相关论文: Towards Hierarchical Spoken Language Dysfluency Mo…

Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the…

How to obtain hierarchical representations with an increasing level of abstraction becomes one of the key issues of learning with deep neural networks. A variety of RNN models have recently been proposed to incorporate both explicit and…

We introduce machine unlearning for speech tasks, a novel and underexplored research problem that aims to efficiently and effectively remove the influence of specific data from trained speech models without full retraining. This has…

Disfluency detection is a critical task in real-time dialogue systems. However, despite its importance, it remains a relatively unexplored field, mainly due to the lack of appropriate datasets. At the same time, existing datasets suffer…

Disfluencies are a natural feature of spontaneous human speech but are typically absent from the outputs of Large Language Models (LLMs). This absence can diminish the perceived naturalness of synthesized speech, which is an important…

This paper presents a new approach for classification of dysfluent and fluent speech using Mel-Frequency Cepstral Coefficient (MFCC). The speech is fluent when person's speech flows easily and smoothly. Sounds combine into syllable,…

Although considerable effort has been dedicated to improving the solution to the hyperspectral unmixing problem, non-idealities such as complex radiation scattering and endmember variability negatively impact the performance of most…

Automatic detection of hate and abusive language is essential to combat its online spread. Moreover, recognising and explaining hate speech serves to educate people about its negative effects. However, most current detection models operate…

A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history - thus enabling the…

(Short version of Abstract) This thesis describes an investigation on unsupervised acoustic modeling (UAM) for automatic speech recognition (ASR) in the zero-resource scenario, where only untranscribed speech data is assumed to be…

Large Language Models (LLMs) are increasingly integrated into real-world applications, raising concerns about privacy, security and the need to remove undesirable knowledge. Machine Unlearning has emerged as a promising solution, yet faces…

Homonyms are words with identical spelling but distinct meanings, which pose challenges for many generative models. When a homonym appears in a prompt, diffusion models may generate multiple senses of the word simultaneously, which is known…

Discrete Diffusion Language Models progressed rapidly as an alternative to autoregressive (AR) models, motivated by their parallel generation abilities. However, for tractability, discrete diffusion models sample from a factorized…

Stuttering is a speech disorder during which the flow of speech is interrupted by involuntary pauses and repetition of sounds. Stuttering identification is an interesting interdisciplinary domain research problem which involves pathology,…

Stutter removal is an essential scenario in the field of speech editing. However, when the speech recording contains stutters, the existing text-based speech editing approaches still suffer from: 1) the over-smoothing problem in the edited…

Diffusion language models (DLMs) are an attractive alternative to autoregressive models because they promise sublinear-time, parallel generation, yet practical gains remain elusive as high-quality samples still demand hundreds of refinement…

Text-to-Speech (TTS) models have advanced significantly, aiming to accurately replicate human speech's diversity, including unique speaker identities and linguistic nuances. Despite these advancements, achieving an optimal balance between…

Current de-facto dysfluency modeling methods utilize template matching algorithms which are not generalizable to out-of-domain real-world dysfluencies across languages, and are not scalable with increasing amounts of training data. To…

Recently, diffusion models have excelled in image generation tasks and have also been applied to neural language processing (NLP) for controllable text generation. However, the application of diffusion models in a cross-lingual setting is…

Transformer language models generate text autoregressively, making inference latency proportional to the number of tokens generated. Speculative decoding reduces this latency without sacrificing output quality, by leveraging a small draft…