Maryam Kamvar
Authored Publications
Sort By
Preview abstract
In this paper, we investigate how to optimize the vocabulary for a voice search language model. The metric we optimize over is the out-of-vocabulary (OoV) rate since it is a strong indicator of user experience. In a departure from the usual way of measuring OoV rates, web search logs allow us to compute the per-session OoV rate and thus estimate the percentage of users that experience a given OoV rate. Under very conservative text normalization, we find that a voice search vocabulary consisting of 2 to 2.5M words extracted from 1 week of search query data will result in an aggregate OoV rate of 0.01; at that size, the same OoV rate will also be experienced by 90% of users. The number of words included in the vocabulary is a stable indicator of the OoV rate. Altering the freshness of the vocabulary or the duration of the time window over which the training data is gathered does not significantly change the OoV rate. Surprisingly, a significantly larger vocabulary (approx. 10 million words) is required to guarantee OoV rates below 0.01 (1%) for 95% of the users.
View details
Preview abstract
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 a users' location, or for a search topic that can be answered in a “hands-free” fashion. We also find, contrary to our intuition, that longer queries have a higher probability of being typed than shorter queries.
View details
Google Search by Voice: A Case Study
Preview
Johan Schalkwyk
Doug Beeferman
Mike Cohen
Brian Strope
Advances in Speech Recognition: Mobile Environments, Call Centers and Clinics, Springer (2010), pp. 61-90
Preview abstract
We present a logs-based comparison of search patterns across three platforms: computers, iPhones and conventional mobile phones. Our goal is to understand how mobile search users differ from computer-based search users, and we focus heavily on the distribution and variability of tasks that users perform from each platform. The results suggest that search usage is much more focused for the average mobile user than for the average computer-based user. However, search behavior on high-end phones resembles computer-based search behavior more so than mobile search behavior. A wide variety of implications follow from these findings. First, there is no single search interface which is suitable for all mobile phones. We suggest that for the higher-end phones, a close integration with the standard computer-based interface (in terms of personalization and available feature set) would be beneficial for the user, since these
phones seem to be treated as an extension of the users' computer. For all other phones, there is a huge opportunity for personalizing the search experience for the user's "mobile needs", as these users are likely to repeatedly search for a single type of information need on their phone.
View details
Preview abstract
We present a new CAPTCHA which is based on identifying an
image's upright orientation. This task requires analysis of the often complex contents of an image, a task which humans usually perform well and machines generally do not. Given a large repository of images, such as those from a web search result, we use a suite of automated orientation detectors to prune those images that can be automatically set upright easily. We then apply a social feedback mechanism to verify that the remaining images have a human-recognizable upright orientation. The main advantages of our CAPTCHA technique over the traditional text recognition techniques are that it is language-independent, does not require text-entry (e.g. for a mobile device), and employs another domain for CAPTCHA generation beyond character obfuscation. This CAPTCHA lends itself to rapid implementation and has an almost limitless supply of images. We conducted extensive experiments to measure the viability of this technique.
View details
Query Suggestions for Mobile Search: Understanding Usage Patterns
Preview
Proceedings of the SIGCHI conference on Human Factors in computing systems (CHI) (2008)
The Role of Context in Query Input: Using contexual signals to complete queries on mobile devices
Preview
Human Computer Interaction with Mobile Devices and Services (Mobile HCI) (2007)
A Large Scale Study of Wireless Search Behavior: Google Mobile Search
Preview
Proceedings of the SIGCHI conference on Human Factors in computing systems (CHI) (2006)
