27 accepted papers
Despite recent breakthroughs, audio foundation models struggle in processing complex multi-source acoustic scenes. We refer to this challenging domain as audio stories, which can have multiple speakers and background/foreground sound effects. Compared to traditional audio processing tasks, audio sto…
Real-world speech recordings suffer from degradations such as background noise and reverberation. Speech enhancement aims to mitigate these issues by generating clean high-fidelity signals. While recent generative approaches for speech enhancement have shown promising results, they still face two ma…
The recent advancement of Artificial Intelligence Generated Content (AIGC) has led to significant strides in modeling human interaction, particularly in the context of multi-modal dialogue. While current methods impressively generates realistic dialogue in speech and vision modalities, challenges r…
Blind room impulse response (RIR) estimation is a core task for capturing and transferring acoustic properties; yet existing methods often suffer from limited modeling capability and degraded performance under unseen conditions. Moreover, emerging generative audio applications call for more flexible…
Recent breakthroughs in language-queried audio source separation (LASS) have shown that generative models can achieve higher separation audio quality than traditional masking-based approaches. However, two key limitations restrict their practical use: (1) users often require operations beyond separa…
While generative Text-to-Speech (TTS) systems leverage vast "in-the-wild" data to achieve remarkable success, speech-to-speech processing tasks like enhancement face data limitations, which lead data-hungry generative approaches to distort speech content and speaker identity. To bridge this gap, we…
Neural codecs have demonstrated strong performance in high-fidelity compression of audio signals at low bitrates. The token-based representations produced by these codecs have proven particularly useful for generative modeling. While much research has focused on improvements in compression ratio and…
Diffusion models have demonstrated significant potential in speech synthesis tasks, including text-to-speech (TTS) and voice cloning. However, their iterative denoising processes are computationally intensive, and previous distillation attempts have shown consistent quality degradation. Moreover, ex…
We propose a unified framework for Singing Voice Synthesis (SVS) and Conversion (SVC), addressing the limitations of existing approaches in cross-domain SVS/SVC, poor output musicality, and scarcity of singing data. Our framework enables control over multiple aspects, including language content base…
Large Vision-Language Models (LVLMs) often produce responses that misalign with factual information, a phenomenon known as hallucinations. While hallucinations are well-studied, the exact causes behind them remain underexplored. In this paper, we first investigate the root causes of hallucinations i…
Instruction Tuning (IT), the process of training large language models (LLMs) using instruction-response pairs, has emerged as the predominant method for transforming base pre-trained LLMs into open-domain conversational agents. While IT has achieved notable success and widespread adoption, its limi…
Research in generative self-supervised learning (SSL) has largely focused on local embeddings for tokenized sequences. We introduce a generative SSL framework that learns a global representation that is disentangled from local embeddings. We apply this technique to jointly learn a global speaker emb…
Audio source separation aims to extract individual sound sources from an audio mixture. Recent studies on source separation focus primarily on minimizing signal-level distance, typically measured by source-to-distortion ratio (SDR). However, scant attention has been given to the perceptual quality o…
High-quality speech synthesis models may be used to spread misinformation or impersonate voices. Audio watermarking can combat misuse by embedding a traceable signature in generated audio. However, existing audio watermarks typically demonstrate robustness to only a small set of transformations of t…
Speech representation learning transforms speech into features that are suitable for downstream tasks, e.g. speech recognition, phoneme classification, or speaker identification. For such recognition tasks, a representation can be lossy (non-invertible), which is typical of BERT-like self-supervised…
Consumer-grade music recordings such as those captured by mobile devices typically contain distortions in the form of background noise, reverb, and microphone-induced EQ. This paper presents a deep learning approach to enhance low-quality music recordings by combining (i) an image-to-image translati…
Automatic speech quality assessment remains challenging, as we lack complete models of human auditory perception. Many existing full-reference models correlate well with human perception, but cannot be used in real-world scenarios where ground truth clean reference recordings are not available. On t…
Speech generation and enhancement have seen recent breakthroughs in quality thanks to deep learning. These methods typically operate at a limited sampling rate of 16-22kHz due to computational complexity and available datasets. This limitation imposes a gap between the output of such methods and tha…
Many speech processing methods based on deep learning require an automatic and differentiable audio metric for the loss function. The DPAM approach of Manocha et al. [1] learns a full-reference metric trained directly on human judgments, and thus correlates well with human perception. However, it re…
Text-based speech editors expedite the process of editing speech recordings by permitting editing via intuitive cut, copy, and paste operations on a speech transcript. A major drawback of current systems, however, is that edited recordings often sound unnatural because of prosody mismatches around e…
The goal of acoustic matching is to transform an audio recording made in one acoustic environment to sound as if it had been recorded in a different environment, based on reference audio from the target environment. This paper introduces a deep learning solution for two parts of the acoustic matchin…
Music similarity search is useful for a variety of creative tasks such as replacing one music recording with another recording with a similar "feel", a common task in video editing. For this task, it is typically necessary to define a similarity metric to compare one recording to another. Music simi…
Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Many style-transfer-inspired methods such as generative adversarial networks (GANs) and variational autoencoders (VAEs) have been proposed. Recently, AutoVC, a conditional autoencoders (CAEs) ba…
We introduce a perceptually motivated approach to bandwidth expansion for speech. Our method pairs a new 3-way split variant of the FFTNet neural vocoder structure with a perceptual loss function, combining objectives from both the time and frequency domains. Mean opinion score tests show that it ou…
This paper introduces a deep learning approach to enhance speech recordings made in a specific environment. A single neural network learns to ameliorate several types of recording artifacts, including noise, reverberation, and non-linear equalization. The method relies on a new perceptual loss funct…
We introduce FFTNet, a deep learning approach synthesizing audio waveforms. Our approach builds on the recent WaveNet project, which showed that it was possible to synthesize a natural sounding audio waveform directly from a deep convolutional neural network. FFTNet offers two improvements over Wave…
State-of-the art voice conversion methods re-synthesize voice from spectral representations such as MFCCs and STRAIGHT, thereby introducing muffled artifacts. We propose a method that circumvents this concern using concatenative synthesis coupled with exemplar-based unit selection. Given parallel sp…