Exemplar-Based Sparse Representations for Noise Robust Automatic Speech Recognition
نویسندگان
چکیده
منابع مشابه
Noise-robust Automatic Speech Recognition with Exemplar-based Sparse Representations Using Multiple Length Adaptive Dictionaries
In this work, we apply our recently proposed sparse representations based speech recognition system on the small vocabulary track of the 2 ‘CHiME’ Speech Separation and Recognition Challenge. This system uses exemplars of different length to approximate noisy speech segments as a linear combination of the speech and noise exemplars with sparse weights. The exemplars are labeled speech segments ...
متن کاملExemplar-based speech enhancement and its application to noise-robust automatic speech recognition
In this work an exemplar-based technique for speech enhancement of noisy speech is proposed. The technique works by finding a sparse representation of the noisy speech in a dictionary containing both speech and noise exemplars, and uses the activated dictionary atoms to create a time-varying filter to enhance the noisy speech. The speech enhancement algorithm is evaluated using measured signal ...
متن کاملNoise robust exemplar matching for speech enhancement: applications to automatic speech recognition
We present a novel automatic speech recognition (ASR) scheme which uses the recently proposed noise robust exemplar matching framework for speech enhancement in the front-end. The proposed system employs a GMM-HMM back-end to recognize the enhanced speech signals unlike the prior work focusing on template matching only. Speech enhancement is achieved using multiple dictionaries containing speec...
متن کاملNoise robust digit recognition using sparse representations
Despite the use o f noise robustness techniques, automatic speech recognition (ASR) systems make many more recognition errors than humans, especially in very noisy circumstances. We argue that this inferior recognition performance is largely due to the fact that in ASR speech is typically processed on a frameby-frame basis preventing the redundancy in the speech signal to be optimally exploited...
متن کاملCombining exemplar-based matching and exemplar-based sparse representations of speech
In this paper, we compare two different frameworks for exemplarbased speech recognition and propose a combined system that approximates the input speech as a linear combination of exemplars of variable length. This approach allows us not only to use multiple length long exemplars, each representing a certain speech unit, but also to jointly approximate input speech segments using several exempl...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Audio, Speech, and Language Processing
سال: 2011
ISSN: 1558-7916,1558-7924
DOI: 10.1109/tasl.2011.2112350