Related papers: Extreme Audio Time Stretching Using Neural Synthes…
Many state-of-the-art signal decomposition techniques rely on a low-rank factorization of a time-frequency (t-f) transform. In particular, nonnegative matrix factorization (NMF) of the spectrogram has been considered in many audio…
This paper proposes speaker-adaptive neural vocoders for parametric text-to-speech (TTS) systems. Recently proposed WaveNet-based neural vocoding systems successfully generate a time sequence of speech signal with an autoregressive…
Extracting the speech of a target speaker from mixed audios, based on a reference speech from the target speaker, is a challenging yet powerful technology in speech processing. Recent studies of speaker-independent speech separation, such…
Speaker extraction is to extract a target speaker's voice from multi-talker speech. It simulates humans' cocktail party effect or the selective listening ability. The prior work mostly performs speaker extraction in frequency domain, then…
Complex-valued processing has brought deep learning-based speech enhancement and signal extraction to a new level. Typically, the process is based on a time-frequency (TF) mask which is applied to a noisy spectrogram, while complex masks…
Deep neural network (DNN)-based speech enhancement algorithms in microphone arrays have now proven to be efficient solutions to speech understanding and speech recognition in noisy environments. However, in the context of ad-hoc microphone…
Time Scale Modification (TSM) is a well-researched field; however, no effective objective measure of quality exists. This paper details the creation, subjective evaluation, and analysis of a dataset for use in the development of an…
Feature mapping using deep neural networks is an effective approach for single-channel speech enhancement. Noisy features are transformed to the enhanced ones through a mapping network and the mean square errors between the enhanced and…
This paper introduces a novel method to separate noisy speech into low or high frequency frames, in order to improve fundamental frequency (F0) estimation accuracy. In this proposal, the target signal is analyzed by means of the ensemble…
Historically, most speech models in machine-learning have used the mel-spectrogram as a speech representation. Recently, discrete audio tokens produced by neural audio codecs have become a popular alternate speech representation for speech…
In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…
Modern neural network-based speech processing systems usually need to have reverberation resistance, so the training of such systems requires a large amount of reverberation data. In the process of system training, it is now more inclined…
In recent decades, neural network based methods have significantly improved the performace of speech enhancement. Most of them estimate time-frequency (T-F) representation of target speech directly or indirectly, then resynthesize waveform…
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…
Transformers and State-Space Models (SSMs) have advanced audio classification by modeling spectrograms as sequences of patches. However, existing models such as the Audio Spectrogram Transformer (AST) and Audio Mamba (AuM) adopt square…
End-to-end model, especially Recurrent Neural Network Transducer (RNN-T), has achieved great success in speech recognition. However, transducer requires a great memory footprint and computing time when processing a long decoding sequence.…
Transient loud intrusions, often occurring in noisy environments, can completely overpower speech signal and lead to an inevitable loss of information. While existing algorithms for noise suppression can yield impressive results, their…
The traditional adaptive algorithms will face the non-uniqueness problem when dealing with stereophonic acoustic echo cancellation (SAEC). In this paper, we first propose an efficient multi-input and multi-output (MIMO) scheme based on deep…
This paper proposes singing voice synthesis (SVS) based on frame-level sequence-to-sequence models considering vocal timing deviation. In SVS, it is essential to synchronize the timing of singing with temporal structures represented by…
Recent advancements in speaker verification techniques show promise, but their performance often deteriorates significantly in challenging acoustic environments. Although speech enhancement methods can improve perceived audio quality, they…