Related papers: Audio Time-Scale Modification with Temporal Compre…
Audio-LLM introduces audio modality into a large language model (LLM) to enable a powerful LLM to recognize, understand, and generate audio. However, during speech recognition in noisy environments, we observed the presence of illusions and…
Existing audio analysis methods generally first transform the audio stream to spectrogram, and then feed it into CNN for further analysis. A standard CNN recognizes specific visual patterns over feature map, then pools for high-level…
Neural speech codecs have been widely used in audio compression and various downstream tasks. Current mainstream codecs are fixed-frame-rate (FFR), which allocate the same number of tokens to every equal-duration slice. However, speech is…
Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss. Previous work has overcome these issues by using convolutional networks to learn long-range…
This paper introduces a novel technique for reconstructing the phase of modified spectrograms of audio signals. From the analysis of mixtures of sinusoids we obtain relationships between phases of successive time frames in the…
Robustness against temporal variations is important for emotion recognition from speech audio, since emotion is ex-pressed through complex spectral patterns that can exhibit significant local dilation and compression on the time axis…
Large Audio Language Models (LALMs) demonstrate impressive performance across diverse tasks, ranging from speech recognition to general audio understanding. However, their scalability is limited by the quadratic complexity of attention and…
Large Audio-Language Models (LALMs) enable general audio understanding and demonstrate remarkable performance across various audio tasks. However, these models still face challenges in temporal perception (e.g., inferring event onset and…
Recent successful applications of convolutional neural networks (CNNs) to audio classification and speech recognition have motivated the search for better input representations for more efficient training. Visual displays of an audio…
In recent years, deep learning-based approaches have significantly improved the performance of single-channel speech enhancement. However, due to the limitation of training data and computational complexity, real-time enhancement of…
Bandwidth extension, the task of reconstructing the high-frequency components of an audio signal from its low-pass counterpart, is a long-standing problem in audio processing. While traditional approaches have evolved alongside the broader…
Time-Scale Modification (TSM) of speech aims to alter the playback rate of audio without changing its pitch. While classical methods like Waveform Similarity-based Overlap-Add (WSOLA) provide strong baselines, they often introduce artifacts…
This paper investigates the optimization of Truncated Backpropagation Through Time (TBPTT) for training neural networks in digital audio effect modeling, with a focus on dynamic range compression. The study evaluates key TBPTT…
In this paper, we propose a novel time-frequency joint learning method for speech emotion recognition, called Time-Frequency Transformer. Its advantage is that the Time-Frequency Transformer can excavate global emotion patterns in the…
One key step in audio signal processing is to transform the raw signal into representations that are efficient for encoding the original information. Traditionally, people transform the audio into spectral representations, as a function of…
We introduce a new audio processing technique that increases the sampling rate of signals such as speech or music using deep convolutional neural networks. Our model is trained on pairs of low and high-quality audio examples; at test-time,…
We present a transformer-based speech-declipping model that effectively recovers clipped signals across a wide range of input signal-to-distortion ratios (SDRs). While recent time-domain deep neural network (DNN)-based declippers have…
Transformers have drawn attention in the MIR field for their remarkable performance shown in natural language processing and computer vision. However, prior works in the audio processing domain mostly use Transformer as a temporal feature…
In recent years, machine learning approaches to modelling guitar amplifiers and effects pedals have been widely investigated and have become standard practice in some consumer products. In particular, recurrent neural networks (RNNs) are a…
Neural autoencoders underpin generative models. Practical, large-scale use of neural autoencoders for generative modeling necessitates fast encoding, low latent rates, and a single model across representations. Existing approaches are…