Related papers: Phoneme Recognition through Fine Tuning of Phoneti…

The rapid advancement of spoofing algorithms necessitates the development of robust detection methods capable of accurately identifying emerging fake audio. Traditional approaches, such as finetuning on new datasets containing these novel…

Currently available benchmarks for few-shot learning (machine learning with few training examples) are limited in the domains they cover, primarily focusing on image classification. This work aims to alleviate this reliance on image-based…

Multilingual speech emotion recognition aims to estimate a speaker's emotional state using a contactless method across different languages. However, variability in voice characteristics and linguistic diversity poses significant challenges…

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…

This paper investigates adapting Audio Large Language Models (ALLMs) for speaker verification (SV). We reformulate SV as an audio question-answering task and conduct comprehensive zero-shot evaluations on public benchmarks, showing that…

Sign language discourse is an essential mode of daily communication for the deaf and hard-of-hearing people. However, research on Bangla Sign Language (BdSL) faces notable limitations, primarily due to the lack of datasets. Recognizing…

This paper explores syllable sequence prediction in Abugida languages using Transformer-based models, focusing on six languages: Bengali, Hindi, Khmer, Lao, Myanmar, and Thai, from the Asian Language Treebank (ALT) dataset. We investigate…

Recent advances in large-scale vision-language models have achieved impressive performance in various zero-shot image classification tasks. While prior studies have demonstrated significant improvements by introducing few-shot labelled…

We introduce DiscoPhon, a multilingual benchmark for evaluating unsupervised phoneme discovery from discrete speech units. DiscoPhon covers 6 dev and 6 test languages, chosen to span a wide range of phonemic contrasts. Given only 10 hours…

Speech large language models (speech-LLMs) integrate speech and text-based foundation models to provide a unified framework for handling a wide range of downstream tasks. In this paper, we introduce WHISMA, a speech-LLM tailored for spoken…

In this article, we present an approach for non native automatic speech recognition (ASR). We propose two methods to adapt existing ASR systems to the non-native accents. The first method is based on the modification of acoustic models…

We present a method for discovering morphological features in low-resource Bantu languages by combining cross-lingual transfer learning with unsupervised clustering. Applied to Giriama (nyf), a language with only 91 labeled paradigms, our…

There exist three approaches for multilingual and crosslingual automatic speech recognition (MCL-ASR) - supervised pretraining with phonetic or graphemic transcription, and self-supervised pretraining. We find that pretraining with phonetic…

Phonetic error detection, a core subtask of automatic pronunciation assessment, identifies pronunciation deviations at the phoneme level. Speech variability from accents and dysfluencies challenges accurate phoneme recognition, with current…

Large pre-trained language models (PLMs) are at the forefront of advances in Natural Language Processing. One widespread use case of PLMs is "prompting" - or in-context learning - where a user provides a description of a task and some…

Large-scale contrastive vision-language pre-trained models provide the zero-shot model achieving competitive performance across a range of image classification tasks without requiring training on downstream data. Recent works have confirmed…

The preservation and revitalization of endangered and extinct languages is a meaningful endeavor, conserving cultural heritage while enriching fields like linguistics and anthropology. However, these languages are typically low-resource,…

Automatic Speech Understanding (ASU) leverages the power of deep learning models for accurate interpretation of human speech, leading to a wide range of speech applications that enrich the human experience. However, training a robust ASU…

The problem of automatic accent identification is important for several applications like speaker profiling and recognition as well as for improving speech recognition systems. The accented nature of speech can be primarily attributed to…

Recognition of speech, and in particular the ability to generalize and learn from small sets of labelled examples like humans do, depends on an appropriate representation of the acoustic input. We formulate the problem of finding robust…