相关论文: The Effect of Spoken Language on Speech Enhancemen…

Language-specific neurons in LLMs that strongly correlate with individual languages have been shown to influence model behavior by deactivating them. However, their role in amplification remains underexplored. This work investigates the…

Speech production is a complex phenomenon, wherein the brain orchestrates a sequence of processes involving thought processing, motor planning, and the execution of articulatory movements. However, this intricate execution of various…

In the context of mobile sensing environments, various sensors on mobile devices continually generate a vast amount of data. Analyzing this ever-increasing data presents several challenges, including limited access to annotated data and a…

Self-supervised learning representations (SSLR) have resulted in robust features for downstream tasks in many fields. Recently, several SSLRs have shown promising results on automatic speech recognition (ASR) benchmark corpora. However,…

Sentence Representation Learning (SRL) is a fundamental task in Natural Language Processing (NLP), with the Contrastive Learning of Sentence Embeddings (CSE) being the mainstream technique due to its superior performance. An intriguing…

In self-supervised learning for speaker recognition, pseudo labels are useful as the supervision signals. It is a known fact that a speaker recognition model doesn't always benefit from pseudo labels due to their unreliability. In this…

Although automatic speech recognition (ASR) task has gained remarkable success by sequence-to-sequence models, there are two main mismatches between its training and testing that might lead to performance degradation: 1) The typically used…

Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task…

Self-supervised learning has attracted plenty of recent research interest. However, most works for self-supervision in speech are typically unimodal and there has been limited work that studies the interaction between audio and visual…

Spoken language understanding (SLU) systems extract both text transcripts and semantics associated with intents and slots from input speech utterances. SLU systems usually consist of (1) an automatic speech recognition (ASR) module, (2) an…

We investigate the performance of self-supervised pretraining frameworks on pathological speech datasets used for automatic speech recognition (ASR). Modern end-to-end models require thousands of hours of data to train well, but only a…

Whispering is a distinct form of speech known for its soft, breathy, and hushed characteristics, often used for private communication. The acoustic characteristics of whispered speech differ substantially from normally phonated speech and…

The performance of deep neural network-based speech enhancement systems typically increases with the training dataset size. However, studies that investigated the effect of training dataset size on speech enhancement performance did not…

Diffusion-based generative models have recently gained attention in speech enhancement (SE), providing an alternative to conventional supervised methods. These models transform clean speech training samples into Gaussian noise centered at…

Text encodings from automatic speech recognition (ASR) transcripts and audio representations have shown promise in speech emotion recognition (SER) ever since. Yet, it is challenging to explain the effect of each information stream on the…

We propose SelfVC, a training strategy to iteratively improve a voice conversion model with self-synthesized examples. Previous efforts on voice conversion focus on factorizing speech into explicitly disentangled representations that…

Self-supervised representation learning approaches have grown in popularity due to the ability to train models on large amounts of unlabeled data and have demonstrated success in diverse fields such as natural language processing, computer…

Self-supervised speech representation learning (S3RL) is revolutionizing the way we leverage the ever-growing availability of data. While S3RL related studies typically use large models, we employ light-weight networks to comply with tight…

While many speakers of low-resource languages regularly code-switch between their languages and other regional languages or English, datasets of codeswitched speech are too small to train bespoke acoustic models from scratch or do language…

Audio and speech self-supervised encoder models are now widely used for a lot of different tasks. Many of these models are often trained on clean segmented speech content such as LibriSpeech. In this paper, we look into how the pretraining…