Marc Delcroix

On the Use of Lime Dereverberation Algorithm in an Acoustic Environment With a Noise Source

This paper addresses the speech dereverberation problem in the presence of a noise source. We show that the previously presented linear-predictive multi-input equalization (LIME) algorithm can achieve both dereverberation and noise reduction. Experiments show that, for a reverberation time of 0.2 seconds, precise dereverberation is possible in the presence of a colored noise source of SNR of 5 dB, with a dereverberation of the room impulse response by more than 20 dB

Discriminative approach to dynamic variance adaptation for noisy speech recognition

The performance of automatic speech recognition suffers from severe degradation in the presence of noise or reverberation. One conventional approach for handling such acoustic distortions is to use a speech enhancement technique prior to recognition. However, most speech enhancement techniques introduce artifacts that create a mismatch between the enhanced speech features and the acoustic model used for recognition, therefore limiting the improvement in recognition performance. Recently, there has been increased interest in methods capable of compensating for such a mismatch by accounting for the feature variance during decoding. In this paper, we propose to estimate the feature variance using an adaptation technique based on a discriminative criterion. In an experiment using the Aurora2 database, the proposed method could achieve significant digit error rate reduction compared with a spectral subtraction pre-processor, and using a discriminative criterion for adaptation provided further improvement compared with maximum likelihood estimation.

Inverse Filtering for Speech Dereverberation Without the Use of Room Acoustics Information

This chapter discusses multi-microphone inverse filtering, which does not use a priori information of room acoustics, such as room impulse responses between the target speaker and the microphones. One major problem as regards achieving this type of processing is the degradation of the recovered speech caused by excessive equalization of the speech characteristics. To overcome this problem, several approaches have been studied based on a multichannel linear prediction framework, since the framework may be able to perform speech dereverberation as well as noise attenuation. Here, we first discuss the relationship between optimal filtering and linear prediction. Then, we review our four approaches, which differ in terms of their treatment of the statistical properties of a speech signal.

Toolkits for Robust Speech Processing

Recent robust automatic speech recognition (ASR) techniques have been developed rapidly due to the demand placed on ASR applications in real environments, with the help of publicly available tools developed in the community. This chapter overviews major toolkits available for robust ASR, covering general ASR toolkits, language model toolkits, speech enhancement/microphone array front-end toolkits, deep learning toolkits, and emergent end-to-end ASR toolkits. The aim of this chapter is to provide information about functionalities (features, functions, platform, and language), license, and source location so that readers can easily access such tools to build their own robust ASR systems. Some of the toolkits have actually been used to build state-of-the-art ASR systems for various challenging tasks. The references in this chapter also includes the URLs of the resource webpages.