Search Results for author:
Found 19 papers, 10 papers with code
TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch
TorchAudio is an open-source audio and speech processing library built for PyTorch.
Neural Diarization with Non-autoregressive Intermediate Attractors
The experiments with the two-speaker CALLHOME dataset show that the intermediate labels with the proposed non-autoregressive intermediate attractors boost the diarization performance.
Diffusion-based Generative Speech Source Separation
We propose DiffSep, a new single channel source separation method based on score-matching of a stochastic differential equation (SDE).
ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding
To showcase such integration, we performed experiments on carefully designed synthetic datasets for noisy-reverberant multi-channel ST and SLU tasks, which can be used as benchmark corpora for future research.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
End-to-End Multi-speaker ASR with Independent Vector Analysis
We develop an end-to-end system for multi-channel, multi-speaker automatic speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Spatial Loss for Unsupervised Multi-channel Source Separation
With the proposed loss, we train the neural separators based on minimum variance distortionless response (MVDR) beamforming and independent vector analysis (IVA).
MLP-ASR: Sequence-length agnostic all-MLP architectures for speech recognition
We propose multi-layer perceptron (MLP)-based architectures suitable for variable length input.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Independence-based Joint Dereverberation and Separation with Neural Source Model
We introduce a neural network in the framework of time-decorrelation iterative source steering, which is an extension of independent vector analysis to joint dereverberation and separation.
SDR -- Medium Rare with Fast Computations
The complexity of this step is thus reduced by a factor quadratic in the distortion filter size used in bss eval, usually 512.
MLP-based architecture with variable length input for automatic speech recognition
We propose three approaches to extend MLP-based architectures for use with sequences of arbitrary length.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Refinement of Direction of Arrival Estimators by Majorization-Minimization Optimization on the Array Manifold
We propose a generalized formulation of direction of arrival estimation that includes many existing methods such as steered response power, subspace, coherent and incoherent, as well as speech sparsity-based methods.
Joint Dereverberation and Separation with Iterative Source Steering
In this case, we manage to reduce the number of matrix inversion to only one per iteration and source.
Surrogate Source Model Learning for Determined Source Separation
We find that the learnt approximate surrogate generalizes well on mixtures of three and four speakers without any modification.
Generalized Minimal Distortion Principle for Blind Source Separation
The method thus provides a cheap and easy way to boost the performance of blind source separation.
Audio and Speech Processing Sound Signal Processing
Independent Vector Analysis via Log-Quadratically Penalized Quadratic Minimization
Numerical experiments demonstrate the effectiveness of the proposed method.
Independent Vector Analysis with more Microphones than Sources
The performance of the algorithm is assessed on simulated signals.
Sound Audio and Speech Processing
Multi-modal Blind Source Separation with Microphones and Blinkies
We show that alternating updates similar to those of independent vector analysis and Itakura-Saito non-negative matrix factorization decrease the negative log-likelihood of the joint distribution.
Sound Audio and Speech Processing
Pyroomacoustics: A Python package for audio room simulations and array processing algorithms
We present pyroomacoustics, a software package aimed at the rapid development and testing of audio array processing algorithms.
Sound Audio and Speech Processing
A Fast Hadamard Transform for Signals with Sub-linear Sparsity in the Transform Domain
A new iterative low complexity algorithm has been presented for computing the Walsh-Hadamard transform (WHT) of an $N$ dimensional signal with a $K$-sparse WHT, where $N$ is a power of two and $K = O(N^\alpha)$, scales sub-linearly in $N$ for some $0 < \alpha < 1$.
