Large Language Models (LLMs) are typically evaluated through general or domain-specific benchmarks testing capabilities that often lack grounding in the lived realities of end users. Critical domains such as healthcare require evaluations that extend beyond artificial or simulated tasks to reflect the everyday needs, cultural practices, and nuanced contexts of communities. We propose Samiksha, a community-driven evaluation pipeline co-created with civil-society organizations (CSOs) and community members. Our approach enables scalable, automated benchmarking through a culturally aware, community-driven pipeline in which community feedback informs what to evaluate, how the benchmark is built, and how outputs are scored. We demonstrate this approach in the health domain in India. Our analysis highlights how current multilingual LLMs address nuanced community health queries, while also offering a scalable pathway for contextually grounded and inclusive LLM evaluation.

Large language models (LLMs) have revolutionized various domains but still struggle with non-Latin scripts and low-resource languages. This paper addresses the critical challenge of improving multilingual performance without extensive fine-tuning. We introduce a novel dynamic learning approach that optimizes prompt strategy, embedding model, and LLM per query at runtime. By adapting configurations dynamically, our method achieves significant improvements over static, best and random baselines. It operates efficiently in both offline and online settings, generalizing seamlessly across new languages and datasets. Leveraging Retrieval-Augmented Generation (RAG) with state-of-the-art multilingual embeddings, we achieve superior task performance across diverse linguistic contexts. Through systematic investigation and evaluation across18 diverse languages using popular question-answering (QA) datasets we show our approach results in 10-15% improvements in multilingual performance over pre-trained models and 4x gains compared to fine-tuned, language-specific models.

Large Language Models (LLMs) and Text-To-Image (T2I) models have demonstrated the ability to generate compelling text and visual stories. However, their outputs predominantly reflect the sensibilities of Western ideologies, often resulting in an outsider’s gaze on other cultures. As a result, non-Western communities have to put extra effort into generating culturally specific stories. To address this challenge, we developed a visual storytelling tool called Kahani that generates culturally grounded visual stories for non-Western cultures. Our tool leverages off-the-shelf models GPT-4 Turbo and Stable Diffusion XL (SDXL). By using Chain of Thought (CoT) and T2I prompting techniques, we capture the cultural context from user’s prompt and generate vivid descriptions of the characters and scene compositions. To evaluate the effectiveness of Kahani, we conducted a comparative user study with ChatGPT-4 (with DALL-E3) in which participants from different regions of India compared the cultural relevance of stories generated by the two tools. The results of the qualitative and quantitative analysis performed in the user study show that Kahani’s visual stories are more culturally nuanced than those generated by ChatGPT-4. In 27 out of 36 comparisons, Kahani outperformed or was on par with ChatGPT-4, effectively capturing cultural nuances and incorporating more Culturally Specific Items (CSI), validating its ability to generate culturally grounded visual stories.

Marine Carpuat, Omri Asscher, Kalika Bali, Luisa Bentivogli, Fred Blain, Lynne Bowker, Monojit Choudhury, Hal Daumé Iii, Kevin Duh, Ge Gao, Alvin C Grissom II, Marzena Karpinska, Elaine C Khoong, William D. Lewis, Andre Martins, Mary Nurminen, Douglas W. Oard, Maja Popovic, Michel Simard, François Yvon. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Varun Gumma, Pranjal A Chitale, Kalika Bali. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

People with disabilities experience high levels of social discrimination worldwide. But, these harms are more pronounced in the Global South due to the intense stigma around disability and its intersections with structural embeddings of patriarchy. The massive growth of social media in the Global South provides people with disabilities a unique opportunity to advocate for disability rights and challenge regressive ableist norms. Yet, little is known about the challenges they face in doing their advocacy work on social media. Through interviews with 20 disability advocates in India with diverse gender identities and abilities, we found that disability advocates routinely face ableist hate and harassment, patronizing and invalidating comments, and lack of visibility and support, which forces them to self-censor as a form of self-protection, leading to low advocacy outcomes. We draw on these findings to illuminate the role of social media in the invisibilization of people with disabilities in the online sphere.

