Weighted Viterbi algorithm and state duration modelling for speech recognition in noise
نویسندگان
چکیده
A weighted Viterbi algorithm (HMM) is proposed and applied in combination with spectral subtraction and Cepstral Mean Normalization to cancel both additive and convolutional noises in speech recognition. The weighted Viterbi approach is compared and used in combination with state duration modelling. The results presented in this paper show that a proper weight on the information provided by static parameters can substantially reduce the error rate, and that the weighting procedure improves better the robustness of the Viterbi algorithm than the introduction of temporal constraints with a low computational load. Finally, it is shown ihat the weighted Viterbi algorithm in combination with temporal constraints leads to a high recognition accuracy itt moderate SNR's without the need of an accurate noise model.
منابع مشابه
Improving Phoneme Sequence Recognition using Phoneme Duration Information in DNN-HSMM
Improving phoneme recognition has attracted the attention of many researchers due to its applications in various fields of speech processing. Recent research achievements show that using deep neural network (DNN) in speech recognition systems significantly improves the performance of these systems. There are two phases in DNN-based phoneme recognition systems including training and testing. Mos...
متن کاملRobust connected word speech recognition using weighted viterbi algorithm and context-dependent temporal constraints
This paper addresses the problem of connected word speech recognition with signals corrupted by additive and convolutional noise. Context-dependent temporal constraints are proposed and compared with the ordinary temporal restrictions, and used in combination with the weighted Viterbi algorithm which had been tested with isolated word recognition experiments in previous papers. Connected-word r...
متن کاملTemporal constraints in viterbi alignment for speech recognition in noise
This paper addresses the problem of temporal constraints in the Viterbi algorithm using conditional transition probabilities. The results here presented suggest that in a speaker dependent small vocabulary task the statistical modelling of state durations is not relevant if the max and min state duration restrictions are imposed, and that truncated probability densities give better results than...
متن کاملA Noise-Robust ASR Back-end Techniqu Recognition
The performance of speech recognition systems trained in quiet degrades significantly under noisy conditions. To address this problem, a Weighted Viterbi Recognition (WVR) algorithm that is a function of the SNR of each speech frame is proposed. Acoustic models trained on clean data, and the acoustic front-end features are kept unchanged in this approach. Instead, a confidence/robustness factor...
متن کاملSpeaker dependent temporal constraints combined with speaker independent HMM for speech recognition in noise
This paper addresses the problem of speech recognition in noise using speaker-dependent temporal constraints in the Viterbi algorithm in combination with speaker-independent HMM. It is shown that the speaker-dependent re-estimation of state duration parameters requires a low computational load and a small training database, and can lead to reductions in the error rate as high as 30% or 40% with...
متن کامل