Related papers: DNN-based Speech Synthesis for Indian Languages fr…

Disfluencies commonly occur in conversational speech. Speech with disfluencies can result in noisy Automatic Speech Recognition (ASR) transcripts, which affects downstream tasks like machine translation. In this paper, we propose an…

Deep Learning techniques are powerful in mimicking humans in a particular set of problems. They have achieved a remarkable performance in complex learning tasks. Deep learning inspired Neural Machine Translation (NMT) is a proficient…

Tibetan text-to-speech (TTS) has long been challenged by scarce speech resources, significant dialectal variation, and the complex mapping between written text and spoken pronunciation. To address these issues, this work presents, to the…

Transliteration is a task in the domain of NLP where the output word is a similar-sounding word written using the letters of any foreign language. Today this system has been developed for several language pairs that involve English as…

Modern Automatic Speech Recognition (ASR) technology has evolved to identify the speech spoken by native speakers of a language very well. However, identification of the speech spoken by non-native speakers continues to be a major challenge…

Use of social media has grown dramatically during the last few years. Users follow informal languages in communicating through social media. The language of communication is often mixed in nature, where people transcribe their regional…

Numerous models have shown great success in the fields of speech recognition as well as speech synthesis, but models for speech to speech processing have not been heavily explored. We propose Speech to Speech Synthesis Network (STSSN), a…

The increased adoption of digital assistants makes text-to-speech (TTS) synthesis systems an indispensable feature of modern mobile devices. It is hence desirable to build a system capable of generating highly intelligible speech in the…

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…

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…

The use of subword embedding has proved to be a major innovation in Neural Machine Translation (NMT). It helps NMT to learn better context vectors for Low Resource Languages (LRLs) so as to predict the target words by better modelling the…

Transliteration is very important in the Indian language context due to the usage of multiple scripts and the widespread use of romanized inputs. However, few training and evaluation sets are publicly available. We introduce Aksharantar,…

In this report, we summarize the integrated multilingual audio processing pipeline developed by our team for the inaugural NCIIPC Startup India AI GRAND CHALLENGE, addressing Problem Statement 06: Language-Agnostic Speaker Identification…

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…

Both acoustic and visual information influence human perception of speech. For this reason, the lack of audio in a video sequence determines an extremely low speech intelligibility for untrained lip readers. In this paper, we present a way…

Hidden-Markov-model (HMM) based text-to-speech (HTS) offers flexibility in speaking styles along with fast training and synthesis while being computationally less intense. HTS performs well even in low-resource scenarios. The primary…

Generative models have long been the dominant approach for speech recognition. The success of these models however relies on the use of sophisticated recipes and complicated machinery that is not easily accessible to non-practitioners.…

In this paper, we present a 170.83 hour Indian English spontaneous speech dataset. Lack of Indian English speech data is one of the major hindrances in developing robust speech systems which are adapted to the Indian speech style. Moreover…

India's vast linguistic diversity presents unique challenges and opportunities for technological advancement, especially in the realm of Natural Language Processing (NLP). While there has been significant progress in NLP applications for…

It is desirable for a text-to-speech system to take into account the environment where synthetic speech is presented, and provide appropriate context-dependent output to the user. In this paper, we present and compare various approaches for…