Related papers: MaskSR: Masked Language Model for Full-band Speech…

This paper proposes a unified deep speaker embedding framework for modeling speech data with different sampling rates. Considering the narrowband spectrogram as a sub-image of the wideband spectrogram, we tackle the joint modeling problem…

Deepfake speech detection presents a growing challenge as generative audio technologies continue to advance. We propose a hybrid training framework that advances detection performance through novel augmentation strategies. First, we…

Masked Language Models (MLMs) have proven to be effective for second-pass rescoring in Automatic Speech Recognition (ASR) systems. In this work, we propose Masked Audio Text Encoder (MATE), a multi-modal masked language model rescorer which…

Audio super-resolution is a fundamental task that predicts high-frequency components for low-resolution audio, enhancing audio quality in digital applications. Previous methods have limitations such as the limited scope of audio types…

Recent advancements in large language models (LLMs) have revolutionized various domains, bringing significant progress and new opportunities. Despite progress in speech-related tasks, LLMs have not been sufficiently explored in multi-talker…

In the past few years, it has been shown that deep learning systems are highly vulnerable under attacks with adversarial examples. Neural-network-based automatic speech recognition (ASR) systems are no exception. Targeted and untargeted…

Systems based on automatic speech recognition (ASR) technology can provide important functionality in computer assisted language learning applications. This is a young but growing area of research motivated by the large number of students…

Visual speech recognition (VSR) is the task of recognizing spoken language from video input only, without any audio. VSR has many applications as an assistive technology, especially if it could be deployed in mobile devices and embedded…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

In this work, we propose a new parameter-efficient learning framework based on neural model reprogramming for cross-lingual speech recognition, which can \textbf{re-purpose} well-trained English automatic speech recognition (ASR) models to…

Audio-visual speech recognition (AVSR) typically improves recognition accuracy in noisy environments by integrating noise-immune visual cues with audio signals. Nevertheless, high-noise audio inputs are prone to introducing adverse…

Existing Visual Speech Recognition (VSR) systems commonly rely on left-to-right autoregressive decoding, which can force premature decisions on visually ambiguous tokens before sufficient context is available. We propose DLLM-VSR, to the…

Vocoders received renewed attention as main components in statistical parametric text-to-speech (TTS) synthesis and speech transformation systems. Even though there are vocoding techniques give almost accepted synthesized speech, their high…

Transformer has been widely used for self-supervised pre-training in Natural Language Processing (NLP) and achieved great success. However, it has not been fully explored in visual self-supervised learning. Meanwhile, previous methods only…

The task of speech recognition in far-field environments is adversely affected by the reverberant artifacts that elicit as the temporal smearing of the sub-band envelopes. In this paper, we develop a neural model for speech dereverberation…

Speech enhancement algorithms based on deep learning have been improved in terms of speech intelligibility and perceptual quality greatly. Many methods focus on enhancing the amplitude spectrum while reconstructing speech using the mixture…

Recently, attention-based transformers have become a de facto standard in many deep learning applications including natural language processing, computer vision, signal processing, etc.. In this paper, we propose a transformer-based…

Speech restoration in real-world conditions is challenging due to compounded distortions and mismatches between input and desired output rates. Most existing systems assume a fixed and shared input-output rate, relying on external…

Phonotactic constraints can be employed to distinguish languages by representing a speech utterance as a multinomial distribution or phone events. In the present study, we propose a new learning mechanism based on subspace-based…

Most neural network speech enhancement models ignore speech production mathematical models by directly mapping Fourier transform spectrums or waveforms. In this work, we propose a neural source filter network for speech enhancement.…