Diarization partitions an audio stream into segments based on the voices of the speakers. Real-time diarization systems that include an enrollment step should limit enrollment training samples to reduce user interaction time. Although training on a small number of samples yields poor performance, we show that the accuracy can be improved dramatically using a chronological self-training approach. We studied the tradeoff between training time and classification performance and found that 1 second is sufficient to reach over 95% accuracy. We evaluated on 700 audio conversation files of about 10 minutes each from 6 different languages and demonstrated average diarization error rates as low as 10%.

Disfluency detection models now approach high accuracy on English text. However, little exploration has been done in improving the size and inference time of the model. At the same time, automatic speech recognition (ASR) models are moving from server-side inference to local, on-device inference. Supporting models in the transcription pipeline (like disfluency detection) must follow suit. In this work we concentrate on the disfluency detection task, focusing on small, fast, on-device models based on the BERT architecture. We demonstrate it is possible to train disfluency detection models as small as 1.3 MiB, while retaining high performance. We build on previous work that showed the benefit of data augmentation approaches such as self-training. Then, we evaluate the effect of domain mismatch between conversational and written text on model performance. We find that domain adaptation and data augmentation strategies have a more pronounced effect on these smaller models, as compared to conventional BERT models.

Translation apps and devices are often presented in the context of providing assistance while traveling abroad. However, the spectrum of needs for cross-language communication is much wider. To investigate these needs, we conducted three studies with populations spanning socioeconomic status and geographic regions: (1) United States-based travelers, (2) migrant workers in India, and (3) immigrant populations in the United States. We compare frequent travelers' perception and actual translation needs with those of the two migrant communities. The latter two, with low language proficiency, have the greatest translation needs to navigate their daily lives. However, current mobile translation apps do not meet these needs. Our findings provide new insights on the usage practices and limitations of mobile translation tools. Finally, we propose design implications to help apps better serve these unmet needs.

Mobile devices offer people the opportunity to get useful tasks done during time previously thought to be unusable. Because mobile devices have small screens and are often used in divided attention scenarios, people are limited to using them for short, simple tasks; complex tasks like editing a document present significant challenges in this environment. In this paper we demonstrate how a complex task requiring focused attention can be adapted to the fragmented way people work while mobile by decomposing the task into smaller, simpler microtasks. We introduce Play Write, a microproductivity tool that allows people to edit Word documents from their phones via such microtasks. When participants used Play Write while simultaneously watching a video, we found that they strongly preferred its microtask-based editing approach to the traditional editing experience offered by Mobile Word. Play Write made participants feel more productive and less stressed, and they completed more edits with it. Our findings suggest microproductivity tools like Play Write can help people be productive in divided attention scenarios.

Email continues to be an important form of communication as well as a way to manage tasks and archive personal information. As the volume of email grows, organizing and finding relevant email remains challenging. In this paper, we present a large-scale log analysis of the activities that people perform on email mes-sages (accessing external information via links or attachments, responding to messages, and organizing messages), their search behavior, and their organizational practices in a popular web email client.

As the number of email users and messages continues to grow, search is becoming more important for finding information in personal archives. In spite of its importance, email search is much less studied than web search, particularly using large-scale behavioral log analysis. In this paper we report the results of a large-scale log analysis of email search and complement this with a survey to better understand email search intent and success. We characterize email search behaviors and highlight differences from web search. When searching for email, people know many attributes about what they are looking for; they often look for specific known items; their queries are shorter and they click on fewer items than in web search. Although repeat queries are common in both email and web search, repeat visits to the same search result are much less common in email search suggesting that the same query is used for different search intents over time. We consider search intent from multiple angles. In email search logs, we find that people use email search not just to find information but also to perform tasks such as cleanup or organization, and that the distribution of actions they perform depends on the type of query. In our survey, people reported that they looked for specific information in both email search and web search, but they were much less likely to search for general information on a topic in email. The differences in overall behavior, re-finding patterns and search intents we observed between email and web search have important implications for the design of email search algorithms and interfaces.

Understanding how users examine result pages across a broad range of information needs is critical for search engine design. Cursor movements can be used to estimate visual attention on search engine results page (SERP) components, including traditional snippets, aggregated results, and advertisements. However, these signals can only be leveraged for SERPs where cursor tracking was enabled, limiting their utility for informing the design of new SERPs. In this work, we develop robust, log-based mouse movement models capable of estimating searcher attention on novel SERP arrangements. These models can help improve SERP design by anticipating searchers' engagement patterns given a proposed arrangement. We demonstrate the efficacy of our method using a large set of mouse-tracking data collected from two independent commercial search engines.

