相关论文: Characterisation of speech diversity using self-or…

Current deep learning architectures show remarkable performance when trained in large-scale, controlled datasets. However, the predictive ability of these architectures significantly decreases when learning new classes incrementally. This…

We investigate the efficiency of two very different spoken term detection approaches for transcription when the available data is insufficient to train a robust ASR system. This work is grounded in very low-resource language documentation…

A methodology based upon recurrence quantification analysis is proposed for the study of orthographic structure of written texts. Five different orthographic data sets (20th century Italian poems, 20th century American poems, contemporary…

Collecting speech data is an important step in training speech recognition systems and other speech-based machine learning models. However, the issue of privacy protection is an increasing concern that must be addressed. The current study…

Language models provide a key framework for studying linguistic theories based on prediction, but phonological analysis using large language models (LLMs) is difficult; there are few phonological benchmarks beyond English and the standard…

Discrete representations of speech, obtained from Self-Supervised Learning (SSL) foundation models, are widely used, especially where there are limited data for the downstream task, such as for a low-resource language. Typically,…

The rapid advancement of speech generation technologies in the era of large language models (LLMs) has established discrete speech tokens as a foundational paradigm for speech representation. These tokens, characterized by their discrete,…

Recent adoption of deep learning methods to the field of machine lipreading research gives us two options to pursue to improve system performance. Either, we develop end-to-end systems holistically or, we experiment to further our…

Automated speaking assessment (ASA) typically involves automatic speech recognition (ASR) and hand-crafted feature extraction from the ASR transcript of a learner's speech. Recently, self-supervised learning (SSL) has shown stellar…

Despite recent availability of large transcribed Kinyarwanda speech data, achieving robust speech recognition for Kinyarwanda is still challenging. In this work, we show that using self-supervised pre-training, following a simple curriculum…

Auditory attention decoding (AAD) is a technique used to identify and amplify the talker that a listener is focused on in a noisy environment. This is done by comparing the listener's brainwaves to a representation of all the sound sources…

In this work, we propose a novel method for modeling numerous speakers, which enables expressing the overall characteristics of speakers in detail like a trained multi-speaker model without additional training on the target speaker's…

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…

Self-supervised speech models can be trained to efficiently recognize spoken words in naturalistic, noisy environments. However, we do not understand the types of linguistic representations these models use to accomplish this task. To…

In recent years, using raw waveforms as input for deep networks has been widely explored for the speaker verification system. For example, RawNet and RawNet2 extracted speaker's feature embeddings from waveforms automatically for…

The growing amount of data produced by simulations and observations of space physics processes encourages the use of methods rooted in Machine Learning for data analysis and physical discovery. We apply a clustering method based on…

Speaker verification (SV) systems are currently being used to make sensitive decisions like giving access to bank accounts or deciding whether the voice of a suspect coincides with that of the perpetrator of a crime. Ensuring that these…

Timbre is a set of perceptual attributes that identifies different types of sound sources. Although its definition is usually elusive, it can be seen from a signal processing viewpoint as all the spectral features that are perceived…

The computing power of mobile devices limits the end-user applications in terms of storage size, processing, memory and energy consumption. These limitations motivate researchers for the design of more efficient deep models. On the other…

Speaker attribution is required in many real-world applications, such as meeting transcription, where speaker identity is assigned to each utterance according to speaker voice profiles. In this paper, we propose to solve the speaker…