ABSTRACT
We focus on the problem of answering OLAP queries via voice output. We present a holistic approach that combines query processing and result vocalization. We use the following key ideas to minimize processing overheads and maximize answer quality. First, our approach samples from the database to evaluate alternative speech fragments. OLAP queries are not fully evaluated. Instead, sampling focuses on result aspects that are relevant for voice output. To guide sampling, we rely on methods from the area of Monte-Carlo Tree Search. Second, we use pipelining to interleave query processing and voice output. The system starts providing the user with high-level insights while generating more fine-grained results in the background. Third, we optimize speech output to maximize the user's information gain under speaking time constraints. We use a maximum-entropy model to predict the user's belief about OLAP results, after listening to voice output. Based on that model, we select the most informative speech fragments (i.e., the ones minimizing the distance between user belief and actual data). We analyze formal properties of the proposed speech structure and analyze complexity of our algorithm. Also, we compare alternative vocalization approaches in an extensive user study.
- CB Browne and Edward Powley. 2012. A survey of monte carlo tree search methods . Trans. on Computational Intelligence and AI in Games, Vol. 4, 1 (2012), 1--49. http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6145622Google ScholarCross Ref
- Dharmil Chandarana, Vraj Shah, Arun Kumar, and Lawrence Saul. 2017. SpeakQL: towards speech-driven multi-modal querying. In HILDA. 1--6.Google Scholar
- Yu Feng and Shan Wang. 2002. Compressed data cube for approximate OLAP query processing . Journal of Computer Science and Technology, Vol. 17, 5 (2002), 625--635.Google ScholarDigital Library
- Sylvain Gelly, L Kocsis, and Marc Schoenauer. 2012. The grand challenge of computer go: monte carlo tree search and extensions . Commun. ACM, Vol. 3 (2012), 106--113. http://dl.acm.org/citation.cfm?id=2093574 Google ScholarDigital Library
- Google. {n. d.}. Google Assistant SDK . https://developers.google.com/assistant/sdk/overview.Google Scholar
- Silviu Guiasu and Abe Shenitzer. 1985. The principle of maximum entropy . The Mathematical Intelligencer, Vol. 7, 1 (1985), 42--48.Google ScholarCross Ref
- Thomas Hermann, Andy Hunt, and John G Neuhoff. 2011. The Sonification Handbook. 301--324 pages. arxiv: arXiv:1011.1669v3Google Scholar
- Ruoming Jin, Leo Glimcher, Chris Jermaine, and Gagan Agrawal. 2006. New sampling-based estimators for OLAP queries . In ICDE. 18. Google ScholarDigital Library
- Manas Joglekar, Hector Garcia-molina, and Aditya Parameswaran. 2015. Smart drill down . VLDBJ, Vol. 8, 12 (2015), 1928--1931. arxiv: arXiv:1412.0364v1Google ScholarDigital Library
- Shantanu Joshi and Christopher Jermaine. 2008. Materialized sample views for database approximation . ICDE, Vol. 20, 3 (2008), 337--351. Google ScholarDigital Library
- Uwe Jugel, Zbigniew Jerzak, and Gregor Hackenbroich. 2014. M4 : A Visualization-Oriented Time Series Data Aggregation . VLDB, Vol. 7, 10 (2014), 797--808. Google ScholarDigital Library
- Niranjan Kamat and Arnab Nandi. 2017. InfiniViz: Interactive Visual Exploration using Progressive Bin Refinement . arXiv preprint arXiv:1710.01854 (2017). arxiv: 1710.01854 http://arxiv.org/abs/1710.01854Google Scholar
- Albert Kim, Eric Blais, Aditya Parameswaran, Piotr Indyk, Sam Madden, and Ronitt Rubinfeld. 2015. Rapid sampling for visualizations with ordering guarantees . VLDB, Vol. 8, 5 (2015), 521--532. arxiv: 1412.3040 Google ScholarDigital Library
- Levente Kocsis and C Szepesvá ri. 2006. Bandit based monte-carlo planning. In European Conf. on Machine Learning . 282--293. http://www.springerlink.com/index/D232253353517276.pdf Google ScholarDigital Library
- Xiaolei Li, Jiawei Han, Zhijun Yin, Jae-Gil Lee, and Yizhou Sun. 2008. Sampling cube: a framework for statistical olap over sampling data. In SIGMOD . 779--790. Google ScholarDigital Library
- Zhicheng Liu and Jeffrey Heer. 2014. The effects of interactive latency on exploratory visual analysis . IEEE Transactions on Visualization & Computer Graphics, Vol. 20, 12 (2014), 2122--2131.Google ScholarCross Ref
- Gabriel Lyons, Vinh Tran, Carsten Binnig, Ugur Cetintemel, and Tim Kraska. 2016. Making the case for Query-by-Voice with EchoQuery. In SIGMOD . 2129--2132. Google ScholarDigital Library
- Patrick Marcel, Place Jean Jaurè s, and Stefano Rizzi. 2012. Towards intensional answers to OLAP queries for analytical sessions. In DOLAP . 49--56. Google ScholarDigital Library
- Robert B. Miller. 1968. Response time in man-computer conversational transactions. In AFIPS . 267--277. Google ScholarDigital Library
- Navneet Potti and Jignesh M. Patel. 2015. DAQ: A new paradigm for approximate query processing . VLDB, Vol. 8, 9 (2015), 898--909. Google ScholarDigital Library
- Rameshsharma Ramloll, Wai Yu, and Beate Riedel. 2001. Using non-speech sounds to improve access to 2D tabular numerical information for visually impaired users. In Conference of the British HCI Group . 515--529. http://eprints.gla.ac.uk/3223/Google ScholarCross Ref
- S. Sarawagi. 2000. User-adaptive exploration of multidimensional data. In VLDB. 307--316. http://citeseer.ist.psu.edu/sarawagi00useradaptive.htmlGoogle Scholar
- Ben Shneiderman. 1984. Response time and display rate in human performance with computers . Comput. Surveys, Vol. 16, 3 (1984), 265--285. Google ScholarDigital Library
- Immanuel Trummer, Mark Bryan, and Ramya Narasimha. 2018. Vocalizing large time series efficiently. In VLDB. 1--12. Google ScholarDigital Library
- Immanuel Trummer, Jiancheng Zhu, and Mark Bryan. 2017. Data vocalization: optimizing voice output of relational data . VLDB, Vol. 10, 11 (2017), 1574--1585. Google ScholarDigital Library
Index Terms
- A Holistic Approach for Query Evaluation andResult Vocalization in Voice-Based OLAP
Recommendations
A segment-based approach to voice conversion
ICASSP '91: Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International ConferenceA voice conversion algorithm that uses speech segments as conversion units is proposed. Input speech is decomposed into speech segments by a speech recognition module, and the segments are replaced by speech segments uttered by another speaker. This ...
Feature-based recommendation framework on OLAP
ADC '12: Proceedings of the Twenty-Third Australasian Database Conference - Volume 124The queries in Online Analytical Processing (OLAP) are user-guided. OLAP is based on a multidimensional data model for complex analytical and ad-hoc queries with a rapid execution time. Those queries are either routed or on-demand revolved around the ...
Voice conversion by mapping the speaker-specific features using pitch synchronous approach
The basic goal of the voice conversion system is to modify the speaker-specific characteristics, keeping the message and the environmental information contained in the speech signal intact. Speaker characteristics reflect in speech at different levels, ...
Comments