Abstract

The demand for high-quality parallel speech data has been increasing as deep learning-based Speech to Speech Machine Translation (SSMT) and automatic dubbing approaches gain popularity in speech applications. Traditional and well-established speech applications such as Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) heavily rely on large corpus of monolingual speech and the corresponding text. While there is a wealth of parallel text data available for both English and Indic languages, parallel speech data is available only for English and other European languages, yet it often lacks natural prosody and semantic alignment between the languages. For achieving cross-lingual prosody transfer, end-to-end SSMT models, and high-quality dubbing from English to Hindi, in this work, an English-Hindi parallel bilingual speech-text corpus named lIlT-Speech Twins 1.0 is created. This data contains twin-like English and Hindi speech-text pairs obtained from publicly available children's stories in both the languages, through manual and automatic processing. Starting with 8 stories in each language, totaling around 4 hours of audio, the final outcome was a 2-hour dataset. This was achieved through systematic segmentation, re-moval of non-speech background audio, and sentence-by-sentence alignment to ensure accurate meaning in both languages. In addition to ensuring proper alignment and transcription, this dataset offers a rich source of natural prosody, expressions, and emotions, due to the narrative diversity within the stories. The dataset also provides sig-nificant speaker variability, with different characters being voiced by various speakers, enhancing the richness of the lIlT-Speech Twins 1.0 corpus.

Abstract

Celebrated for its stunning landscapes, Himachal Pradesh has become a renowned tourist destination, experiencing a surge in visitors. Since the 1980s, the state has witnessed significant economic growth, supported by a boom in the tourism industry. This research aims to correlate tourism with economic growth and analyse the unique tourism-driven development of Himachal Pradesh. We used urban built-up areas in key tourist hotspots as a proxy, and employed Geographic Information Systems (GIS) and visual interpretation techniques to examine urban growth around Solang Valley, Bhagsunag Temple, Chail, Kufri, and Khajjiar from 1990 to 2020. Historical Landsat satellite imagery was utilised to quantify urban built-up changes. The findings revealed a significant increase in built-up areas within all tourist buffer zones, with Bhagsunag Temple showing the most dramatic growth (~1000%). Non-tourist locations with similar demographics showed an average increase of 55%, compared to 427% in tourist buffers. This study demonstrates that built-up areas have expanded more rapidly in tourist areas, highlighting the substantial impact of tourism on urban growth. These findings suggest the need for further exploration into tourism, policy studies, and economics in Himachal Pradesh. Keywords: GIS, Tourism, Urbanisation, Remote Sensing, Landsat, Himachal Pradesh.

Abstract

Edge–cloud coordination offers the chance to mitigate the enormous storage and processing load brought on by a massive increase in traffic at the network’s edge. Though this paradigm has benefits on a large scale, outsourcing the sensitive data from the smart devices deployed in an Internet of Things (IoT) application may lead to privacy leakage. With an attribute-based keyword search (ABKS), the search over ciphertext can be achieved; this reduces the risk of sensitive data explosion. However, ABKS has several issues, like huge computational overhead to perform multi-keyword searches and tracing malicious users. To address these issues and enhance the performance of ABKS, we propose a novel traceable and lightweight attribute-based keyword search technique in an Edge–cloud-assisted IoT, named TL-ABKS, using edge–cloud coordination. With TL-ABKS, it is possible to do effective multi-keyword searches and implement fine-grained access control. Further, TL-ABKS outsources the encryption and decryption computation to edge nodes to enable its usage to resource-limited IoT smart devices. In addition, TL-ABKS achieves tracing user identity who misuse their secret keys. TL-ABKS is secure against modified secret keys, chosen plaintext, and chosen keyword attacks. By comparing the proposed TL-ABKS with the current state-of-the-art schemes, and conducting a theoretical and experimental evaluation of its performance and credibility, TL-ABKS is efficient.

Abstract

Obtaining sufficient information in one’s mother tongue is crucial for satisfying the information needs of the users. While high-resource languages have abundant online resources, the situation is less than ideal for very low-resource languages. Moreover, the insufficient reporting of vital national and international events continues to be a worry, especially in languages with scarce resources, like Mizo. In this paper, we conduct a study to investigate the effectiveness of a simple methodology designed to generate a holistic summary for Mizo news articles, which leverages English-language news to supplement and enhance the information related to the corresponding news events. Furthermore, we make available 500 Mizo news articles and corresponding enriched holistic summaries. Human evaluation confirms that our approach significantly enhances the information coverage of Mizo news articles.

