相关论文: Online Spectrogram Inversion for Low-Latency Audio…

In this report we describe an ongoing line of research for solving single-channel source separation problems. Many monaural signal decomposition techniques proposed in the literature operate on a feature space consisting of a time-frequency…

In neural network-based monaural speech separation techniques, it has been recently common to evaluate the loss using the permutation invariant training (PIT) loss. However, the ordinary PIT requires to try all $N!$ permutations between $N$…

Considering a mixed signal composed of various audio sources and recorded with a single microphone, we consider on this paper the blind audio source separation problem which consists in isolating and extracting each of the sources. To…

This letter introduces an innovative method to enhance the quality of audio time stretching by precisely decomposing a sound into sines, transients, and noise and by improving the processing of the latter component. While there are…

In Gaussian model-based multichannel audio source separation, the likelihood of observed mixtures of source signals is parametrized by source spectral variances and by associated spatial covariance matrices. These parameters are estimated…

Speech separation has been very successful with deep learning techniques. Substantial effort has been reported based on approaches over spectrogram, which is well known as the standard time-and-frequency cross-domain representation for…

Blind source separation (BSS) is addressed, using a novel data-driven approach, based on a well-established probabilistic model. The proposed method is specifically designed for separation of multichannel audio mixtures. The algorithm…

Streaming recognition and segmentation of multi-party conversations with overlapping speech is crucial for the next generation of voice assistant applications. In this work we address its challenges discovered in the previous work on…

An ideal music synthesizer should be both interactive and expressive, generating high-fidelity audio in realtime for arbitrary combinations of instruments and notes. Recent neural synthesizers have exhibited a tradeoff between…

We consider the task of region-based source separation of reverberant multi-microphone recordings. We assume pre-defined spatial regions with a single active source per region. The objective is to estimate the signals from the individual…

In full-duplex systems, oscillator phase noise (PN) problem is considered the bottleneck challenge that may face the self-interference cancellation (SIC) stage especially when orthogonal frequency division multiplexing (OFDM) transmission…

A fundamental challenge in acoustic data processing is to separate a measured time series into relevant phenomenological components. A given measurement is typically assumed to be an additive mixture of myriad signals plus noise whose…

Orthogonal time sequency multiplexing (OTSM) has been recently proposed as a single-carrier waveform offering similar bit error rate to orthogonal time frequency space (OTFS) and outperforms orthogonal frequency division multiplexing (OFDM)…

Deep learning methods have brought substantial advancements in speech separation (SS). Nevertheless, it remains challenging to deploy deep-learning-based models on edge devices. Thus, identifying an effective way to compress these large…

Although supervised learning based on a deep neural network has recently achieved substantial improvement on speech enhancement, the existing schemes have either of two critical issues: spectrum or metric mismatches. The spectrum mismatch…

The recently-proposed mixture invariant training (MixIT) is an unsupervised method for training single-channel sound separation models in the sense that it does not require ground-truth isolated reference sources. In this paper, we…

Automatic lyrics transcription (ALT) remains a challenging task in the field of music information retrieval, despite great advances in automatic speech recognition (ASR) brought about by transformer-based architectures in recent years. One…

Typical high quality text-to-speech (TTS) systems today use a two-stage architecture, with a spectrum model stage that generates spectral frames and a vocoder stage that generates the actual audio. High-quality spectrum models usually…

We propose an audio-to-audio neural network model that learns to denoise old music recordings. Our model internally converts its input into a time-frequency representation by means of a short-time Fourier transform (STFT), and processes the…

Acoustic-to-articulatory inversion (AAI) is to obtain the movement of articulators from speech signals. Until now, achieving a speaker-independent AAI remains a challenge given the limited data. Besides, most current works only use audio…