A steady increase in the performance of Massively Multilingual Models (MMLMs) has contributed to their rapidly increasing use in data collection pipelines. Interactive Neural Machine Translation (INMT) systems are one class of tools that can utilize MMLMs to promote such data collection in several under-resourced languages. However, these tools are often not adapted to the deployment constraints that native language speakers operate in, as bloated, online inference-oriented MMLMs trained for data-rich languages, drive them. INMT-Lite addresses these challenges through its support of (1) three different modes of Internet-independent deployment and (2) a suite of four assistive interfaces suitable for (3) data-sparse languages. We perform an extensive user study for INMT-Lite with an under-resourced language community, Gondi, to find that INMT-Lite improves the data generation experience of community members along multiple axes, such as cognitive load, task productivity, and interface interaction time and effort, without compromising on the quality of the generated translations.INMT-Lite’s code is open-sourced to further research in this domain.

Generative models are increasingly being used in various applications, such as text generation, commonsense reasoning, and question-answering. To be effective globally, these models must be aware of and account for local socio-cultural contexts, making it necessary to have benchmarks to evaluate the models for their cultural familiarity. Since the training data for LLMs is web-based and the Web is limited in its representation of information, it does not capture knowledge present within communities that are not on the Web. Thus, these models exacerbate the inequities, semantic misalignment, and stereotypes from the Web. There has been a growing call for community-centered participatory research methods in NLP. In this work, we respond to this call by using participatory research methods to introduce DOSA, the first community-generated Dataset of 615 Social Artifacts, by engaging with 260 participants from 19 different Indian geographic subcultures. We use a gamified framework that relies on collective sensemaking to collect the names and descriptions of these artifacts such that the descriptions semantically align with the shared sensibilities of the individuals from those cultures. Next, we benchmark four popular LLMs and find that they show significant variation across regional sub-cultures in their ability to infer the artifacts.

Sagnik Mukherjee, Muhammad Farid Adilazuarda, Sunayana Sitaram, Kalika Bali, Alham Fikri Aji, Monojit Choudhury. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Sanchit Ahuja, Divyanshu Aggarwal, Varun Gumma, Ishaan Watts, Ashutosh Sathe, Millicent Ochieng, Rishav Hada, Prachi Jain, Mohamed Ahmed, Kalika Bali, Sunayana Sitaram. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Social media platforms have witnessed an unprecedented growth in users from rural communities in India. Many of these users are new to online information environments and are highly susceptible to misinformation. Fact-checking has the potential to reduce the proliferation and impact of misinformation; however, little is known about how fact-checking organizations in India serve rural users. To fill this gap, we conducted interviews with 12 prominent fact-checking organizations in India to understand their current practices and challenges in providing their services to rural users and the associated human and technological infrastructure they use. We discovered several measures that fact-checking organizations take to increase the reach, awareness, and relevance of fact-checked content for rural users, such as engaging with stringer networks and utilizing vernacular languages. However, fact-checking organizations also face severe challenges that limit both the scale of their work and engagement from rural users. Drawing on these findings, we provide design and policy recommendations to improve the reach, awareness, and relevance of fact-checked content for social media users in rural areas.

Kabir Ahuja, Harshita Diddee, Rishav Hada, Millicent Ochieng, Krithika Ramesh, Prachi Jain, Akshay Nambi, Tanuja Ganu, Sameer Segal, Mohamed Ahmed, Kalika Bali, Sunayana Sitaram. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

This paper contains statements that may be offensive or upsetting.

Pre-trained multilingual language models are gaining popularity due to their cross-lingual zero-shot transfer ability, but these models do not perform equally well in all languages. Evaluating task-specific performance of a model in a large number of languages is often a challenge due to lack of labeled data, as is targeting improvements in low performing languages through few-shot learning. We present a tool - LITMUS Predictor - that can make reliable performance projections for a fine-tuned task-specific model in a set of languages without test and training data, and help strategize data labeling efforts to optimize performance and fairness objectives.

Women’s economic empowerment is central to gender equality. However, work opportunities available to low-income women in patriarchal societies are infrequent. While crowd work has the potential to increase labor participation of such women, much remains unknown about their engagement with crowd work and the resultant opportunities and tensions. To fill this gap, we critically examined the adoption and use of a crowd work platform by low-income women in India. Through a qualitative study, we found that women faced tremendous challenges, for example, in seeking permission from family members to do crowd work, lack of family support and encouragement, and often working in unfavorable environments where they had to hide their work lives. While crowd work took a toll on their physical and emotional wellbeing, it also led to increased confidence, agency, and autonomy. We discuss ways to reduce frictions and tensions in participation of low-income women on crowd work platforms.

