Chang Woo Han

Reverberation and Noise Robust Feature Compensation Based on IMM

In this paper, we propose a novel feature compensation approach based on the interacting multiple model (IMM) algorithm specially designed for joint processing of background noise and acoustic reverberation. Our approach to cope with the time-varying environmental parameters is to establish a switching linear dynamic model for the additive and convolutive distortions, such as the background noise and acoustic reverberation, in the log-spectral domain. We construct multiple state space models with the speech corruption process in which the log spectra of clean speech and log frequency response of acoustic reverberation are jointly handled as the state of our interest. The proposed approach shows significant improvements in the Aurora-5 automatic speech recognition (ASR) task which was developed to investigate the influence on the performance of ASR for a hands-free speech input in noisy room environments.

Speech Feature Mapping Based on Switching Linear Dynamic System

Signals originated from the same speech source usually appear differently depending on a variety of acoustic effects such as the background noises, linear or nonlinear distortions incurred by the recording devices or reverberations. These acoustical effects result in mismatches between the trained speech recognition models and the input speech. One of the well-known approaches to reduce this mismatch is to map the distorted speech feature to its clean counterpart. The mapping function is usually trained based on a set of stereo data which consists of the simultaneous recordings obtained in both the reference and target conditions. In this paper, we propose the switching linear dynamic system (SLDS) as a useful model for speech feature sequence mapping. In contrast to the conventional vector-to-vector mapping algorithms, SLDS can describe sequence-to-sequence mapping in a systematic way. The proposed approach is applied to robust speech recognition in various environmental conditions and shows a dramatic improvement in recognition performance.

Switching linear dynamic transducer for stereo data based speech feature mapping

The performance of a speech recognition system may be degraded even without any background noise because of the linear or non-linear distortions incurred by recording devices or reverberations. One of the well-known approaches to reduce this channel distortion is feature mapping which maps the distorted speech feature to its clean counterpart. The feature mapping rule is usually trained based on a set of stereo data which consists of the simultaneous recordings obtained in both the reference and target conditions. In this paper, we propose a novel approach to speech feature sequence mapping based on the switching linear dynamic transducer (SLDT). The proposed algorithm enables us a sequence-to-sequence mapping in a systematic way, instead of the traditional vector-to-vector mapping. The proposed approach is applied to compensate channel distortion in speech recognition and shows improvement in recognition performance.

Cepstral domain feature compensation based on diagonal approximation

In this paper, we propose a novel approach to feature compensation performed in the cepstral domain. We apply the linear approximation method in the cepstral domain to simplify the relationship among clean speech, noise and noisy speech. Conventional log-spectral domain feature compensation methods usually assume that each log-spectral coefficient is independent, which is far from real observations. Processing in the cepstral domain has the advantage that the spectral correlation among different frequencies are taken into consideration. By using the diagonal covariance approximation, we can easily modify the conventional log-spectral domain feature compensation technique to fit to the cepstral domain. The proposed approach shows significant improvements in the AURORA2 speech recognition task.

Feature enhancement error compensation for noise robust speech recognition

This paper presents an approach to feature enhancement error compensation for noise robust speech recognition. The conventional feature enhancement techniques estimate the enhanced clean speech from the noise corrupted speech for improving speech recognition performance under noisy environments. During speech feature enhancement process, undesired residual error is generated because of incomplete property of the noise reduction. We apply the switching linear dynamic transducer (SLDT) to compensate this residual error. The SLDT describes the sequence-to-sequence mapping in a systematic way and has been applied to stereo data based speech feature mapping for channel distorted speech recognition. We assume that feature enhancement is a channel. The proposed method shows recognition error reduction in Aurora 2 digit task and Aurora 4 large vocabulary task with the interacting multiple model.

IMM-based feature compensation robust to slowly time-varying noise and reverberation

In this paper, we propose a novel feature compensation approach based on the interacting multiple model (IMM) algorithm specially designed for joint processing of background noise and acoustic reverberation. Our approach to cope with the time-varying environmental parameters is to establish a switching linear dynamic model for the additive and convolutive distortions in the log-spectral domain. The proposed approach shows significant improvements in the Aurora-5 automatic speech recognition (ASR) task which was developed to investigate the influence on the performance of ASR for a hands-free speech input in noisy room environments.

Artificial stereo data generation for speech feature mapping

Feature mapping technique is widely used to eliminate the mismatch between the training and test conditions of speech recognition. In the feature mapping, a target (mismatched) feature vector sequence is mapped closer to the corresponding reference (matched) feature vector stream. The training of the mapping system is usually carried out based on a set of stereo data which consists of simultaneous recordings obtained in both the reference and target conditions. In this paper, we propose a novel approach to blind parameter estimation which does not require the reference feature vectors. The proposed approach is motivated by the hidden Markov model (HMM)-based speech synthesis algorithm.