Related papers: Prosody Labelled Dataset for Hindi using Semi-Auto…

Poetry generation in Sanskrit typically requires the verse to be semantically coherent and adhere to strict prosodic rules. In Sanskrit prosody, every line of a verse is typically a fixed length sequence of syllables adhering to prescribed…

Speech generation for machine dubbing adds complexity to conventional Text-To-Speech solutions as the generated output is required to match the expressiveness, emotion and speaking rate of the source content. Capturing and transferring…

Emotion and intent recognition from speech is essential and has been widely investigated in human-computer interaction. The rapid development of social media platforms, chatbots, and other technologies has led to a large volume of speech…

We address the problem of inferring a speaker's level of certainty based on prosodic information in the speech signal, which has application in speech-based dialogue systems. We show that using phrase-level prosodic features centered around…

Recently, self-supervised pre-training has gained success in automatic speech recognition (ASR). However, considering the difference between speech accents in real scenarios, how to identify accents and use accent features to improve ASR is…

Audio deepfakes are increasingly in-differentiable from organic speech, often fooling both authentication systems and human listeners. While many techniques use low-level audio features or optimization black-box model training, focusing on…

Natural language processing (NLP) has experienced rapid advancements with the rise of deep learning, significantly outperforming traditional rule-based methods. By capturing hidden patterns and underlying structures within data, deep…

Recent parallel neural text-to-speech (TTS) synthesis methods are able to generate speech with high fidelity while maintaining high performance. However, these systems often lack control over the output prosody, thus restricting the…

In recent decades, Speech interactive systems gained increasing importance. To develop Dictation System like Dragon for Indian languages it is most important to adapt the system to a speaker with minimum training. In this paper we focus on…

The demo proposal presents a Phrase-based Sanskrit-Hindi (SaHiT) Statistical Machine Translation system. The system has been developed on Moses. 43k sentences of Sanskrit-Hindi parallel corpus and 56k sentences of a monolingual corpus in…

In this paper, we present specially designed automatic speech recognition (ASR) systems for the highly agglutinative and inflective languages of Tamil and Kannada that can recognize unlimited vocabulary of words. We use subwords as the…

A cornerstone in AI research has been the creation and adoption of standardized training and test datasets to earmark the progress of state-of-the-art models. A particularly successful example is the GLUE dataset for training and evaluating…

Automatic Speech Recognition (ASR) for low-resource Dravidian languages like Telugu and Kannada faces significant challenges in specialized medical domains due to limited annotated data and morphological complexity. This work proposes a…

Recent NLP advances focus primarily on standardized languages, leaving most low-resource dialects under-served especially in Indian scenarios. In India, the issue is particularly important: despite Hindi being the third most spoken language…

The goal of Text-to-Speech (TTS) synthesis in a particular language is to convert arbitrary input text to intelligible and natural sounding speech. However, for a particular language like Hindi, which is a highly confusing language (due to…

The use of emojis affords a visual modality to, often private, textual communication. The task of predicting emojis however provides a challenge for machine learning as emoji use tends to cluster into the frequently used and the rarely used…

This paper presents a speech BERT model to extract embedded prosody information in speech segments for improving the prosody of synthesized speech in neural text-to-speech (TTS). As a pre-trained model, it can learn prosody attributes from…

Prosody is a rich information source in natural language, serving as a marker for phenomena such as contrast. In order to make this information available to downstream tasks, we need a way to detect prosodic events in speech. We propose a…

Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency training on a large amount of unlabeled data to constrain model…

This paper argues that the relationship between lexical identity and prosody -- one well-studied parameter of linguistic variation -- can be characterized using information theory. We predict that languages that use prosody to make lexical…