The COVID-19 pandemic has brought out both the best and worst of language technology (LT). On one hand, conversational agents for information dissemination and basic diagnosis have seen widespread use, and arguably, had an important role in fighting against the pandemic. On the other hand, it has also become clear that such technologies are readily available for a handful of languages, and the vast majority of the global south is completely bereft of these benefits. What is the state of LT, especially conversational agents, for healthcare across the world’s languages? And, what would it take to ensure global readiness of LT before the next pandemic? In this paper, we try to answer these questions through survey of existing literature and resources, as well as through a rapid chatbot building exercise for 15 Asian and African languages with varying amount of resource-availability. The study confirms the pitiful state of LT even for languages with large speaker bases, such as Sinhala and Hausa, and identifies the gaps that could help us prioritize research and investment strategies in LT for healthcare.

Deployment of speech and language technology for social good (LT4SG), especially those targeted at the welfare of marginalized communities and speakers of low-resource and under-served languages, has been a prominent theme of research within NLP, Speech and the AI communities. Many researchers, especially those working in core NLP/Speech domains, rely on a combination of individual expertise, experiences or ad hoc surveys for prioritizing between language technologies that provide social good to the end-users. This has been criticized by several scholars who argue that it is critical to include the target community during the LT’s design and development process. However, prioritization of communities, languages, technologies and design approaches presents a very large set of complex challenges to the technologists, for which there are no simple or off-the-shelf solutions. In this position paper, we distill our experiential insights into six fundamental conundrums that technologists face and must resolve while deciding which LT technology to build for which community, and by using what approach. We discuss that at the root of these conundrums lie certain fundamental ethical problems of a digital-divide that can be overcome only by resolving deeper ethical dilemmas of distributive justice. We urge the community to reflect on these conundrums and leverage shared experiential insights to reconcile the intent of broadly, any Technology for Social Good, with the ground realities of its deployment.

In this work, we conduct a quantitative linguistic analysis of the language usage patterns of multilingual peer supporters in two health-focused WhatsApp groups in Kenya comprising of youth living with HIV. Even though the language of communication for the group was predominantly English, we observe frequent use of Kiswahili, Sheng and code-mixing among the three languages. We present an analysis of language choice and its accommodation, different functions of code-mixing, and relationship between sentiment and code-mixing. To explore the effectiveness of off-the-shelf Language Technologies (LT) in such situations, we attempt to build a sentiment analyzer for this dataset. Our experiments demonstrate the challenges of developing LT and therefore effective interventions for such forums and languages. We provide recommendations for language resources that should be built to address these challenges.

Seamless access to information in a rapidly globalizing world demands for availability of information across, ideally all but at the least a large number of, languages. Machine translation has been proposed as a technological solution to this complex problem. However, despite seven decades of research, and recently seen rapid progress in the field - thanks to deep learning and availability of large data-sets, perfect machine translation across a large number of the world’s languages still remains elusive. In fact, it is a distant and perhaps even an impossible goal. Erroneous translations, on the other hand, can be detrimental in critical situations such as talking to a law enforcement officer; or, they could potentially perpetuate social biases or stereotypes, for instance, by producing mis-gendered translations. In this work, we argue that language translation is inherently a socio-technical system, which has to be viewed, studied, and optimized for, as such. The need and context of translation, the socio-demographic factors behind the human translators as well as the consumers of the translated content affect the complexity of the translation system, as much as the accuracy of the technology and its interface. Through a series of case studies on mixed-initiative interaction based approach to translation, we bring out the various socio-technical factors and their complex interactions that one has to bear in mind while designing for the ideal human-machine translation systems. Through these observations, we make multiple recommendations which, at the core, suggest that ”solving” translation in the real sense would require more coordinated efforts between the technical (NLP) and social communities (HCI + CSCW + DEV).

Recently, there is increasing interest in multilingual automatic speech recognition (ASR) where a speech recognition system caters to multiple low resource languages by taking advantage of low amounts of labeled corpora in multiple languages. With multilingualism becoming common in today's world, there has been increasing interest in code-switching ASR as well. In code-switching, multiple languages are freely interchanged within a single sentence or between sentences. The success of low-resource multilingual and code-switching ASR often depends on the variety of languages in terms of their acoustics, linguistic characteristics as well as the amount of data available and how these are carefully considered in building the ASR system. In this challenge, we would like to focus on building multilingual and code-switching ASR systems through two different subtasks related to a total of seven Indian languages, namely Hindi, Marathi, Odia, Tamil, Telugu, Gujarati and Bengali. For this purpose, we provide a total of ~600 hours of transcribed speech data, comprising train and test sets, in these languages including two code-switched language pairs, Hindi-English and Bengali-English. We also provide a baseline recipe for both the tasks with a WER of 30.73% and 32.45% on the test sets of multilingual and code-switching subtasks, respectively.

