Related papers: Stuttering-Aware Automatic Speech Recognition for …

Question Answering (QA) has seen significant improvements with the advancement of machine learning models, further studies enhanced this question answering system by retrieving external information, called Retrieval-Augmented Generation…

When the amount of parallel sentences available to train a neural machine translation is scarce, a common practice is to generate new synthetic training samples from them. A number of approaches have been proposed to produce synthetic…

In this work, we present our submission to the Speech Accessibility Project challenge for dysarthric speech recognition. We integrate parameter-efficient fine-tuning with latent audio representations to improve an encoder-decoder ASR…

To train transcriptor models that produce robust results, a large and diverse labeled dataset is required. Finding such data with the necessary characteristics is a challenging task, especially for languages less popular than English.…

Modern speech synthesis systems have improved significantly, with synthetic speech being indistinguishable from real speech. However, efficient and holistic evaluation of synthetic speech still remains a significant challenge. Human…

Disentangled representation learning in speech processing has lagged behind other domains, largely due to the lack of datasets with annotated generative factors for robust evaluation. To address this, we propose SynSpeech, a novel…

Automatic Speech Recognition (ASR) systems often struggle with transcribing child speech due to the lack of large child speech datasets required to accurately train child-friendly ASR models. However, there are huge amounts of annotated…

While recent text to speech (TTS) models perform very well in synthesizing reading-style (e.g., audiobook) speech, it is still challenging to synthesize spontaneous-style speech (e.g., podcast or conversation), mainly because of two…

Automated speaking assessment (ASA) on opinion expressions is often hampered by the scarcity of labeled recordings, which restricts prompt diversity and undermines scoring reliability. To address this challenge, we propose a novel training…

Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…

We consider the problem of recognizing speech utterances spoken to a device which is generating a known sound waveform; for example, recognizing queries issued to a digital assistant which is generating responses to previous user inputs.…

We introduce a sophisticated multi-speaker speech data simulator, specifically engineered to generate multi-speaker speech recordings. A notable feature of this simulator is its capacity to modulate the distribution of silence and overlap…

End-to-end models are an attractive new approach to spoken language understanding (SLU) in which the meaning of an utterance is inferred directly from the raw audio without employing the standard pipeline composed of a separately trained…

Making use of off-the-shelf resources of resource-rich languages to transfer knowledge for low-resource languages raises much attention recently. The requirements of enabling the model to reach the reliable performance lack well guided,…

Silent Speech Interfaces (SSIs) have gained attention for their ability to generate intelligible speech from non-acoustic signals. While significant progress has been made in advancing speech generation pipelines, limited work has addressed…

Disordered speech recognition is a highly challenging task. The underlying neuro-motor conditions of people with speech disorders, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large…

End-to-end automatic speech recognition often degrades on domain-specific data due to scarce in-domain resources. We propose a synthetic-data-based domain adaptation framework with two contributions: (1) a large language model (LLM)-based…

Automatic speech recognition (ASR) is a crucial tool for linguists aiming to perform a variety of language documentation tasks. However, modern ASR systems use data-hungry transformer architectures, rendering them generally unusable for…

Automatic speech recognition (ASR) for conversational code-switching speech remains challenging due to the scarcity of realistic, high-quality labeled speech data. This paper explores multilingual text-to-speech (TTS) models as an effective…

The evaluation of audio fingerprinting at a realistic scale is limited by the scarcity of large public music databases. We present an audio-free approach that synthesises latent fingerprints which approximate the distribution of real…