• The Journal of the Acoustical Society of Korea
• /
• v.39 no.2
• /
• pp.131-136
• /
• 2020

Wake Up Word (WUW) is a short utterance used to convert speech recognizer to recognition mode. The WUW defined by the user who actually use the speech recognizer is called user-defined WUW. In this paper, to recognize user-defined WUW, we construct traditional Gaussian Mixture Model-Hidden Markov Model (GMM-HMM), Linear Discriminant Analysis (LDA)-GMM-HMM and LDA-Deep Neural Network (DNN)-HMM based system and compare their performances. Also, to improve recognition accuracy of the WUW system, a threshold method is applied to each model, which significantly reduces the error rate of the WUW recognition and the rejection failure rate of non-WUW simultaneously. For LDA-DNN-HMM system, when the WUW error rate is 9.84 %, the rejection failure rate of non-WUW is 0.0058 %, which is about 4.82 times lower than the LDA-GMM-HMM system. These results demonstrate that LDA-DNN-HMM model developed in this paper proves to be highly effective for constructing user-defined WUW recognition system.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.453-458
• /
• 2018

본 논문은 한국어 자소를 인식 단위로 사용한 hybrid CTC-Attention 모델 기반 end-to-end speech recognition을 제안한다. End-to-end speech recognition은 기존에 사용된 DNN-HMM 기반 음향 모델과 N-gram 기반 언어 모델, WFST를 이용한 decoding network라는 여러 개의 모듈로 이루어진 과정을 하나의 DNN network를 통해 처리하는 방법을 말한다. 본 논문에서는 end-to-end 모델의 출력을 추정하기 위해 자소 단위의 출력구조를 사용한다. 자소 기반으로 네트워크를 구성하는 경우, 추정해야 하는 출력 파라미터의 개수가 11,172개에서 49개로 줄어들어 보다 효율적인 학습이 가능하다. 이를 구현하기 위해, end-to-end 학습에 주로 사용되는 DNN 네트워크 구조인 CTC와 Attention network 모델을 조합하여 end-to-end 모델을 구성하였다. 실험 결과, 음절 오류율 기준 10.05%의 성능을 보였다.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.335-341
• /
• 2022

In this paper, we adopt a transformer that shows remarkable performance in natural language processing as an acoustic model of hybrid speech recognition. The transformer acoustic model uses attention structures to process sequential data and shows high performance with low computational cost. This paper proposes a method to improve the performance of transformer AM by applying each of the four algorithms of sequence discriminative training, a weighted finite-state transducer (wFST)-based learning used in the existing DNN-HMM model. In addition, compared to the Cross Entropy (CE) learning method, sequence discriminative method shows 5 % of the relative Word Error Rate (WER).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.7
• /
• pp.2785-2799
• /
• 2020

We propose a novel speaker adaptation method using acoustic model clustering. The similarity of different speakers is defined by the cosine distance between their i-vectors (intermediate vectors), and various efficient clustering algorithms are applied to obtain a number of speaker subsets with different characteristics. The speaker-independent model is then retrained with the training data of the individual speaker subsets grouped by the clustering results, and an unknown speech is recognized by the retrained model of the closest cluster. The proposed method is applied to a large-scale speech recognition system implemented by a hybrid hidden Markov model and deep neural network framework. An experiment was conducted to evaluate the word error rates using Resource Management database. When the proposed speaker adaptation method using i-vector based clustering was applied, the performance, as compared to that of the conventional speaker-independent speech recognition model, was improved relatively by as much as 12.2% for the conventional fully neural network, and by as much as 10.5% for the bidirectional long short-term memory.