相关论文: A Dataset for measuring reading levels in India at…

We describe here our work with automatic speech recognition (ASR) in the context of voice search functionality on the Flipkart e-Commerce platform. Starting with the deep learning architecture of Listen-Attend-Spell (LAS), we build upon and…

India's rich cultural and linguistic diversity poses various challenges in the domain of Natural Language Processing (NLP), particularly in Named Entity Recognition (NER). NER is a NLP task that aims to identify and classify tokens into…

Automatic classification of disordered speech can provide an objective tool for identifying the presence and severity of speech impairment. Classification approaches can also help identify hard-to-recognize speech samples to teach ASR…

Despite the growing advancements in Automatic Speech Recognition (ASR) models, the development of robust models for underrepresented languages, such as Nepali, remains a challenge. This research focuses on making an exhaustive and…

Automatic Speech Recognition (ASR) systems often struggle to accurately process children's speech due to its distinct and highly variable acoustic and linguistic characteristics. While recent advancements in self-supervised learning (SSL)…

Automatic speech recognition (ASR) is widely used in consumer electronics. ASR greatly improves the utility and accessibility of technology, but usually the output is only word sequences without punctuation. This can result in ambiguity in…

State-of-the-art ASRs show suboptimal performance for child speech. The scarcity of child speech limits the development of child speech recognition (CSR). Therefore, we studied child-to-child voice conversion (VC) from existing child…

Large language models (LLMs) demonstrated transformative capabilities in many applications that require automatically generating responses based on human instruction. However, the major challenge for building LLMs, particularly in Indic…

We summarize the results of a host of efforts using giant automatic speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets containing approximately a million hours of audio. We find that the combination of…

We describe our end-to-end system for Bengali long-form speech recognition (ASR) and speaker diarization submitted to the DL Sprint 4.0 competition on Kaggle. Bengali presents substantial challenges for both tasks: a large phoneme…

Speech technologies are transforming interactions across various sectors, from healthcare to call centers and robots, yet their performance on African-accented conversations remains underexplored. We introduce Afrispeech-Dialog, a benchmark…

This paper introduces Multilingual LibriSpeech (MLS) dataset, a large multilingual corpus suitable for speech research. The dataset is derived from read audiobooks from LibriVox and consists of 8 languages, including about 44.5K hours of…

From ancient period in India, educational institution embarked to use class room teaching. Where a teacher explains the material and students understand and learn the lesson. There is no absolute scale for measuring knowledge but…

India has 1369 languages of which 22 are official. About 13 different scripts are used to represent these languages. A Common Label Set (CLS) was developed based on phonetics to address the issue of large vocabulary of units required in the…

Studying early speech development at scale requires automatic tools, yet automatic phoneme recognition, especially for young children, remains largely unsolved. Building on decades of data collection, we curate TinyVox, a corpus of more…

In a conventional Speech emotion recognition (SER) task, a classifier for a given language is trained on a pre-existing dataset for that same language. However, where training data for a language does not exist, data from other languages…

Expanding the language coverage of speech technology has the potential to improve access to information for many more people. However, current speech technology is restricted to about one hundred languages which is a small fraction of the…

Text encodings from automatic speech recognition (ASR) transcripts and audio representations have shown promise in speech emotion recognition (SER) ever since. Yet, it is challenging to explain the effect of each information stream on the…

Modern language models (LMs) must be trained on many orders of magnitude more words of training data than human children receive before they begin to produce useful behavior. Assessing the nature and origins of this "data gap" requires…

Audio tagging is the task of predicting the presence or absence of sound classes within an audio clip. Previous work in audio tagging focused on relatively small datasets limited to recognising a small number of sound classes. We…