Jerome White

Designing a voice-based employment exchange for rural India

We present observations from various user studies that have helped to guide the design and deployment of a voice-based employment platform. Specifically, we present findings as a function of demographics, considering employers and candidates across two regions of Karnataka. Our results are of use to those building interfaces to address rural unemployment in particular, and those looking to understand the employment landscape of rural India in general. Our main contributions are motivating the need for such a platform in this context, and offering insight into the engineering of job matches.

Before-Commit Client State Management Services for AJAX Applications

Heavily script-based browser applications change the manner in which users interact with Web browsers. Instead of downloading a succession of HTML pages, users download a single application and use that application for a long period of time. The application is not a set of HTML pages, but rather a single page that can possible modify its own presentation based on data exchanged with a server. In such an environment, it is necessary to provide some means for the client to manage its own state. We describe the initial results of our work in providing client-side state management services for these script-based applications. We focus on browser-based services that can help the user before any data is committed on the server. Our services include state checkpointing, property binding, operation logging, operational replay, ATOM/RSS data updates, and application-controlled persistence.

Using Zero-Resource Spoken Term Discovery for Ranked Retrieval.

Research on ranked retrieval of spoken content has assumed the existence of some automated (word or phonetic) transcription. Recently, however, methods have been demonstrated for matching spoken terms to spoken content without the need for language-tuned transcription. This paper describes the first application of such techniques to ranked retrieval, evaluated using a newly created test collection. Both the queries and the collection to be searched are based on Gujarati produced naturally by native speakers; relevance assessment was performed by other native speakers of Gujarati. Ranked retrieval is based on fast acoustic matching that identifies a deeply nested set of matching speech regions, coupled with ways of combining evidence from those matching regions. Results indicate that the resulting ranked lists may be useful for some practical similarity-based ranking tasks.

The FIRE 2013 Question Answering for the Spoken Web Task

The FIRE 2013 Question Answering for the Spoken Web (QASW) task was an information retrieval evaluation in which the goal was to match spoken Gujarati questions to spoken Gujarati answers. This paper describes the design of the task, the development of the test collection, the runs that were submitted, and the corresponding results.

Live data views: programming pervasive applications that use "timely" and "dynamic" data

In the absence of generic programming abstractions for dynamic data in most enterprise programming environments, individual applications treat data streams as a special case requiring custom programming. With the growing number of live data sources such as RSS feeds, messaging and presence servers, multimedia streams, and sensor data. a general-purpose client-server programming model is needed to easily incorporate live data into applications. In this paper, we present Live Data Views, a programming abstraction that represents live data as a time-windowed view over a set of data streams. Live Data Views allow applications to create and retrieve stateful abstractions of dynamic data sources in a uniform manner, via the application of intra- and inter- stream operators. We provide details of our model and evaluate a proof-of-concept Live Data Views implementation to monitor traffic conditions on a highway. We also provide the preliminary design of a J2EE-based implementation, and outline some of the research challenges raised by this abstraction in a distributed computing environment.

Speech-interface prompt design: lessons from the field

Designers of IVR systems often shy away from using speech prompts; preferring, where they can, to use keypad input. Part of the reason is that speech processing is expensive and often error prone. This work attempts to address this problem by offering guidelines for prompt design based on field experiments. It is shown, specifically, that accuracy can be influenced by prompt examples, depending on the nature of the information requested.

Simulating Zero-Resource Spoken Term Discovery

If search engines are ever to index all of the spoken content in the world, they will need to handle hundreds of languages for which no automatic speech recognition systems exist. Zero-resource spoken term discovery, in which repeated content is detected in some acoustic representation, offers a potentially useful source of indexing features. This paper describes a text-based simulation of a zero-resource spoken term discovery system that allows any information retrieval test collection to be used as a basis for early development of information retrieval techniques. It is proposed that these techniques can be later applied to actual zero-resource spoken term discovery results.

Vapor Engine: Demonstrating an Early Prototype of a Language-Independent Search Engine for Speech

Typical search engines for spoken content begin with some form of language-specific audio processing such as phonetic word recognition. Many languages, however, lack the language tuned preprocessing tools that are needed to create indexing terms for speech. One approach in such cases is to rely on repetition, detected using acoustic features, to find terms that might be worth indexing. Experiments have shown that this approach yields term sets that might be sufficient for some applications in both spoken term detection and ranked retrieval experiments. Such approaches currently work only with spoken queries, however, and only when the searcher is able to speak in a manner similar to that of the speakers in the collection. This demonstration paper proposes Vapor Engine, a new tool for selectively transcribing repeated terms that can be automatically detected from spoken content in any language. These transcribed terms could then be matched to queries formulated using written terms. Vapor Engine is early in development: it currently supports only single-term queries and has not yet having been formally evaluated. This paper introduces the interface and summarizes the challenges it seeks to address.

A Test Collection for Spoken Gujarati Queries

The development of a new test collection is described in which the task is to search naturally occurring spoken content using naturally occurring spoken queries. To support research on speech retrieval for low-resource settings, the collection includes terms learned by zero-resource term discovery techniques. Use of a new tool designed for exploration of spoken collections provides some additional insight into characteristics of the collection.

An Un-tethered Mobile Shopping Experience

Smart phones with access to apps from online stores are ideal candidates to replace expensive hardware like Point-of-Sale terminals for retail. A standard set of shopper and retailer apps can replace the conventional retailer IT setup in settings ranging from rural areas with low connectivity to dense urban areas. We describe how we built such a set of apps for mobile shoppers and retailers equipped only with smart phones and tablets, and who require little to no training to use them. These apps are flexible enough to be used by small shops with small inventories as well as large grocery chains. Our apps enable retailers to manage their inventories and finances, and shoppers to discover retailers, match shopping lists, and make purchases. We describe how we conducted a user study of retailers in North India to ascertain their needs, and to understand the ecosystem in emerging markets. This helped us build a mobile shopping platform that can support a range of transactional scenarios.