Corpus ID: 18352125

Say what? why users choose to speak their web queries

@inproceedings{Kamvar2010SayWW,
  title={Say what? why users choose to speak their web queries},
  author={Maryam Kamvar and Doug Beeferman},
  booktitle={INTERSPEECH},
  year={2010}
}
The context in which a speech-driven application is used (or conversely not used) can be an important signal for recognition engines, and for spoken interface design. Using large-scale logs from a widely deployed spoken system, we analyze on an aggregate level factors that are correlated with a decision to speak a web search query rather than type it. We find the factors most predictive of spoken queries are whether a query is made from an unconventional keyboard, for a search topic relating to… Expand

Figures, Tables, and Topics from this paper

Speak to Me: Interacting with a Spoken Language Interface
TLDR
Examination of the interaction between users and a spoken language interface through a user-centered Wizard of Oz experiment showed that using the spoken interface resulted in significantly less interaction measured by the number of iterations, number of viewed webpages, and number of clicks/touches, than using the baseline interface. Expand
Mobile query reformulations
TLDR
The results suggest that users do not tend to switch between different input types (e.g. voice and text), and voice to text switches are largely caused by speech recognition errors, and text to voice switches are unlikely to be about the same intent. Expand
How Many Multiword Expressions do People Know?
TLDR
This article will use the question of how many words do people know, as an excuse for surveying how such issues are addressed in a variety of fields: computer science, Web search, linguistics, lexicography, educational testing, psychology, statistics, and so on. Expand
Examining users' partial query modification patterns in voice search
TLDR
This article examines if users would prefer partial query modification and how they perform it in voice search and results indicated that when given the opportunity, the users performed more partial query modifications than complete queries. Expand
Mobile Voice Query Reformulation by Visually Impaired People
TLDR
This study will compare the mobile query reformulation patterns of visually impaired and sighted people using a voice user interface to explore the differences between these two groups in terms of their interactions patterns and the potential effects of voice query reformulations on task completion. Expand
Effective automatic speech recognition data collection for under-resourced languages
TLDR
The development of a tool for effectively collecting ASR data for under-resourced languages, called Woefzela, is documents, from the determination of the requirements necessary for effective data collection in this context, to the verification and validation of its functionality. Expand
MWEs and Topic Modelling: Enhancing Machine Learning with Linguistics
TLDR
This talk will discuss recent work on consolidating the micro-level document representation with multiword expressions, and present experimental results which demonstrate that linguistically-richer document representations enhance topic modelling. Expand
Study of Web search patterns in mobile devices
In the last couple of decades, the Web has become a major source of information. With the rising number of people navigating on the Web, the number of information documents also increased. Therefore,Expand
LSpeakIt : Immersive interface for 3D object Search
The number of available three-dimensional digital objects has been increasing considerably. As a result, retrieving such objects from large collections has been subject of research. However, proposedExpand
How context determines perceived quality and modality choice. Secondary task paradigm applied to the evaluation of multimodal interfaces
TLDR
The relation between input modality, workload and perceived quality of a multimodal mobile application and the results are largely in line with the above reported assumptions. Expand
...
1
2
...

References

SHOWING 1-10 OF 11 REFERENCES
Leveraging multiple query logs to improve language models for spoken query recognition
TLDR
This work presents the use of multiple data sources, with the focus on query logs, in improving ASR language models for a voice search application, and shows that by leveraging these resources, one can achieve recognition performance comparable to, or even better than, that of a previously deploy system. Expand
Query log analysis: social and technological challenges
TLDR
This paper reports on a workshop held at the WWW 2007 Conference to foster dialogue on the social and technical challenges that are posed by the content of query logs and the analysis of that content. Expand
Live search for mobile:Web services by voice on the cellphone
TLDR
A speech-recognition interface which was recently developed for live search for mobile, which allows the users to interact by voice, and initial performance results indicating that for sentence level utterance recognition the authors achieve 60 to 65% of human capability. Expand
Architecture, User Interface, and Enabling Technology in Windows Vista's Speech Systems
TLDR
Some of the challenges encountered in providing a speech-based interface to a system as complex and extensible as the modern desktop PC are outlined, as well as the technology developments that have made this possible. Expand
Computers and iphones and mobile phones, oh my!: a logs-based comparison of search users on different devices
TLDR
It is suggested that for the higher-end phones, a close integration with the standard computer-based interface would be beneficial for the user, since these phones seem to be treated as an extension of the users' computer. Expand
A large scale study of wireless search behavior: Google mobile search
TLDR
The goal is to understand the current state of wireless search by analyzing over 1 Million hits to Google's mobile search sites, which includes the examination of search queries and the general categories under which they fall. Expand
The magical number seven plus or minus two: some limits on our capacity for processing information.
TLDR
The theory provides us with a yardstick for calibrating the authors' stimulus materials and for measuring the performance of their subjects, and the concepts and measures provided by the theory provide a quantitative way of getting at some of these questions. Expand
A Study of Mobile Search Queries in Japan
TLDR
The characteristics of search queries on mobile phones in Japan are studied, comparing them with previous results of generic search queries in Japan and mobileSearch queries in the USA to find some interesting differences. Expand
Speaking: From Intention to Articulation
In Speaking, Willem "Pim" Levelt, Director of the Max-Planck-Institut fur Psycholinguistik, accomplishes the formidable task of covering the entire process of speech production, from constraints onExpand
Deciphering Trends in Mobile Search
TLDR
An analysis of search data from a large US carrier showed that cell-phone subscribers are typing longer queries in less time and clicking on more results. Expand
...
1
2
...