Search Results for author:
Found 26 papers, 7 papers with code
Neural Fast Full-Rank Spatial Covariance Analysis for Blind Source Separation
Our neural separation model introduced for AVI alternately performs neural network blocks and single steps of an efficient iterative algorithm called iterative source steering.
Neural Steerer: Novel Steering Vector Synthesis with a Causal Neural Field over Frequency and Source Positions
We address the problem of accurately interpolating measured anechoic steering vectors with a deep learning framework called the neural field.
DNN-Free Low-Latency Adaptive Speech Enhancement Based on Frame-Online Beamforming Powered by Block-Online FastMNMF
Our DNN-free system leverages the posteriors of the latest source spectrograms given by block-online FastMNMF to derive the current source covariance matrices for frame-online beamforming.
Direction-Aware Adaptive Online Neural Speech Enhancement with an Augmented Reality Headset in Real Noisy Conversational Environments
This paper describes the practical response- and performance-aware development of online speech enhancement for an augmented reality (AR) headset that helps a user understand conversations made in real noisy echoic environments (e. g., cocktail party).
Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments
This paper describes noisy speech recognition for an augmented reality headset that helps verbal communication within real multiparty conversational environments.
Ranked #1 on
Speech Enhancement
on EasyCom
(SDR metric)
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Generalized Fast Multichannel Nonnegative Matrix Factorization Based on Gaussian Scale Mixtures for Blind Source Separation
This paper describes heavy-tailed extensions of a state-of-the-art versatile blind source separation method called fast multichannel nonnegative matrix factorization (FastMNMF) from a unified point of view.
Global Structure-Aware Drum Transcription Based on Self-Attention Mechanisms
To mitigate the difficulty of training the self-attention-based model from an insufficient amount of paired data and improve the musical naturalness of the estimated scores, we propose a regularized training method that uses a global structure-aware masked language (score) model with a self-attention mechanism pretrained from an extensive collection of drum scores.
Tatum-Level Drum Transcription Based on a Convolutional Recurrent Neural Network with Language Model-Based Regularized Training
This paper describes a neural drum transcription method that detects from music signals the onset times of drums at the $\textit{tatum}$ level, where tatum times are assumed to be estimated in advance.
The MIDI Degradation Toolkit: Symbolic Music Augmentation and Correction
To that end, MDTK includes a script that measures the distribution of different types of errors in a transcription, and creates a degraded dataset with similar properties.
End-to-end Music-mixed Speech Recognition
The time-domain separation method outperformed a frequency-domain separation method, which reuses the phase information of the input mixture signal, both in simple cascading and joint training settings.
Audio and Speech Processing
Semi-supervised Neural Chord Estimation Based on a Variational Autoencoder with Latent Chord Labels and Features
In contrast, we propose a unified generative and discriminative approach in the framework of amortized variational inference.
MirrorNet: A Deep Bayesian Approach to Reflective 2D Pose Estimation from Human Images
Specifically, we formulate a hierarchical generative model of poses and images by integrating a deep generative model of poses from pose features with that of images from poses and image features.
Multi-Step Chord Sequence Prediction Based on Aggregated Multi-Scale Encoder-Decoder Network
In this paper, we postulate that this comes from the multi-scale structure of musical information and propose new architectures based on an iterative temporal aggregation of input labels.
Semi-Supervised Multichannel Speech Enhancement With a Deep Speech Prior
To solve this problem, we replace a low-rank speech model with a deep generative speech model, i. e., formulate a probabilistic model of noisy speech by integrating a deep speech model, a low-rank noise model, and a full-rank or rank-1 model of spatial characteristics of speech and noise.
Deep Bayesian Unsupervised Source Separation Based on a Complex Gaussian Mixture Model
This paper presents an unsupervised method that trains neural source separation by using only multichannel mixture signals.
Musical Rhythm Transcription Based on Bayesian Piece-Specific Score Models Capturing Repetitions
Focusing on rhythm, we formulate several classes of Bayesian Markov models of musical scores that describe repetitions indirectly using the sparse transition probabilities of notes or note patterns.
Statistical Learning and Estimation of Piano Fingering
We find that the methods based on high-order HMMs outperform the other methods in terms of estimation accuracies.
Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition
To solve this problem, we take an unsupervised approach that decomposes each TF bin into the sum of speech and noise by using multichannel nonnegative matrix factorization (MNMF).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Fast Multichannel Source Separation Based on Jointly Diagonalizable Spatial Covariance Matrices
A popular approach to multichannel source separation is to integrate a spatial model with a source model for estimating the spatial covariance matrices (SCMs) and power spectral densities (PSDs) of each sound source in the time-frequency domain.
A Deep Generative Model of Speech Complex Spectrograms
To improve the consistency of the phase values in the time-frequency domain, we also apply the von Mises distribution to the phase derivatives, i. e., the group delay and the instantaneous frequency.
Statistical Piano Reduction Controlling Performance Difficulty
We present a statistical-modelling method for piano reduction, i. e. converting an ensemble score into piano scores, that can control performance difficulty.
Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization
This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech.
Generative Statistical Models with Self-Emergent Grammar of Chord Sequences
Generative statistical models of chord sequences play crucial roles in music processing.
Note Value Recognition for Piano Transcription Using Markov Random Fields
This paper presents a statistical method for use in music transcription that can estimate score times of note onsets and offsets from polyphonic MIDI performance signals.
Rhythm Transcription of Polyphonic Piano Music Based on Merged-Output HMM for Multiple Voices
In a recent conference paper, we have reported a rhythm transcription method based on a merged-output hidden Markov model (HMM) that explicitly describes the multiple-voice structure of polyphonic music.