Language technologies contribute to promoting multilingualism and linguistic diversity around the world.However, only a very small number of the over 7000 languages of the world are represented in the rapidly evolving language technologies and applications.In this paper we look at the relation between the types of languages, resources, and their representation in NLP conferences to understand the trajectory that different languages have followed over time.Our quantitative investigation underlines the disparity between languages, especially in terms of their resources, and calls into question the "language agnostic" status of current models and systems.Through this paper, we attempt to convince the ACL community to prioritise the resolution of the predicaments highlighted here, so that no language is left behind.

Voice-based technologies are essential to cater to the hundreds of millions of new smartphone users. However, most of the languages spoken by these new users have little to no labelled speech data. Unfortunately, collecting labelled speech data in any language is an expensive and resource-intensive task. Moreover, existing platforms typically collect speech data only from urban speakers familiar with digital technology whose dialects are often very different from low-income users. In this paper, we explore the possibility of collecting labelled speech data directly from low-income workers. In addition to providing diversity to the speech dataset, we believe this approach can also provide valuable supplemental earning opportunities to these communities. To this end, we conducted a study where we collected labelled speech data in the Marathi language from three different user groups: low-income rural users, low-income urban users, and university students. Overall, we collected 109 hours of data from 36 participants. Our results show that the data collected from low-income participants is of comparable quality to the data collected from university students (who are typically employed to do this work) and that crowdsourcing speech data from low-income rural and urban workers is a viable method of gathering speech data.

The primary obstacle to developing technologies for low-resource languages is the lack of usable data. In this paper, we report the adaption and deployment of 4 technology-driven methods of data collection for Gondi, a low-resource vulnerable language spoken by around 2.3 million tribal people in south and central India. In the process of data collection, we also help in its revival by expanding access to information in Gondi through the creation of linguistic resources that can be used by the community, such as a dictionary, children’s stories, an app with Gondi content from multiple sources and an Interactive Voice Response (IVR) based mass awareness platform. At the end of these interventions, we collected a little less than 12,000 translated words and/or sentences and identified more than 650 community members whose help can be solicited for future translation efforts. The larger goal of the project is collecting enough data in Gondi to build and deploy viable language technologies like machine translation and speech to text systems that can help take the language onto the internet.

Despite their pervasiveness, current text-based conversational agents (chatbots) are predominantly monolingual, while users are often multilingual. It is well-known that multilingual users mix languages while interacting with others, as well as in their interactions with computer systems (such as query formulation in text-/voice-based search interfaces and digital assistants). Linguists refer to this phenomenon as code-mixing or code-switching. Do multilingual users also prefer chatbots that can respond in a code-mixed language over those which cannot? In order to inform the design of chatbots for multilingual users, we conduct a mixed-method user-study (N=91) where we examine how conversational agents, that code-mix and reciprocate the users' mixing choices over multiple conversation turns, are evaluated and perceived by bilingual users. We design a human-in-the-loop chatbot with two different code-mixing policies -- (a) always code-mix irrespective of user behavior, and (b) nudge with subtle code-mixed cues and reciprocate only if the user, in turn, code-mixes. These two are contrasted with a monolingual chatbot that never code-mixed. Users are asked to interact with the bots, and provide ratings on perceived naturalness and personal preference. They are also asked open-ended questions around what they (dis)liked about the bots. Analysis of the chat logs, users' ratings, and qualitative responses reveal that multilingual users strongly prefer chatbots that can code-mix. We find that self-reported language proficiency is the strongest predictor of user preferences. Compared to the Always code-mix policy, Nudging emerges as a low-risk low-gain policy which is equally acceptable to all users. Nudging as a policy is further supported by the observation that users who rate the code-mixing bot higher typically tend to reciprocate the language mixing pattern of the bot. These findings present a first step towards developing conversational systems that are more human-like and engaging by virtue of adapting to the users' linguistic style.

