Spoken content retrieval—beyond cascading speech recognition with text retrieval
Spoken content retrieval refers to directly indexing and retrieving spoken content based on
the audio rather than text descriptions. This potentially eliminates the requirement of …
the audio rather than text descriptions. This potentially eliminates the requirement of …
Sparse transcription
S Bird - Computational Linguistics, 2021 - direct.mit.edu
The transcription bottleneck is often cited as a major obstacle for efforts to document the
world's endangered languages and supply them with language technologies. One solution …
world's endangered languages and supply them with language technologies. One solution …
Written Term Detection Improves Spoken Term Detection
B Yusuf, M Saraçlar - IEEE/ACM Transactions on Audio …, 2024 - ieeexplore.ieee.org
End-to-end (E2E) approaches to keyword search (KWS) are considerably simpler in terms of
training and indexing complexity when compared to approaches which use the output of …
training and indexing complexity when compared to approaches which use the output of …
Joint learning of distance metric and query model for posteriorgram-based keyword search
B Gündoğdu, B Yusuf, M Saraçlar - IEEE Journal of Selected …, 2017 - ieeexplore.ieee.org
In this paper, we propose a novel approach to keyword search (KWS) in low-resource
languages, which provides an alternative method for retrieving the terms of interest …
languages, which provides an alternative method for retrieving the terms of interest …
Automatic speech recognition and topic identification for almost-zero-resource languages
Automatic speech recognition (ASR) systems often need to be developed for extremely low-
resource languages to serve end-uses such as audio content categorization and search …
resource languages to serve end-uses such as audio content categorization and search …
Distance metric learning for posteriorgram based keyword search
B Gündoğdu, M Saraçlar - 2017 IEEE International Conference …, 2017 - ieeexplore.ieee.org
In this paper, we propose a neural network based distance metric learning method for a
better discrimination in the sequence-matching based keyword search (KWS). In this …
better discrimination in the sequence-matching based keyword search (KWS). In this …
Generative RNNs for OOV keyword search
B Gundogdu, B Yusuf, M Saraclar - IEEE Signal Processing …, 2018 - ieeexplore.ieee.org
The modeling of text queries as sequences of embeddings for conducting similarity
matching based search within speech features has been recently shown to improve keyword …
matching based search within speech features has been recently shown to improve keyword …
[PDF][PDF] Similarity Learning Based Query Modeling for Keyword Search.
B Gündogdu, M Saraclar - Interspeech, 2017 - isca-archive.org
In this paper, we propose a novel approach for query modeling using neural networks for
posteriorgram based keyword search (KWS). We aim to help the conventional large …
posteriorgram based keyword search (KWS). We aim to help the conventional large …
[PDF][PDF] Robust speech recognition for low-resource languages
A Romanenko - 2022 - oparu.uni-ulm.de
Process of human-machine interaction is an integral part of everyday human life in a modern
world. The various interfaces are intended to facilitate this interaction and provide maximum …
world. The various interfaces are intended to facilitate this interaction and provide maximum …
Improvements on transducing syllable lattice to word lattice for keyword search
This paper investigates a weighted finite state transducer (WFST) based syllable decoding
and transduction method for keyword search (KWS), and compares it with sub-word search …
and transduction method for keyword search (KWS), and compares it with sub-word search …