Matching the Acoustic Model to Front-End Signal Processing for ASR in Noisy and Reverberant Environments
نویسندگان
چکیده
Distant-talking automatic speech recognition (ASR) represents an extremely challenging task. The major reason is that unwanted additive interference and reverberation are picked up by the microphones besides the desired signal. A hands-free human-machine interface should therefore comprise a powerful acoustic preprocessing unit in line with a robust ASR back-end. However, since perfect speech enhancement cannot be achieved in practice, the output of the front-end will always contain some residual interference and some distortion of the desired signal. It is hence of decisive importance to carefully adjust the hidden Markovmodels (HMMs) of the ASR system to the front-end. In this contribution, we present a two-channel acoustic front-end based on blind source separation along with Wiener filtering. For the front-end integration into the ASR system, different types of multi-style as well as adaptive training and HMM adaptation are investigated.
منابع مشابه
Towards Natural Acoustic Interfaces for Automatic Speech Recognition
Aiming at ’natural’ hands-free acoustic human/machine interfaces, the need for according distant-talking automatic speech recognition (ASR) systems increases and presents us with major signal processing challenges at the acoustic front-end. Considering interactive TV as a challenging exemplary application scenario, we investigate the structural problems presented by noisy and reverberant multi-...
متن کاملA Two-Channel Acoustic Front-End for Robust Automatic Speech Recognition in Noisy and Reverberant Environments
An acoustic front-end for robust automatic speech recognition in noisy and reverberant environments is proposed in this contribution. It comprises a blind source separation-based signal extraction scheme and only requires two microphone signals. The proposed front-end and its integration into the recognition system is analyzed and evaluated in noisy living room-like environments according to th...
متن کاملMultipitch Tracking for Noisy and Reverberant Speech
Abstract – Multipitch tracking in real environments is critical for speech signal processing. Determining pitch in reverberant and noisy speech is a particularly challenging task. In this paper, we propose a robust algorithm for multipitch tracking in the presence of both background noise and room reverberation. An auditory front-end and a new channel selection method are utilized to extract pe...
متن کاملOptimization of Speech Enhancement Front-End with Speech Recognition-Level Criterion
This paper concerns the use of speech enhancement to improve automatic speech recognition (ASR) performance in noisy environments. Speech enhancement systems are usually designed separately from a back-end recognizer by optimizing the frontend parameters with signal-level criteria. Such a disjoint processing approach is not always useful for ASR. Indeed, timefrequency masking, which is widely u...
متن کاملVerified speaker localization utilizing voicing level in split-bands
This paper proposes a joint verification-localization structure based on split-band analysis of speech signal and the mixed voicing level. To address the problems in reverberant acoustic environments, a new fundamental frequency estimation algorithm is proposed based on high resolution spectral estimation. In the reconstruction of the distorted speech this information is utilized to reduce the ...
متن کامل