We studied the topical preferences of social media campaigns of India's two main political parties by examining the tweets of 7382 politicians during the key phase of campaigning between Jan - May of 2019 in the run up to the 2019 general election. First, we compare the use of self-promotion and opponent attack, and their respective success online by categorizing 1208 most commonly used hashtags accordingly into the two categories. Second, we classify the tweets applying a qualitative typology to hashtags on the subjects of nationalism, corruption, religion and development. We find that the ruling BJP tended to promote itself over attacking the opposition whereas the main challenger INC was more likely to attack than promote itself. Moreover, while the INC gets more retweets on average, the BJP dominates Twitter's trends by flooding the online space with large numbers of tweets. We consider the implications of our findings hold for political communication strategies in democracies across the world.

Code-switching or the juxtaposition of linguistic units from two or more languages in a single utterance, has, in recent times, become very common in text, thanks to social media and other computer mediated forms of communication. In this exploratory study of English-Hindi code-switching on Twitter, we automatically create a large corpus of code-switched tweets and devise techniques to identify the relationship between successive components in a code-switched tweet. More specifically, we identify pragmatic functions such as narrative-evaluative, negative reinforcement, translation or semantically equivalent statements, and so on characterizing the relation between successive components. We analyze the difference/similarity between switching patterns in code-switched and monolingual multi-component tweets. We observe strong dominance of narrative-evaluative (non-opinion to opinion or vice versa) switching in case of both code-switched and monolingual multi-component tweets in around 40% of cases. Polarity switching appears to be a prevalent switching phenomenon (10%) specifically in code-switched tweets (three to four times higher than monolingual multi-component tweets) where preference of expressing negative sentiment in Hindi is approximately twice compared to English. Positive reinforcement appears to be an important pragmatic function for English multi-component tweets, whereas negative reinforcement plays a key role for Devanagari multi-component tweets. Our results also indicate that the extent and nature of code-switching also strongly depend on the topic (sports, politics, etc.) of discussion.

Adithya Pratapa, Gayatri Bhat, Monojit Choudhury, Sunayana Sitaram, Sandipan Dandapat, Kalika Bali. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018.

Shruti Rijhwani, Royal Sequiera, Monojit Choudhury, Kalika Bali, Chandra Shekhar Maddila. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2017.

Linguistic research on multilingual societies has indicated that there is usually a preferred language for expression of emotion and sentiment (Dewaele, 2010).Paucity of data has limited such studies to participant interviews and speech transcriptions from small groups of speakers.In this paper, we report a study on 430,000 unique tweets from Indian users, specifically Hindi-English bilinguals, to understand the language of preference, if any, for expressing opinion and sentiment.To this end, we develop classifiers for opinion detection in these languages, and further classifying opinionated tweets into positive, negative and neutral sentiments.Our study indicates that Hindi (i.e., the native language) is preferred over English for expression of negative opinion and swearing.As an aside, we explore some common pragmatic functions of codeswitching through sentiment detection.* * This work was done when the author was a Research Fellow at Microsoft Research Lab India.1 Although some linguists differentiate between Codeswitching and Code-mixing, this paper will use the two terms interchangeably.

Code-mixing is frequently observed in user generated content on social media, especially from multilingual users. The linguistic complexity of such content is compounded by presence of spelling vari-ations, transliteration and non-adherance to formal grammar. We describe our initial efforts to create a multi-level an-notated corpus of Hindi-English code-mixed text collated from Facebook fo-rums, and explore language identifica-tion, back-transliteration, normalization and POS tagging of this data. Our re-sults show that language identification and transliteration for Hindi are two major challenges that impact POS tagging accu-racy. 1

For many languages that use non-Roman based indigenous scripts (e.g., Arabic, Greek and Indic languages) one can often find a large amount of user generated transliterated content on the Web in the Roman script. Such content creates a monolingual or multi-lingual space with more than one script which we refer to as the Mixed-Script space. IR in the mixed-script space is challenging because queries written in either the native or the Roman script need to be matched to the documents written in both the scripts. Moreover, transliterated content features extensive spelling variations. In this paper, we formally introduce the concept of Mixed-Script IR, and through analysis of the query logs of Bing search engine, estimate the prevalence and thereby establish the importance of this problem. We also give a principled solution to handle the mixed-script term matching and spelling variation where the terms across the scripts are modelled jointly in a deep-learning architecture and can be compared in a low-dimensional abstract space. We present an extensive empirical analysis of the proposed method along with the evaluation results in an ad-hoc retrieval setting of mixed-script IR where the proposed method achieves significantly better results (12% increase in MRR and 29% increase in MAP) compared to other state-of-the-art baselines.

