相关论文: SAGA-SR: Semantically and Acoustically Guided Audi…

Automatic Speech Scoring (ASS) is the computer-assisted evaluation of a candidate's speaking proficiency in a language. ASS systems face many challenges like open grammar, variable pronunciations, and unstructured or semi-structured…

This study presents a new image super-resolution (SR) technique based on diffusion inversion, aiming at harnessing the rich image priors encapsulated in large pre-trained diffusion models to improve SR performance. We design a Partial noise…

Audio deepfake detection has become increasingly challenging due to rapid advances in speech synthesis and voice conversion technologies, particularly under channel distortions, replay attacks, and real-world recording conditions. This…

Automatic speech recognition (ASR) has been widely researched with supervised approaches, while many low-resourced languages lack audio-text aligned data, and supervised methods cannot be applied on them. In this work, we propose a…

One common approach for question answering over speech data is to first transcribe speech using automatic speech recognition (ASR) and then employ text-based retrieval-augmented generation (RAG) on the transcriptions. While this cascaded…

Data augmentation is vital to the generalization ability and robustness of deep neural networks (DNNs) models. Existing augmentation methods for speaker verification manipulate the raw signal, which are time-consuming and the augmented…

The rich textual information of large vision-language models (VLMs) combined with the powerful generative prior of pre-trained text-to-image (T2I) diffusion models has achieved impressive performance in single-image super-resolution (SISR).…

Pre-trained models for automatic speech recognition (ASR) and speech enhancement (SE) have exhibited remarkable capabilities under matched noise and channel conditions. However, these models often suffer from severe performance degradation…

Automatic Speech Recognition (ASR) systems must be robust to the myriad types of noises present in real-world environments including environmental noise, room impulse response, special effects as well as attacks by malicious actors…

Dysarthric speech reconstruction (DSR) aims to transform dysarthric speech into normal speech by improving the intelligibility and naturalness. This is a challenging task especially for patients with severe dysarthria and speaking in…

Singing voice synthesis (SVS) systems are built to synthesize high-quality and expressive singing voice, in which the acoustic model generates the acoustic features (e.g., mel-spectrogram) given a music score. Previous singing acoustic…

Speech super-resolution (SSR) aims to predict a high resolution (HR) speech signal from its low resolution (LR) corresponding part. Most neural SSR models focus on producing the final result in a noise-free environment by recovering the…

Current audio language models are predominantly text-first, either extending pre-trained text LLM backbones or relying on semantic-only audio tokens, limiting general audio modeling. This paper presents a systematic empirical study of…

Automatic Speech Recognition (ASR) for adults' speeches has made significant progress by employing deep neural network (DNN) models recently, but improvement in children's speech is still unsatisfactory due to children's speech's distinct…

Speech super-resolution (SR), which generates a waveform at a higher sampling rate from its low-resolution version, is a long-standing critical task in speech restoration. Previous works have explored speech SR in different data spaces, but…

Large Language Models (LLMs) have recently shown remarkable ability to process not only text but also multimodal inputs such as speech and audio. However, most existing models primarily focus on analyzing input signals using text…

State-of-the-art (SOTA) Automatic Speech Recognition (ASR) systems primarily rely on acoustic information while disregarding additional multi-modal context. However, visual information are essential in disambiguation and adaptation. While…

General audio source separation is a key capability for multimodal AI systems that can perceive and reason about sound. Despite substantial progress in recent years, existing separation models are either domain-specific, designed for fixed…

Singing voice synthesis (SVS) aims to produce high-fidelity singing audio from music scores, requiring a detailed understanding of notes, pitch, and duration, unlike text-to-speech tasks. Although diffusion models have shown exceptional…

With the widespread application of automatic speech recognition (ASR) systems, their vulnerability to adversarial attacks has been extensively studied. However, most existing adversarial examples are generated on specific individual models,…