for four directions. Experiments with 500 mixtures of two women's utterances of a word showed that the cumulative accuracy of word recognition up to the 10th candidate of each woman's utterance is, on average, 75%.
منابع مشابه
A New Shuffled Sub-swarm Particle Swarm Optimization Algorithm for Speech Enhancement
In this paper, we propose a novel algorithm to enhance the noisy speech in the framework of dual-channel speech enhancement. The new method is a hybrid optimization algorithm, which employs the combination of the conventional θ-PSO and the shuffled sub-swarms particle optimization (SSPSO) technique. It is known that the θ-PSO algorithm has better optimization performance than standard PSO al...
متن کاملChallenge Problem for Computational Auditory Scene Analysis: Understanding Three Simultaneous Speeches
Understanding three simultaneous speeches is proposed as a challenge problem to foster arti cial intelligence, speech and sound understanding or recognition, and computational auditory scene analysis research. Automatic speech recognition under noisy environments is attacked by speech enhancement techniques such as noise reduction and speaker adaptation. However, the signal-to-noise ratio of sp...
متن کاملUnderstanding Three Simultaneous Speeches
Understanding three simultaneous speeches is proposed as a challenge problem to foster artificial intelligence, speech and sound understanding or recognition, and computational auditory scene analysis research. Automatic speech recognition under noisy environments is attacked by speech enhancement techniques such as noise reduction and speaker adaptation. However, the signal-to-noise ratio of s...
متن کاملSpeech Enhancement by Modified Convex Combination of Fractional Adaptive Filtering
This paper presents new adaptive filtering techniques used in speech enhancement system. Adaptive filtering schemes are subjected to different trade-offs regarding their steady-state misadjustment, speed of convergence, and tracking performance. Fractional Least-Mean-Square (FLMS) is a new adaptive algorithm which has better performance than the conventional LMS algorithm. Normalization of LMS ...
متن کاملSpeech enhancement based on hidden Markov model using sparse code shrinkage
This paper presents a new hidden Markov model-based (HMM-based) speech enhancement framework based on the independent component analysis (ICA). We propose analytical procedures for training clean speech and noise models by the Baum re-estimation algorithm and present a Maximum a posterior (MAP) estimator based on Laplace-Gaussian (for clean speech and noise respectively) combination in the HMM ...
متن کامل