The MERL/SRI system for the 3rd CHiME challenge using beamforming, robust feature extraction, and advanced speech recognition

Warning The system is temporarily closed to updates for reporting purpose.

Hori, Takaaki and Chen, Zhuo and Erdoğan, Hakan and Hershey, John R. and Le Roux, Jonathan and Mitra, Vikramjit and Watanabe, Shinji (2015) The MERL/SRI system for the 3rd CHiME challenge using beamforming, robust feature extraction, and advanced speech recognition. In: IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU 2015), Scottsdale, Arizona, USA

Full text not available from this repository. (Request a copy)

Abstract

This paper introduces the MERL/SRI system designed for the 3rd CHiME speech separation and recognition challenge (CHiME-3). Our proposed system takes advantage of recurrent neural networks (RNNs) throughout the model from the front speech enhancement to the language modeling. Two different types of beamforming are used to combine multi-microphone signals to obtain a single higher quality signal. Beamformed signal is further processed by a single-channel bi-directional long short-term memory (LSTM) enhancement network which is used to extract stacked mel-frequency cepstral coefficients (MFCC) features. In addition, two proposed noise-robust feature extraction methods are used with the beamformed signal. The features are used for decoding in speech recognition systems with deep neural network (DNN) based acoustic models and large-scale RNN language models to achieve high recognition accuracy in noisy environments. Our training methodology includes data augmentation and speaker adaptive training, whereas at test time model combination is used to improve generalization. Results on the CHiME-3 benchmark show that the full cadre of techniques substantially reduced the word error rate (WER). Combining hypotheses from different robust-feature systems ultimately achieved 9.10% WER for the real test data, a 72.4% reduction relative to the baseline of 32.99% WER.
Item Type: Papers in Conference Proceedings
Uncontrolled Keywords: CHiME-3; robust speech recognition; beamforming; noise robust feature; system combination
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Faculty of Engineering and Natural Sciences > Academic programs > Electronics
Faculty of Engineering and Natural Sciences
Depositing User: Hakan Erdoğan
Date Deposited: 24 Dec 2015 15:39
Last Modified: 26 Apr 2022 09:21
URI: https://research.sabanciuniv.edu/id/eprint/28867

Actions (login required)

View Item
View Item