Designing ICT systems for rural users in the developing world is difficult for a variety of reasons ranging from problems with infrastructure to wide differences in user contexts and capabilities. Developing regions may include huge variability in spoken languages, and users are often low- or non-literate, with very little experience interacting with digital technologies. Researchers have explored the use of text-free graphical interfaces as well as speech-based applications to overcome some of the issues related to language and literacy. While there are benefits and drawbacks to each of these approaches, they can be complementary when used together. In this work, we present VideoKheti, a mobile system using speech, graphics, and touch interaction for low-literate farmers in rural India. VideoKheti helps farmers to find and watch agricultural extension videos in their own language and dialect. In this paper, we detail the design and development of VideoKheti and report on a field study with 20 farmers in rural India who were asked to find videos based on a scenario. The results show that farmers could use VideoKheti, but their success still greatly depended on their education level. While participants were enthusiastic about using the system, the multimodal interface did not overcome many obstacles for low-literate users.

In Hindi, affirmative particle ha carries out a variety of discourse functions. Preliminary investigation has shown that though it is difficult to disambiguate these different functions, there seems to be a distinct prosodic pattern associated with each of these. In this paper, we present a corpus study of spoken utterances of the Hindi word ha. We identify these prosodic patterns and capture the specific pitch variations associated with each of the various functions. We also examine the use of prosodic cues in classification of the utterances into different functions using k-means clustering. While certain amount of speaker dependency, as well as lack of contextual and lexical information resulted in high classification entropy, however, the results were consistent with comparable studies in other languages.

Multimodal systems, incorporating more natural input modalities like speech, hand gesture, facial expression etc., can make human-computer-interaction more intuitive by drawing inspiration from spontaneous human-human-interaction. We present here a multimodal input device for Indic scripts called the Voice Key Board (VKB) which offers a simpler and more intuitive method for input of Indic scripts. VKB exploits the syllabic nature of Indic language scripts and exploits the user's mental model of Indic scripts wherein a base consonant character is modified by different vowel ligatures to represent the actual syllabic character. We also present a user evaluation result for VKB comparing it with the most common input method for the Devanagari script, the InScript keyboard. The results indicate a strong user preference for VKB in terms of input speed and learnability. Though VKB starts with a higher user error rate compared to InScript, the error rate drops by 55% by the end of the experiment, and the input speed of VKB is found to be 81% higher than InScript. Our user study results point to interesting research directions for the use of multiple natural modalities for Indic text input.

Affirmative particles are often employed in conversational speech to convey more than their literal semantic meaning. The discourse information conveyed by such particles can have consequences in both Speech Understanding and Speech Production for a Spoken Dialogue System. This paper analyses the different discourse functions of the affirmative particle ha (“yes”) in Hindi and in explores the role of fundamental frequency (f0) as a cue to disambiguating these functions.

We investigate the effect of accent on comprehension of English for speakers of English as a second language in southern India. Subjects were exposed to real and TTS voices with US and several Indian accents, and were tested for intelligibility and comprehension. Performance trends indicate a measurable advantage for familiar accents, and are broken down by various demographic factors.

The full range of possibilities for spoken-language technologies (SLTs) to impact poor communities has been investigated on partially, despite what appears to be strong potential. Voice interfaces raise fewer barriers for the illiterate, require less training to use, and are a natural choice for applications on cell phones, which have far greater penetration, in the developing world than PCs. At the same time, critical lessons of existing technology projects in development still apply and require careful attention. We suggest how to expand the view of SLT for development, and discuss how its potential can realistically be explored.

This paper introduces our efforts to create UPX, an XML-based successor to the venerable UNIPEN format for the representation of annotated datasets of online handwriting data. In the first part of the paper, shortcomings of the UNIPEN format are discussed and the goals of UPX are outlined. Prior work related to UPX in the form of the recently proposed hwDataset representation is presented. The second part of the paper summarizes the status of the UPX effort, in particular, experiments to map UNIPEN elements to hwDataset and InkML and identify potential issues with migrating existing UNIPEN data to UPX. This is work in progress, and we invite participation from the handwriting recognition research community and industry to make UPX a reality.

This paper reports preliminary results of data-driven modeling of segmental (phoneme) duration for Hindi. Classification and Regression Tree (CART) based datadriven duration modeling for segmental duration prediction is presented. A number of features are considered and their usefulness and relative contribution for segmental duration prediction is assessed. Objective evaluation of the duration model, by root mean squared prediction error (RMSE) and correlation between actual and predicted durations, is performed.