A hybrid HMM/DNN approach to keyword spotting of short words
نویسندگان
چکیده
An HMM/DNN framework is proposed to address the issues of short-word detection. The first-stage keyword hypothesizer is redesigned with a context-aware keyword model and a 9state filler model to reduce the miss rate from 80% to 6% and increase the figure-of-merit (FOM) from 6.08% to 21.88% for short words. The hypothesizer is followed by a MLP-based second-stage keyword verifier to further reduce its putative hits. To enhance short word detection, three new techniques, including an HMM-based feature transformation for the MLPs, knowledge-based features, and deep neural networks, are incorporated into redesigning the verifier. With a set of nine short keywords from the TIMIT set the best FOM we had achieved for the proposed KWS system was 42.79%, which is comparable with that of 42.6% for long content words and much better than the FOM of 18.4% for short keywords reported in previous research [10].
منابع مشابه
Unrestricted Vocabulary Keyword Spotting Using LSTM-CTC
Keyword spotting (KWS) aims to detect predefined keywords in continuous speech. Recently, direct deep learning approaches have been used for KWS and achieved great success. However, these approaches mostly assume fixed keyword vocabulary and require significant retraining efforts if new keywords are to be detected. For unrestricted vocabulary, HMM based keywordfiller framework is still the main...
متن کاملExploiting phoneme similarities in hybrid HMM-ANN keyword spotting
We propose a technique for generating alternative models for keywords in a hybrid hidden Markov model artificial neural network (HMM-ANN) keyword spotting paradigm. Given a base pronunciation for a keyword from the lookup dictionary, our algorithm generates a new model for a keyword which takes into account the systematic errors made by the neural network and avoiding those models that can be c...
متن کاملNon-Uniform Boosted MCE Training of Deep Neural Networks for Keyword Spotting
Keyword spotting can be formulated as a non-uniform error automatic speech recognition (ASR) problem. It has been demonstrated [1] that this new formulation with the nonuniform MCE training technique can lead to improved system performance in keyword spotting applications. In this paper, we demonstrate that deep neural networks (DNNs) can be successfully trained on the non-uniform minimum class...
متن کاملPerformance Improvement in Keyword Spotting for Telephony Services
In this paper, a new hybrid approach is presented for keyword spotting. The proposed Method is based on Hidden Markov Mode (HMM) and is performed in two stages. In the first stage by using phoneme models, a series of candidate keyword(s) is recognized. In the second stage, word models are used to decide on acceptance or rejection of each candidate keyword. Two different methods are presented in...
متن کاملOff-line Arabic Handwritten Recognition Using a Novel Hybrid HMM-DNN Model
In order to facilitate the entry of data into the computer and its digitalization, automatic recognition of printed texts and manuscripts is one of the considerable aid to many applications. Research on automatic document recognition started decades ago with the recognition of isolated digits and letters, and today, due to advancements in machine learning methods, efforts are being made to iden...
متن کامل