Related papers: Mandarin Lombard Flavor Classification
Speaker adaptation aims to estimate a speaker specific acoustic model from a speaker independent one to minimize the mismatch between the training and testing conditions arisen from speaker variabilities. A variety of neural network…
Multiple studies have probed representations emerging in neural networks trained for end-to-end NLP tasks and examined what word-level linguistic information may be encoded in the representations. In classical probing, a classifier is…
Interpretability research has shown that self-supervised Spoken Language Models (SLMs) encode a wide variety of features in human speech from the acoustic, phonetic, phonological, syntactic and semantic levels, to speaker characteristics.…
This letter introduces a novel speech enhancement method in the Hilbert-Huang Transform domain to mitigate the effects of acoustic impulsive noises. The estimation and selection of noise components is based on the impulsiveness index of…
Research related to automatically detecting Alzheimer's disease (AD) is important, given the high prevalence of AD and the high cost of traditional methods. Since AD significantly affects the acoustics of spontaneous speech, speech…
Previous works on expressive speech synthesis focus on modelling the mono-scale style embedding from the current sentence or context, but the multi-scale nature of speaking style in human speech is neglected. In this paper, we propose a…
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…
The increased adoption of digital assistants makes text-to-speech (TTS) synthesis systems an indispensable feature of modern mobile devices. It is hence desirable to build a system capable of generating highly intelligible speech in the…
We introduce a simple and linear SNR (strictly speaking, periodic to random power ratio) estimator (0dB to 80dB without additional calibration/linearization) for providing reliable descriptions of aperiodicity in speech corpus. The main…
Recommender systems are crucial for personalizing user experiences but often depend on implicit feedback data, which can be noisy and misleading. Existing denoising studies involve incorporating auxiliary information or learning strategies…
The effect of hearing impairment on speech perception was described by Plomp (1978) as a sum of a loss of class A, due to signal attenuation, and a loss of class D, due to signal distortion. While a loss of class A can be compensated by…
Language Models (LMs) have shown impressive performance in various natural language tasks. However, when it comes to natural language reasoning, LMs still face challenges such as hallucination, generating incorrect intermediate reasoning…
One way to analyse the behaviour of machine learning models is through local explanations that highlight input features that maximally influence model predictions. Sensitivity analysis, which involves analysing the effect of input…
Speech-comprehension difficulties are common among older people. Standard speech tests do not fully capture such difficulties because the tests poorly resemble the context-rich, story-like nature of ongoing conversation and are typically…
A judicious combination of dictionary learning methods, block sparsity and source recovery algorithm are used in a hierarchical manner to identify the noises and the speakers from a noisy conversation between two people. Conversations are…
In this work, we propose the use of dropout as a Bayesian estimator for increasing the generalizability of a deep neural network (DNN) for speech enhancement. By using Monte Carlo (MC) dropout, we show that the DNN performs better…
Speech Large Language Models (SpeechLLMs) process spoken input directly, retaining cues such as accent and perceived gender that were previously removed in cascaded pipelines. This introduces speaker identity dependent variation in…
Large language models (LLMs) exhibit excellent ability to understand human languages, but do they also understand their own language that appears gibberish to us? In this work we delve into this question, aiming to uncover the mechanisms…
Deep neural network (DNN) based end-to-end optimization in the complex time-frequency (T-F) domain or time domain has shown considerable potential in monaural speech separation. Many recent studies optimize loss functions defined solely in…
This paper addresses the problem of multiclass classification with corrupted or noisy bandit feedback. In this setting, the learner may not receive true feedback. Instead, it receives feedback that has been flipped with some non-zero…