Phonetic subspace features for improved query by example spoken term detection
نویسندگان
چکیده
منابع مشابه
Query-by-example spoken term detection based on phonetic posteriorgram Query-by-example spoken term detection based on phonetic posteriorgram
Spoken term detection in low-resource situations is a challenging problem, because traditional large vocabulary continuous speech recognition (LVCSR) approaches are often unusable. This paper introduces a method to use deep neural network (DNN) softmax outputs as input features in a query-by-example (QBE) spoken term detection (STD) system. Matches between queries and test utterances are locate...
متن کاملSparse Subspace Modeling for Query by Example Spoken Term Detection
We cast the problem of query by example spoken term detection (QbE-STD) as subspace detection where query and background are modeled as a union of low-dimensional subspaces. The speech exemplars used for subspace modeling consist of class-conditional posterior probabilities obtained from deep neural network (DNN). The query and background training exemplars are exploited to model the underlying...
متن کاملQuery-by-Example Spoken Term Detection
This paper aims at a search in a large speech database with zero or low-resource languages by spoken term example in a spoken utterance. The data can not be recognized by Automatic Speech Recognition system due to a lack of resources. A modern method for searching patterns in speech called Query-by-Example is investigated. This technique exploits a well-known dynamic programming approach named ...
متن کاملSubspace Detection of DNN Posterior Probabilities via Sparse Representation for Query by Example Spoken Term Detection
We cast the query by example spoken term detection (QbESTD) problem as subspace detection where query and background subspaces are modeled as union of low-dimensional subspaces. The speech exemplars used for subspace modeling are class-conditional posterior probabilities estimated using deep neural network (DNN). The query and background training exemplars are exploited to model the underlying ...
متن کاملA Phonetic-Based Approach to Query-by-Example Spoken Term Detection
Query-by-Example Spoken Term Detection (QbE-STD) tasks are usually addressed by representing speech signals as a sequence of feature vectors by means of a parametrization step, and then using a pattern matching technique to find the candidate detections. In this paper, we propose a phoneme-based approach in which the acoustic frames are first converted into vectors representing the a posteriori...
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: Speech Communication
سال: 2018
ISSN: 0167-6393
DOI: 10.1016/j.specom.2018.07.001