Abstract Long Short-Term Memory (LSTM) is a recurrent neural network (RNN) architecture
specializing in modeling long-range temporal dynamics. On acoustic modeling tasks, LSTM …

Spoken term detection (STD) aims at retrieving data from a speech repository given a textual
representation of the search term. Nowadays, it is receiving much interest due to the large …

Multilingual deep neural networks (DNNs) can act as deep feature extractors and have been
applied successfully to crosslanguage acoustic modeling. Learning these feature extractors …

When deployed in automated speech recognition (ASR), deep neural networks (DNNs) can
be treated as a complex feature extractor plus a simple linear classifier. Previous work has …

Query-by-example spoken document retrieval (QbESDR) aims at finding those documents in
a set that include a given spoken query. Current approaches are, in general, not valid for …

The most common pipelines in keyword spotting involve some kind of speech recognition,
which leads to the generation of sets of plausible hypotheses (eg, word lattices), which are …

Query-by-example spoken document retrieval (QbESDR) consists in, given a collection of
documents, computing how likely a spoken query is present in each document. This is …

针对词图合并方法产生的词图冗余信息过多, 规模较大, 导致检索速度较慢的问题,
本文提出了一种基于词图相交融合的语音关键词检测方法. 首先, 将不同语音识别系统产生的词 …

Spoken keyword search (KWS) is a task to detect a set of keywords in continuous speech. It
could be considered as an application of automatic speech recognition (ASR) focusing only …

With the advent of the big data era, the amount of audio data is rapidly increasing. In order to
effectively utilize this information, we urgently need an efficient method for retrieving speech …