Related papers: Dhvani: A Weakly-supervised Phonemic Error Detecti…
The rapid growth of machine translation (MT) systems has necessitated comprehensive studies to meta-evaluate evaluation metrics being used, which enables a better selection of metrics that best reflect MT quality. Unfortunately, most of the…
Transformer-based models have recently become very popular for sequence-to-sequence applications such as machine translation and speech recognition. This work proposes a dual-decoder transformer model for low-resource multilingual speech…
Full-duplex spoken dialogue systems can model natural conversational behaviours such as interruptions, overlaps, and backchannels, yet such systems remain largely unexplored for Indian languages. We present the first open, reproducible…
The advancements in generative AI have enabled the improvement of audio synthesis models, including text-to-speech and voice conversion. This raises concerns about its potential misuse in social manipulation and political interference, as…
Text-to-speech (TTS) systems typically require high-quality studio data and accurate transcriptions for training. India has 1369 languages, with 22 official using 13 scripts. Training a TTS system for all these languages, most of which have…
Handwritten character recognition is getting popular among researchers because of its possible applications in facilitating technological search engines, social media, recommender systems, etc. The Devanagari script is one of the oldest…
Voice based technologies have the potential to bridge digital accessibility gaps; however, existing datasets fail to capture the linguistic and regional diversity of Indic languages. We present Project VAANI, a large scale multimodal…
The primary obstacle to developing technologies for low-resource languages is the lack of usable data. In this paper, we report the adoption and deployment of 4 technology-driven methods of data collection for Gondi, a low-resource…
We present a speaker conditioned text-to-speech (TTS) system aimed at addressing challenges in generating speech for unseen speakers and supporting diverse Indian languages. Our method leverages a diffusion-based TTS architecture, where a…
Conversational speech often consists of deviations from the speech plan, producing disfluent utterances that affect downstream NLP tasks. Removing these disfluencies is necessary to create fluent and coherent speech. This paper presents…
Automatic speech recognition has recently seen a significant advancement with large foundational models such as Whisper. However, these models often struggle to perform well in low-resource languages, such as Indian languages. This paper…
Natural Language Processing (NLP) and especially natural language text analysis have seen great advances in recent times. Usage of deep learning in text processing has revolutionized the techniques for text processing and achieved…
Text-to-Speech synthesis in Indian languages has a seen lot of progress over the decade partly due to the annual Blizzard challenges. These systems assume the text to be written in Devanagari or Dravidian scripts which are nearly phonemic…
Computer-Assisted Pronunciation Training (CAPT) plays an important role in language learning. Conventional ASR-based CAPT methods require expensive annotation of the ground truth pronunciation for the supervised training. Meanwhile, certain…
Written Communication on Computers requires knowledge of writing text for the desired language using Computer. Mostly people do not use any other language besides English. This creates a barrier. To resolve this issue we have developed a…
Spelling error correction is the task of identifying and rectifying misspelled words in texts. It is a potential and active research topic in Natural Language Processing because of numerous applications in human language understanding. The…
The performance of a text-to-speech (TTS) synthesis model depends on various factors, of which the quality of the training data is of utmost importance. Millions of data are collected around the globe for various languages, but resources…
Codeswitching has become one of the most common occurrences across multilingual speakers of the world, especially in countries like India which encompasses around 23 official languages with the number of bilingual speakers being around 300…
The recent advancements in generative artificial speech models have made possible the generation of highly realistic speech signals. At first, it seems exciting to obtain these artificially synthesized signals such as speech clones or deep…
We propose a new method for the calculation of error rates in Automatic Speech Recognition (ASR). This new metric is for languages that contain half characters and where the same character can be written in different forms. We implement our…