检索结果-内蒙古大学图书馆

query-by-example Spoken Term Detection ALBAYZIN 2012 evaluation: overview, systems, results, and discussion

EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING 2013年第1期2013卷 1-17页

作者： Tejedor, Javier Toledano, Doroteo T. Anguera, Xavier Varona, Amparo Hurtado, Lluis F. Miguel, Antonio Colas, Jose Univ Autonoma Madrid Human Comp Technol Lab HCTLab E-28049 Madrid Spain Univ Autonoma Madrid Biometr Recognit Grp ATVS E-28049 Madrid Spain Telefon Res Barcelona Spain Univ Basque Country UPV EHU Working Grp Software Technol GTTS Leioa 48940 Spain Univ Politecn Valencia Dept Sistemes Informat & Comp Valencia 46022 Spain Univ Zaragoza Voice Input Voice Output Lab ViVoLab Aragon Inst Engn Res I3A Zaragoza 50018 Spain

query-by-example Spoken Term Detection (QbE STD) aims at retrieving data from a speech data repository given an acoustic query containing the term of interest as input. Nowadays, it has been receiving much interest due to the high volume of information stored in audio or audiovisual format. QbE STD differs from automatic speech recognition (ASR) and keyword spotting (KWS)/spoken term detection (STD) since ASR is interested in all the terms/words that appear in the speech signal and KWS/STD relies on a textual transcription of the search term to retrieve the speech data. This paper presents the systems submitted to the ALBAYZIN 2012 QbE STD evaluation held as a part of ALBAYZIN 2012 evaluation campaign within the context of the IberSPEECH 2012 Conference(a). The evaluation consists of retrieving the speech files that contain the input queries, indicating their start and end timestamps within the appropriate speech file. Evaluation is conducted on a Spanish spontaneous speech database containing a set of talks from MAVIR workshops(b), which amount at about 7 h of speech in total. We present the database metric systems submitted along with all results and some discussion. Four different research groups took part in the evaluation. Evaluation results show the difficulty of this task and the limited performance indicates there is still a lot of room for improvement. The best result is achieved by a dynamic time warping-based search over Gaussian posteriorgrams/posterior phoneme probabilities. This paper also compares the systems aiming at establishing the best technique dealing with that difficult task and looking for defining promising directions for this relatively novel task.

关键词： query-by-example Spoken term detection International evaluation Search on spontaneous speech

来源：评论

学校读者我要写书评

暂无评论

query-by-example surgical activity detection

引用

INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY 2016年第6期11卷 987-996页

作者： Gao, Yixin Vedula, S. Swaroop Lee, Gyusung I. Lee, Mija R. Khudanpur, Sanjeev Hager, Gregory D. Johns Hopkins Univ Dept Comp Sci Whiting Sch Engn Baltimore MD 21218 USA Johns Hopkins Univ Sch Med Dept Surg Baltimore MD 21287 USA Johns Hopkins Univ Dept Elect & Comp Engn Whiting Sch Engn Baltimore MD 21218 USA

Easy acquisition of surgical data opens many opportunities to automate skill evaluation and teaching. Current technology to search tool motion data for surgical activity segments of interest is limited by the need for manual pre-processing, which can be prohibitive at scale. We developed a content-based information retrieval method, query-by-example (QBE), to automatically detect activity segments within surgical data recordings of long duration that match a query. The example segment of interest (query) and the surgical data recording (target trial) are time series of kinematics. Our approach includes an unsupervised feature learning module using a stacked denoising autoencoder (SDAE), two scoring modules based on asymmetric subsequence dynamic time warping (AS-DTW) and template matching, respectively, and a detection module. A distance matrix of the query against the trial is computed using the SDAE features, followed by AS-DTW combined with template scoring, to generate a ranked list of candidate subsequences (substrings). To evaluate the quality of the ranked list against the ground-truth, thresholding conventional DTW distances and bipartite matching are applied. We computed the recall, precision, F1-score, and a Jaccard index-based score on three experimental setups. We evaluated our QBE method using a suture throw maneuver as the query, on two tool motion datasets (JIGSAWS and MISTIC-SL) captured in a training laboratory. We observed a recall of 93, 90 and 87 % and a precision of 93, 91, and 88 % with same surgeon same trial (SSST), same surgeon different trial (SSDT) and different surgeon (DS) experiment setups on JIGSAWS, and a recall of 87, 81 and 75 % and a precision of 72, 61, and 53 % with SSST, SSDT and DS experiment setups on MISTIC-SL, respectively. We developed a novel, content-based information retrieval method to automatically detect multiple instances of an activity within long surgical recordings. Our method demonstrated adequate recall across d

关键词： query-by-example Stacked denoising autoencoder Asymmetric subsequence dynamic time warping Surgical data indexing Surgical activity detection

来源：评论

学校读者我要写书评

暂无评论

query-by-example speech search using Mamba and Random Offset Mixed Padding 14

Query-by-Example speech search using Mamba and Random Offset...

