Related papers: Phoneme Recognition through Fine Tuning of Phoneti…

Conventional text-to-speech (TTS) research has predominantly focused on enhancing the quality of synthesized speech for speakers in the training dataset. The challenge of synthesizing lifelike speech for unseen, out-of-dataset speakers,…

We consider the problem of detecting, isolating and classifying elephant calls in continuously recorded audio. Such automatic call characterisation can assist conservation efforts and inform environmental management strategies. In contrast…

This paper summarizes the JHU team's efforts in tracks 1 and 2 of the CHiME-6 challenge for distant multi-microphone conversational speech diarization and recognition in everyday home environments. We explore multi-array processing…

Recent advancements in machine learning have significantly improved speech recognition, but recognizing speech from non-fluent or accented speakers remains a challenge. Previous efforts, relying on rule-based pronunciation patterns, have…

The idea of combining multiple languages' recordings to train a single automatic speech recognition (ASR) model brings the promise of the emergence of universal speech representation. Recently, a Transformer encoder-decoder model has been…

Training a conventional automatic speech recognition (ASR) system to support multiple languages is challenging because the sub-word unit, lexicon and word inventories are typically language specific. In contrast, sequence-to-sequence models…

Automatic Speech Recognition (ASR) for Bengali, the world's fifth most spoken language, remains a significant challenge, critically hindering technological accessibility for its over 270 million speakers. This challenge is compounded by two…

This paper investigates different pretraining approaches to spoken language identification. The paper is based on our submission to the Oriental Language Recognition 2021 Challenge. We participated in two tracks of the challenge:…

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…

Intent Recognition and Slot Identification are crucial components in spoken language understanding (SLU) systems. In this paper, we present a novel approach towards both these tasks in the context of low resourced and unwritten languages.…

Multilingual Large Language Models (LLMs) often provide suboptimal performance on low-resource languages like Urdu. This paper introduces UrduLLaMA 1.0, a model derived from the open-source Llama-3.1-8B-Instruct architecture and continually…

Language is inherent and compulsory for human communication. Whether expressed in a written or spoken way, it ensures understanding between people of the same and different regions. With the growing awareness and effort to include more…

In the traditional cascading architecture for spoken language understanding (SLU), it has been observed that automatic speech recognition errors could be detrimental to the performance of natural language understanding. End-to-end (E2E) SLU…

We present the first systematic study of machine translation for Chakma, an endangered and extremely low-resource Indo-Aryan language, with the goal of supporting language access and preservation. We introduce a new Chakma-Bangla parallel…

Despite advancements in speech recognition, accented speech remains challenging. While previous approaches have focused on modeling techniques or creating accented speech datasets, gathering sufficient data for the multitude of accents,…

We present a novel Automatic Speech Recognition (ASR) dataset for the Oromo language, a widely spoken language in Ethiopia and neighboring regions. The dataset was collected through a crowd-sourcing initiative, encompassing a diverse range…

Speech technology systems struggle with many downstream tasks for child speech due to small training corpora and the difficulties that child speech pose. We apply a novel dataset, SpeechMaturity, to state-of-the-art transformer models to…

Transformer based end-to-end modelling approaches with multiple stream inputs have been achieved great success in various automatic speech recognition (ASR) tasks. An important issue associated with such approaches is that the intermediate…

The rapid proliferation of Large Language Models (LLMs) has created a profound digital divide, effectively excluding indigenous languages of the Global South from the AI revolution. The Tharu language, an Indo-Aryan vernacular spoken by…

Traditionally, the performance of non-native mispronunciation verification systems relied on effective phone-level labelling of non-native corpora. In this study, a multi-view approach is proposed to incorporate discriminative feature…