Related papers: Context-Driven Dynamic Pruning for Large Speech Fo…

A computationally expensive and memory intensive neural network lies behind the recent success of language representation learning. Knowledge distillation, a major technique for deploying such a vast language model in resource-scarce…

Speech enhancement is a critical component of many user-oriented audio applications, yet current systems still suffer from distorted and unnatural outputs. While generative models have shown strong potential in speech synthesis, they are…

Most state-of-the-art models in natural language processing (NLP) are neural models built on top of large, pre-trained, contextual language models that generate representations of words in context and are fine-tuned for the task at hand.…

Large Language Models (LLMs) have achieved remarkable success in natural language processing tasks, but their massive size and computational demands hinder their deployment in resource-constrained environments. Existing model pruning…

We present an analysis of large-scale pretrained deep learning models used for cross-modal (text-to-audio) retrieval. We use embeddings extracted by these models in a metric learning framework to connect matching pairs of audio and text.…

This paper introduces the integration of language-specific bi-directional context into a speech large language model (SLLM) to improve multilingual continuous conversational automatic speech recognition (ASR). We propose a character-level…

Deep biasing improves automatic speech recognition (ASR) performance by incorporating contextual phrases. However, most existing methods enhance subwords in a contextual phrase as independent units, potentially compromising contextual…

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…

Children speech recognition is indispensable but challenging due to the diversity of children's speech. In this paper, we propose a filter-based discriminative autoencoder for acoustic modeling. To filter out the influence of various…

We propose a diffusion-based framework for prompt optimization that leverages Diffusion Language Models (DLMs) to iteratively refine system prompts through masked denoising. By conditioning on interaction traces, including user queries,…

Recently, the application of diffusion probabilistic models has advanced speech enhancement through generative approaches. However, existing diffusion-based methods have focused on the generation process in high-dimensional waveform or…

Diffusion probabilistic models have demonstrated an outstanding capability to model natural images and raw audio waveforms through a paired diffusion and reverse processes. The unique property of the reverse process (namely, eliminating…

Acoustics-to-word models are end-to-end speech recognizers that use words as targets without relying on pronunciation dictionaries or graphemes. These models are notoriously difficult to train due to the lack of linguistic knowledge. It is…

Existing research suggests that automatic speech recognition (ASR) models can benefit from additional contexts (e.g., contact lists, user specified vocabulary). Rare words and named entities can be better recognized with contexts. In this…

A primary challenge when deploying speaker recognition systems in real-world applications is performance degradation caused by environmental mismatch. We propose a diffusion-based method that takes speaker embeddings extracted from a…

Large Language Models (LLMs) have made significant progress in various downstream tasks, inspiring the development of Speech Understanding Language Models (SULMs) to enable comprehensive speech-based interactions. However, most advanced…

Large Language Model (LLM)-based agents are increasingly applied to tasks requiring structured reasoning, tool use, and environmental adaptation, such as data manipulation, multistep planning, and computer-use automation. However, despite…

Speaker recognition systems are often limited to classification tasks and struggle to generate detailed speaker characteristics or provide context-rich descriptions. These models primarily extract embeddings for speaker identification but…

When performing tasks like automatic speech recognition or spoken language understanding for a given utterance, access to preceding text or audio provides contextual information can improve performance. Considering the recent advances in…

Despite the significant improvements in speaker recognition enabled by deep neural networks, unsatisfactory performance persists under noisy environments. In this paper, we train the speaker embedding network to learn the "clean" embedding…