引用

14th International Symposium on Chinese Spoken Language Processing

作者： Yang, Kaixin Cheng, Gaofeng Li, Ta Zhao, Qingwei Yan, Yonghong Chinese Acad Sci Inst Acoust Key Lab Speech Acoust & Content Understanding Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9798331516833;9798331516826

State-of-the-art approaches to query-by-example speech search are usually based on acoustic word embedding (AWE), representing variable-length speech segments with fixed-dimensional vectors using metric learning. In this paper, we propose a novel AWE network based on Mamba, a new state space model architecture for information-dense data. In order to further mitigate the mismatch between the training phase and the testing phase of AWE-based models, we also propose a novel audio segment padding method used in the training phase, Random Offset Mixed Padding. Comparisons with the state-of-the-art methods show that our method, Mamba-based network together with Random Offset Mixed Padding, achieves the best performance with significantly fewer parameters. We also demonstrate that the proposed padding method can enhance the performance of AWE-based baseline models.

关键词： query-by-example speech search spoken term detection Mamba

来源：评论

学校读者我要写书评

暂无评论

query-by-example KEYWORD SPOTTING SYSTEM USING MULTI-HEAD ATTENTION AND SOFTTRIPLE LOSS

QUERY-BY-EXAMPLE KEYWORD SPOTTING SYSTEM USING MULTI-HEAD AT...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Huang, Jinmiao Gharbieh, Waseem Shim, Han Suk Kim, Eugene LG Elect Toronto AI Lab Toronto ON Canada LG Elect Artificial Intelligence Lab Seoul South Korea

ISBN: (纸本)9781728176055

This paper proposes a neural network architecture for tackling the query-by-example user-defined keyword spotting task. A multi-head attention module is added on top of a multi-layered GRU for effective feature extraction, and a normalized multi-head attention module is proposed for feature aggregation. We also adopt the softtriple loss - a combination of triplet loss and softmax loss - and showcase its effectiveness. We demonstrate the performance of our model on internal datasets with different languages and the public Hey-Snips dataset. We compare the performance of our model to a baseline system [1] and conduct an ablation study to show the benefit of each component in our architecture. The proposed work shows solid performance while preserving simplicity.

关键词： User-defined Keyword Spotting query-by-example Multi-head Attention Softtriple Deep Metric Learning

来源：评论

学校读者我要写书评

暂无评论

query-by-example Search with Discriminative Neural Acoustic Word Embeddings 18

Query-by-Example Search with Discriminative Neural Acoustic ...

引用

18th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2017)

作者： Settle, Shane Levin, Keith Kamper, Herman Livescu, Karen TTI Chicago IL 60637 USA Johns Hopkins Univ Baltimore MD 21218 USA

ISBN: (纸本)9781510848764

query-by-example search often uses dynamic time warping (DTW) for comparing queries and proposed matching segments. Recent work has shown that comparing speech segments by representing them as fixed-dimensional vectors - acoustic word embeddings - and measuring their vector distance (e.g., cosine distance) can discriminate between words more accurately than DTW-based approaches. We consider an approach to query-by-example search that embeds both the query and database segments according to a neural model, followed by nearest neighbor search to find the matching segments. Earlier work on embedding-based query-by-example, using template-based acoustic word embeddings, achieved competitive performance. We find that our embeddings, based on recurrent neural networks trained to optimize word discrimination. achieve substantial improvements in performance and run-time efficiency over the previous approaches.

关键词： query-by-example acoustic word embeddings word discrimination recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

query-by-example music information retrieval by score-based genre prediction and similarity measure

引用

INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL 2017年第2期6卷 155-166页

作者： Borjian, Nastaran Tarbiat Modares Univ Dept Elect & Comp Engn Tehran Iran

Atopic of music information retrieval (MIR) field is query-by-example (QBE), which searches a popular music dataset using a user-provided query and aims to find the target song. Since this type of MIR has been generally used in online systems, retrieval time is also as important as accuracy. In this paper, we propose a QBE-based MIR system and investigate the impact of automatic music genre prediction on the performance of it, specifically on perspective of accuracy-time trade-off, using a score-based genre prediction method as well as similarity measures. The proposed system is evaluated on a dataset containing 6000 music pieces from six musical genres, and we show that how much improvement on the performance can be achieved in terms of accuracy and retrieval time, compared with a typical QBE-based MIR system that uses only similarity measures to find the user-desired song.

关键词： Music information retrieval query-by-example Score-based genre prediction Similarity measure

来源：评论

学校读者我要写书评

暂无评论

query-by-example Spoken Term Detection Using Generative Adversarial Network

Query-By-Example Spoken Term Detection Using Generative Adve...