Web search engines now offer more than ranked results. Queries on topics like weather, definitions, and movies may return inline results called answers that can resolve a searcher's information need without any additional interaction. Despite the usefulness of answers, they are limited to popular needs because each answer type is manually authored. To extend the reach of answers to thousands of new information needs, we introduce Tail Answers: a large collection of direct answers that are unpopular individually, but together address a large proportion of search traffic. These answers cover long-tail needs such as the average body temperature for a dog, substitutes for molasses, and the keyboard shortcut for a right-click. We introduce a combination of search log mining and paid crowdsourcing techniques to create Tail Answers. A user study with 361 participants suggests that Tail Answers significantly improved users' subjective ratings of search quality and their ability to solve needs without clicking through to a result. Our findings suggest that search engines can be extended to directly respond to a large new class of queries.

Smartphone use in presentations is often seen as distracting to the audience and speaker. However, phones can encourage people participate more fully in what is going on around them and build stronger ties with their companions. In this paper, we describe a smartphone interface designed to help audience members engage fully in a presentation by providing real time mobile feedback. This feedback is then aggregated and reflected back to the group via a projected visualization, with notifications provided to the presenter and the audience on interesting feedback events. We deployed this system in a large enterprise meeting, and collected information about the attendees' experiences with it via surveys and interaction logs. Participants report that providing mobile feedback was convenient, helped them pay close attention to the presentation, and enabled them to feel connected with other audience members.

Identifying content for which a user may search has a variety of applications, including ranking and recommendation. In this poster, we examine how pre-search context can be used to predict content that the user will seek before they have even specified a search query. We call this anticipatory search. Using a log-based approach, we compare different methods for predicting the content to be searched using different attributes of the pre-query context and behavioral signals from previous visitors to the most recent browse URL. Each method covers different cases and shows promise for query-free anticipatory search on the Web.

This paper presents an algorithm that predicts with very high accuracy which Web search result a user will click for one sixth of all Web queries. Prediction is done via a straightforward form of personalization that takes advantage of the fact that people often use search engines to re-find previously viewed resources. In our approach, an individual's past navigational behavior is identified via query log analysis and used to forecast identical future navigational behavior by the same individual. We compare the potential value of personal navigation with general navigation identified using aggregate user behavior. Although consistent navigational behavior across users can be useful for identifying a subset of navigational queries, different people often use the same queries to navigate to different resources. This is true even for queries comprised of unambiguous company names or URLs and typically thought of as navigational. We build an understanding of what personal navigation looks like, and identify ways to improve its coverage and accuracy by taking advantage of people's consistency over time and across groups of individuals.

The Web is constantly changing, but most tools used to access Web content deal only with what can be captured at a single instance in time. As a result, Web users may not have a good understanding of the changes that occur. In this paper we show that making Web content change explicitly visible allows people to interact with the Web in new ways. We present a longitudinal study in which 30 people used a Web browser plug-in that caches visited pages and highlights text changes to those pages when revisited. We used a survey to capture their understanding of Web page change and their own revisitation patterns at the beginning of use and after one month. For a majority of the participants, we also logged their Web page visits and associated content change. Exposing change is more valuable to our participants than initially expected, making them aware of how dynamic content they visit is and changing their interactions with it.

The Web is a dynamic information environment. Web content changes regularly and people revisit Web pages frequently. But the tools used to access the Web, including browsers and search engines, do little to explicitly support these dynamics. In this paper we present DiffIE, a browser plug-in that makes content change explicit in a simple and lightweight manner. DiffIE caches the pages a person visits and highlights how those pages have changed when the person returns to them. We describe how we built a stable, reliable, and usable system, including how we created compact, privacy-preserving page representations to support fast difference detection. Via a longitudinal user study, we explore how DiffIE changed the way people dealt with changing content. We find that much of its benefit came not from exposing expected change, but rather from drawing attention to unexpected change and helping people build a richer understanding of the Web content they frequent.

We describe results from Web search log studies aimed at elucidating user behaviors associated with queries and destination URLs that appear with different frequencies. We note the diversity of information goals that searchers have and the differing ways that goals are specified. We examine rare and common information goals that are specified using rare or common queries. We identify several significant differences in user behavior depending on the rarity of the query and the destination URL. We find that searchers are more likely to be successful when the frequencies of the query and destination URL are similar. We also establish that the behavioral differences observed for queries and goals of varying rarity persist even after accounting for potential confounding variables, including query length, search engine ranking, session duration, and task difficulty. Finally, using an information-theoretic measure of search difficulty, we show that the benefits obtained by search and navigation actions depend on the frequency of the information goal.

In most previous work on personalized search algorithms, the results for all queries are personalized in the same manner. However, as we show in this paper, there is a lot of variation across queries in the benefits that can be achieved through personalization. For some queries, everyone who issues the query is looking for the same thing. For other queries, different people want very different results even though they express their need in the same way. We examine variability in user intent using both explicit relevance judgments and large-scale log analysis of user behavior patterns. While variation in user behavior is correlated with variation in explicit relevance judgments the same query, there are many other factors, such as result entropy, result quality, and task that can also affect the variation in behavior. We characterize queries using a variety of features of the query, the results returned for the query, and people's interaction history with the query. Using these features we build predictive models to identify queries that can benefit from personalization.