Abstract

Controller synthesis is pivotal in automating control system design from formal specifications and enhancing industrial system verification and optimization processes. This paper critically evaluates LTL-based controller synthesis, highlighting significant gaps in tool support that hinder its widespread adoption in the industry. Despite substantial theoretical progress, an apparent disparity persists between academic research outcomes and the robust, practical tools demanded by industry. Through a comprehensive evaluation, this study reveals mismatches between industrial requirements and the capabilities of current open-source tools. The findings emphasize underexplored challenges and propose future research directions and strategies for practical integration. This work aims to bridge the gap by advocating for enhanced tool support, enabling solutions that align with industrial standards and fostering the broader application of controller synthesis across various sectors.

Abstract

Graphs, including, for example, social networks, collaboration networks, and epidemiological networks, offer a way to represent relationships among entities. Graphs arising from most real-world phenomena are not static and evolve. Dealing with such dynamic graphs requires special algorithms, known as dynamic graph algorithms, that update the required graph analytic based on the change in the current graph instead of recomputing the analytic from scratch. Parallel dynamic graph algorithms are now known for various graph problems such as connectivity, spanning trees, shortest paths, centrality metrics, and community detection. Dynamic algorithms often work in settings where a batch of edge insertions/deletions affects the current graph.

Abstract

Open Vocabulary Keyword Spotting is essential in numerous applications, from virtual assistants to security systems, as it allows systems to identify specific words or phrases in continuous speech. In this paper, we propose a novel end-to-end method for detecting user-defined open vocabulary keywords by leveraging linguistic patterns for the correlation between audio and text modalities. Our approach utilizes quantized pre-trained foundation models for robust audio embeddings and a unique lightweight Multi-Scale Linear Attention (MSLA) network that aligns speech and text representations for effective cross-modal agreement. We evaluate our method on two distinct datasets, comparing its performance against other baselines. The results highlight the effectiveness of our approach, achieving significant improvements over the Cross-Modality Correspondence Detector (CMCD) method, with a 16.08% increase in AUC and a 17.2% reduction in EER metrics on the Google Speech Commands dataset. These findings demonstrate the potential of our method to advance keyword spotting across various real-world applications.

Abstract

Coreference resolution, the process of determining what a referring expression (a pronoun or a noun phrase) refers to in discourse, is a critical aspect of natural language understanding. However, the development of computational models for coreference resolution in low-resource languages, such as the Dravidian (and more broadly all South Asian) languages, still remains a significant challenge due to the scarcity of annotated corpora in these languages. To address this data scarcity, we adopt a pipeline that translates the English GAP dataset into various South Asian languages, creating a multi-lingual coreference dataset mGAP. Our research aims to leverage this dataset and develop two novel models, namely the joint embedding model and the cross attention model for coreference resolution with Dravidian languages in mind. We also demonstrate that cross-attention captures pronoun-candidate relations better leading to improved coreference resolution. We also harness the similarity across South Asian languages via transfer learning in order to use high resource languages to learn coreference for low resource languages.

Abstract

Voltage-Controlled Oscillator (VCO) is a crucial component of a Phase-Locked Loop (PLL) system. However, the frequency of a typical Ring-Oscillator-based VCO varies by about 2–3 times across its frequency tuning range and process, voltage and temperature (PVT) conditions. The gain of a Ring-VCO is another crucial parameter that is significantly affected by PVT variations, thereby impacting the stability and loop bandwidth of the PLL. This paper describes a compensation technique to minimize variations in Ring-VCO gain across PVT conditions. A Charge-Pump PLL operating at 4 GHz is implemented in a 28nm CMOS process. The gain of the Ring-VCO varies by ±27% across PVT at 4 GHz. This gain variation of Ring-VCO combined with other PVT-dependent blocks of PLL lead to a deviation of ±60% in Loop Bandwidth and ±21 % in Phase-Margin (PM). Process trimming reduces the VCO gain variation to ±25 %. Subsequently, the temperature compensation technique reduces the VCO gain variation by 3 times to ±8 %, over a temperature range −40∘C to 125∘C . The resulting variations in Loop Bandwidth and Phase-Margin are reduced to ±34%” and ±l5%” respectively.

Abstract

Scene text recognition has historically concentrated on English, with limited advancements in developing solutions that perform well across multiple languages. Previous efforts in multilingual scene text recognition have predominantly targeted languages with considerable syntactic and semantic differences. However, Indian languages, while diverse, share numerous common features that remain largely underutilized. This competition aims to address the often-overlooked challenge of scene text recognition within the Indian context and to advance robust word image recognition across ten Indian languages. The dataset provided for this competition is one of the most comprehensive multilingual datasets, encompassing 10 languages, each with 17,500 training samples, 2,500 validation samples and 5,000 test word-image samples. The task was to correctly recognize the word-images, for which we received forty-nine registrations and five final submissions from industrial and research communities. The winning team achieved an average Character Recognition Rate (CRR) of 92.85% and a Word Recognition Rate (WRR) of 84.01% across the ten languages. This paper details the proposed dataset and summarizes the submissions for the competition- WIRIndic-2024.