引用

Asia-Pacific-Signal-and-Information-Processing-Association Annual Summit and Conference (APSIPA ASC)

作者： Shah, Neil Sreeraj, R. Madhavi, Maulik C. Shah, Nirmesh J. Patil, Hemant A. Dhirubahi Ambani Inst Informat & Commun Technol D Gandhinagar India Tata Consultancy Serv Pvt Ltd TCS Res Pune Maharashtra India Natl Univ Singapore Dept Elect & Comp Engn Singapore Singapore

ISBN: (纸本)9789881476883

Several Neural Network (NN)-based representation techniques have already been proposed for query-by-example Spoken Term Detection (QbE-STD) task. The recent advancement in Generative Adversarial Network (GAN) for several speech technology applications, motivated us to explore the GAN in QbE-STD. In this work, we propose to exploit GAN with the regularized cross-entropy loss, and develop a framework featuring GAN, trained using Gaussian Mixture Model (GMM)-based posterior labels. The proposed GAN maps the speech-specific features to the unsupervised posterior labels. This mapping represents the speech through an unsupervised GAN posteriorgram (uGAN-PG), for matching the query (keyword) with the utterances in the document. The QbE-STD, using the proposed posteriorgram is performed on the TIMIT database. We compare the performance of the proposed uGAN-PG with the unsupervised Deep Neural Network (DNN) posteriorgram (uDNN-PG) and obtained the relative performance improvement of 10.32 % Mean Average Precision and 5.6 % Precision by considering top N queries (p@N) over uDNN-PG.

关键词： query-by-example Generative Adversarial Network Posteriorgram Spoken term detection

来源：评论

学校读者我要写书评

暂无评论

query-by-example ON-DEVICE KEYWORD SPOTTING

QUERY-BY-EXAMPLE ON-DEVICE KEYWORD SPOTTING

引用

IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

作者： Kim, Byeonggeun Lee, Mingu Lee, Jinkyu Kim, Yeonseok Hwang, Kyuwoong Qualcomm AI Res Seoul South Korea

ISBN: (纸本)9781728103068

A keyword spotting (KWS) system determines the existence of, usually predefined, keyword in a continuous speech stream. This paper presents a query-by-example on-device KWS system which is user-specific. The proposed system consists of two main steps: query enrollment and testing. In query enrollment step, phonetic posteriors are output by a small-footprint automatic speech recognition model based on connectionist temporal classification. Using the phonetic-level posteriorgram, hypothesis graph of finite-state transducer (FST) is built, thus can enroll any keywords thus avoiding an out-of-vocabulary problem. In testing, a log-likelihood is scored for input audio using the FST. We propose a threshold prediction method while using the user-specific keyword hypothesis only. The system generates query-specific negatives by rearranging each query utterance in waveform. The threshold is decided based on the enrollment queries and generated negatives. We tested two keywords in English, and the proposed work shows promising performance while preserving simplicity.

关键词： keyword spotting user-specific query-by-example on-device threshold prediction

来源：评论

学校读者我要写书评

暂无评论

query-by-example Search with Multi-view Recurrent Auto-Encoder Representation 2021

Query-by-Example Search with Multi-view Recurrent Auto-Encod...

引用

2nd International Conference on Artificial Intelligence and Information Systems (ICAIIS )

作者： Lv, Lixia Wang, Lei Beijing Univ Posts & Telecommun Beijing Peoples R China

ISBN: (纸本)9781450390200

query-by-example (QbE) speech search is the task of matching spoken queries with speech recordings in the search collection. With the rapid development of human-computer voice interaction technology, higher requirements are put forward for the search of spoken queries. In low-resource or zero-resource settings, QbE speech search usually uses dynamic time warping (DTW) to compare spoken queries and speech segments in the search collection. Recent studies have found that methods based on acoustic word embedding can not only improve search performance but also increase search speed. In this paper, we combine the autoencoder and multi-view method, and propose a weakly supervised method to train a multi-view recurrent autoencoder (RAE) model. This model can represent spoken queries and speech segments in the search collection as fixed dimensional vectors, and then find the matching speech segments by nearest neighbor search.

关键词： query-by-example multi-view recurrent auto-encoder acoustic word embeddings

来源：评论

学校读者我要写书评

暂无评论

Multitask Feature Learning for Low-Resource query-by-example Spoken Term Detection

引用

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING 2017年第8期11卷 1329-1339页

作者： Chen, Hongjie Leung, Cheung-Chi Xie, Lei Ma, Bin Li, Haizhou Northwestern Polytech Univ Sch Comp Sci Xian 710129 Shaanxi Peoples R China Agcy Sci Technol & Res Inst Infocomm Res Singapore 138632 Singapore Natl Univ Singapore Dept Elect & Comp Engn Singapore 117583 Singapore

We propose a novel technique that learns a low-dimensional feature representation from unlabeled data of a target language, and labeled data from a nontarget language. The technique is studied as a solution to query-by-example spoken term detection (QbE-STD) for a low-resource language. We extract low-dimensional features from a bottle-neck layer of a multitask deep neural network, which is jointly trained with speech data from the low-resource target language and resource-rich nontarget language. The proposed feature learning technique aims to extract acoustic features that offer phonetic discriminability. It explores a new way of leveraging cross-lingual speech data to overcome the resource limitation in the target language. We conduct QbE-STD experiments using the dynamic time warping distance of the multitask bottle-neck features between the query and the search database. The QbE-STD process does not rely on an automatic speech recognition pipeline of the target language. We validate the effectiveness of multitask feature learning through a series of comparative experiments.

关键词： query-by-example spoken term detection multitask learning bottle-neck feature

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：