[HTML][HTML] Spoken term detection ALBAYZIN 2014 evaluation: overview, systems, results, and discussion
J Tejedor, DT Toledano, P Lopez-Otero… - EURASIP Journal on …, 2015 - Springer
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 …
representation of the search term. Nowadays, it is receiving much interest due to the large …
End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations
B Yusuf, J Černocký, M Saraçlar - IEEE/ACM Transactions on …, 2023 - ieeexplore.ieee.org
Conventional keyword search systems operate on automatic speech recognition (ASR)
outputs, which causes them to have a complex indexing and search pipeline. This has led to …
outputs, which causes them to have a complex indexing and search pipeline. This has led to …
Constructing sub-word units for spoken term detection
C Van Heerden, D Karakos… - … , Speech and Signal …, 2017 - ieeexplore.ieee.org
Spoken term detection, especially of out-of-vocabulary (OOV) keywords, benefits from the
use of sub-word systems. We experiment with different language-independent approaches …
use of sub-word systems. We experiment with different language-independent approaches …
Low resource keyword search with synthesized crosslingual exemplars
B Yusuf, B Gundogdu, M Saraclar - IEEE/ACM Transactions on …, 2019 - ieeexplore.ieee.org
The transfer of acoustic data across languages has been shown to improve keyword search
(KWS) performance in data-scarce settings. In this paper, we propose a way of performing …
(KWS) performance in data-scarce settings. In this paper, we propose a way of performing …
On the study of very low-resource language keyword search
In this paper we report our approaches to accomplishing the very limited resource keyword
search (KWS) task in the NIST Open Keyword Search 2015 (OpenKWS15) Evaluation. We …
search (KWS) task in the NIST Open Keyword Search 2015 (OpenKWS15) Evaluation. We …
Pruning strategies for partial search in spoken term detection
In this paper, we propose a partial search approach for subword-based keyword search
(KWS) systems. The proposed approach addresses the problem of high miss rate in the …
(KWS) systems. The proposed approach addresses the problem of high miss rate in the …
Morph-to-word transduction for accurate and efficient automatic speech recognition and keyword search
A Ragni, D Saunders, P Zahemszky… - … , Speech and Signal …, 2017 - ieeexplore.ieee.org
Word units are a popular choice in statistical language modelling. For inflective and
agglutinative languages this choice may result in a high out of vocabulary rate. Subword …
agglutinative languages this choice may result in a high out of vocabulary rate. Subword …
[图书][B] Segmental models with an exploration of acoustic and lexical grouping in automatic speech recognition
Y He - 2015 - search.proquest.com
Developing automatic speech recognition (ASR) technologies is of significant importance to
facilitate human-machine interactions. The main challenges for ASR development have …
facilitate human-machine interactions. The main challenges for ASR development have …
Robust spoken term detection using partial search and re-scoring hypothesized detections techniques
VT Pham - 2019 - dr.ntu.edu.sg
This research focusses on Spoken Term Detection (STD) which aims to detect a textual
keyword in a speech corpus. A typical STD system relies on an Automatic Speech …
keyword in a speech corpus. A typical STD system relies on an Automatic Speech …
[PDF][PDF] Syllable based Lattice Transduction for Keyword Search
H Su - 2015 - eecs.berkeley.edu
Low-resource speech recognition and keyword search (KWS) are important topics for
speech technologies. However, their performance often suffers from out-ofvocabulary (OOV) …
speech technologies. However, their performance often suffers from out-ofvocabulary (OOV) …