Related papers: Scaling strategies for on-device low-complexity so…
Recent research on the time-domain audio separation networks (TasNets) has brought great success to speech separation. Nevertheless, conventional TasNets struggle to satisfy the memory and latency constraints in industrial applications. In…
Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…
Recent speech enhancement models have shown impressive performance gains by scaling up model complexity and training data. However, the impact of dataset variability (e.g. text, language, speaker, and noise) has been underexplored.…
We present a work on low-complexity acoustic scene classification (ASC) with multiple devices, namely the subtask A of Task 1 of the DCASE2021 challenge. This subtask focuses on classifying audio samples of multiple devices with a…
The goal of speech separation is to extract multiple speech sources from a single microphone recording. Recently, with the advancement of deep learning and availability of large datasets, speech separation has been formulated as a…
Time-domain audio separation network (TasNet) has achieved remarkable performance in blind source separation (BSS). Classic multi-channel speech processing framework employs signal estimation and beamforming. For example, Beam-TasNet links…
In this paper, we present Reshape Dimensions Network (ReDimNet), a novel neural network architecture for extracting utterance-level speaker representations. Our approach leverages dimensionality reshaping of 2D feature maps to 1D signal…
This paper targets a new scenario that integrates speech separation with speech compression, aiming to disentangle multiple speakers while producing discrete representations for efficient transmission or storage, with applications in online…
This paper proposes a neural network based speech separation method using spatially distributed microphones. Unlike with traditional microphone array settings, neither the number of microphones nor their spatial arrangement is known in…
Diffusion models, emerging as powerful deep generative tools, excel in various applications. They operate through a two-steps process: introducing noise into training samples and then employing a model to convert random noise into new…
In this paper, we investigate distillation and pruning methods to reduce model size for non-intrusive speech quality assessment based on self-supervised representations. Our experiments build on XLS-R-SQA, a speech quality assessment model…
Speaker Recognition and Speaker Identification are challenging tasks with essential applications such as automation, authentication, and security. Deep learning approaches like SincNet and AM-SincNet presented great results on these tasks.…
The end-to-end approach for single-channel speech separation has been studied recently and shown promising results. This paper extended the previous approach and proposed a new end-to-end model for multi-channel speech separation. The…
Compressing resource-intensive large language models by removing whole transformer blocks is a seemingly simple idea, but identifying which blocks to remove constitutes an exponentially difficult combinatorial problem. In this paper, we…
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…
This paper introduces an area-based source separation method designed for virtual meeting scenarios. The aim is to preserve speech signals from an unspecified number of sources within a defined spatial area in front of a linear microphone…
Factors that limit the size of the input and output of a neural network include memory requirements for the network states/activations to compute gradients, as well as memory for the convolutional kernels or other weights. The memory…
Quantization-Aware Training from scratch has emerged as a promising approach for building efficient large language models (LLMs) with extremely low-bit weights (sub 2-bit), which can offer substantial advantages for edge deployment.…
Recently, deep clustering (DPCL) based speaker-independent speech separation has drawn much attention, since it needs little speaker prior information. However, it still has much room of improvement, particularly in reverberant…
In multi-speaker scenarios, leveraging spatial features is essential for enhancing target speech. While with limited microphone arrays, developing a compact multi-channel speech enhancement system remains challenging, especially in…