相关论文: LAHAJA: A Robust Multi-accent Benchmark for Evalua…

Deaf or hard-of-hearing (DHH) speakers typically have atypical speech caused by deafness. With the growing support of speech-based devices and software applications, more work needs to be done to make these devices inclusive to everyone. To…

We introduce RASMALAI, a large-scale speech dataset with rich text descriptions, designed to advance controllable and expressive text-to-speech (TTS) synthesis for 23 Indian languages and English. It comprises 13,000 hours of speech and 24…

Question answering (QA) systems are now available through numerous commercial applications for a wide variety of domains, serving millions of users that interact with them via speech interfaces. However, current benchmarks in QA research do…

Voice based applications are ruling over the era of automation because speech has a lot of factors that determine a speakers information as well as speech. Modern Automatic Speech Recognition (ASR) is a blessing in the field of…

Although Automatic Speech Recognition (ASR) in Bengali has seen significant progress, processing long-duration audio and performing robust speaker diarization remain critical research gaps. To address the severe scarcity of joint ASR and…

Recent advances in speech-enabled AI, including Google's NotebookLM and OpenAI's speech-to-speech API, are driving widespread interest in voice interfaces globally. Despite this momentum, there exists no publicly available…

India is home to a multitude of languages of which 22 languages are recognised by the Indian Constitution as official. Building speech based applications for the Indian population is a difficult problem owing to limited data and the number…

Large language models (LLMs) have driven substantial advances in speech language models (SpeechLMs), yielding strong performance in automatic speech recognition (ASR) under high-resource conditions. However, existing benchmarks…

Analogies test a model's ability to infer implicit relationships between concepts, making them a key benchmark for evaluating reasoning capabilities. While large language models (LLMs) are widely evaluated for reasoning in English, their…

Evaluating English ASR systems for conversational AI applications remains difficult, as many publicly available corpora are either pre-segmented into short segments, consist of read or prepared speech, or lack explicit dialect annotations…

This paper describes the systems developed by SPRING Lab, Indian Institute of Technology Madras, for the ASRU MADASR 2.0 challenge. The systems developed focuses on adapting ASR systems to improve in predicting the language and dialect of…

Bengali is one of the most spoken languages in the world with over 300 million speakers globally. Despite its popularity, research into the development of Bengali speech recognition systems is hindered due to the lack of diverse open-source…

With the rise of online abuse, the NLP community has begun investigating the use of neural architectures to generate counterspeech that can "counter" the vicious tone of such abusive speech and dilute/ameliorate their rippling effect over…

Speech evaluation is an essential component in computer-assisted language learning (CALL). While speech evaluation on English has been popular, automatic speech scoring on low resource languages remains challenging. Work in this area has…

Large language models (LLMs) are increasingly deployed in multilingual applications but often generate plausible yet incorrect or misleading outputs, known as hallucinations. While hallucination detection has been studied extensively in…

Current evaluation benchmarks for question answering (QA) in Indic languages often rely on machine translation of existing English datasets. This approach suffers from bias and inaccuracies inherent in machine translation, leading to…

Automatic Speech Recognition (ASR) for Bengali, the world's fifth most spoken language, remains a significant challenge, critically hindering technological accessibility for its over 270 million speakers. This challenge is compounded by two…

Speech systems are sensitive to accent variations. This is especially challenging in the Indian context, with an abundance of languages but a dearth of linguistic studies characterising pronunciation variations. The growing number of L2…

To build an automatic speech recognition (ASR) system that can serve everyone in the world, the ASR needs to be robust to a wide range of accents including unseen accents. We systematically study how three different variables in training…

Despite Telugu being spoken by over 80 million people, speech translation research for this morphologically rich language remains severely underexplored. We address this gap by developing a high-quality Telugu--English speech translation…