Improved Frequency Modulation Features For Multichannel Distant Speech Recognition
2018 · Isidoros Rodomagoulakis, Petros Maragos
Abstract
Frequency modulation features capture the fine structure of speech formants that constitute beneficial and supplementary to the traditional energy-based cepstral features. Improvements have been demonstrated mainly in GMM-HMM systems for small and large vocabulary tasks. Yet, they have limited applications in DNN-HMM systems and Distant Speech Recognition (DSR) tasks. Herein, we elaborate on their integration within state-of-the-art front-end schemes that include post-processing of MFCCs resulting in discriminant and speaker adapted features of large temporal contexts. We explore 1) multichannel demodulation schemes for multi-microphone setups, 2) richer descriptors of frequency modulations, and 3) feature transformation and combination via hierarchical deep networks. We present results for tandem and hybrid recognition with GMM and DNN acoustic models, respectively. The improved modulation features are combined efficiently with MFCCs yielding modest and consistent improvements in mult
Authors
(none)
Tags
Stats
Related papers
- Frequency Domain Multi-channel Acoustic Modeling For Distant Speech Recognition (2019)9.92
- Improving Dual-microphone Speech Enhancement By Learning Cross-channel Features With Multi-head Attention (2022)6.77
- 3-D Feature And Acoustic Modeling For Far-field Speech Recognition (2019)0.00
- Distortionless Multi-channel Target Speech Enhancement For Overlapped Speech Recognition (2020)0.00
- Single Channel Far Field Feature Enhancement For Speaker Verification In The Wild (2020)0.00
- DNN-HMM Based Speaker Adaptive Emotion Recognition Using Proposed Epoch And MFCC Features (2018)14.11
- Efficient Multi-channel Speech Enhancement With Spherical Harmonics Injection For Directional Encoding (2023)3.58
- Unsupervised Speech Enhancement Based On Multichannel Nmf-informed Beamforming For Noise-robust Automatic Speech Recognition (2019)13.23