Related papers: Filterbank design for end-to-end speech separation

While numerous forecasters have been proposed using different network architectures, the Transformer-based models have state-of-the-art performance in time series forecasting. However, forecasters based on Transformers are still suffering…

We present an upper bound for the Single Channel Speech Separation task, which is based on an assumption regarding the nature of short segments of speech. Using the bound, we are able to show that while the recent methods have made…

State-of-the-art speaker diarization systems utilize knowledge from external data, in the form of a pre-trained distance metric, to effectively determine relative speaker identities to unseen data. However, much of recent focus has been on…

In this research, we advanced a spoken language recognition system, moving beyond traditional feature vector-based models. Our improvements focused on effectively capturing language characteristics over extended periods using a specialized…

End-to-end diarization presents an attractive alternative to standard cascaded diarization systems because a single system can handle all aspects of the task at once. Many flavors of end-to-end models have been proposed but all of them…

In recent years, deep learning-based single-channel speech separation has improved considerably, in large part driven by increasingly compute- and parameter-efficient neural network architectures. Most such architectures are, however,…

This work addresses the problem of speech separation in the Spanish Language using pre-trained deep learning models. As with many speech processing tasks, large databases in other languages different from English are scarce. Therefore this…

Recently, the research on ad-hoc microphone arrays with deep learning has drawn much attention, especially in speech enhancement and separation. Because an ad-hoc microphone array may cover such a large area that multiple speakers may…

Speaker identification systems in a real-world scenario are tasked to identify a speaker amongst a set of enrolled speakers given just a few samples for each enrolled speaker. This paper demonstrates the effectiveness of meta-learning and…

The constant Q transform (CQT) has been shown to be one of the most effective speech signal pre-transforms to facilitate synthetic speech detection, followed by either hand-crafted (subband) constant Q cepstral coefficient (CQCC) feature…

Speaker verification (SV) utilizing features obtained from models pre-trained via self-supervised learning has recently demonstrated impressive performances. However, these pre-trained models (PTMs) usually have a temporal resolution of 20…

Many approaches can derive information about a single speaker's identity from the speech by learning to recognize consistent characteristics of acoustic parameters. However, it is challenging to determine identity information when there are…

Deep dilated temporal convolutional networks (TCN) have been proved to be very effective in sequence modeling. In this paper we propose several improvements of TCN for end-to-end approach to monaural speech separation, which consists of 1)…

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…

The wide deployment of speech-based biometric systems usually demands high-performance speaker recognition algorithms. However, most of the prior works for speaker recognition either process the speech in the frequency domain or time…

To date, mainstream target speech separation (TSS) approaches are formulated to estimate the complex ratio mask (cRM) of the target speech in time-frequency domain under supervised deep learning framework. However, the existing deep models…

This paper proposes a delayed subband LSTM network for online monaural (single-channel) speech enhancement. The proposed method is developed in the short time Fourier transform (STFT) domain. Online processing requires frame-by-frame signal…

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…

Separation of competing speech is a key challenge in signal processing and a feat routinely performed by the human auditory brain. A long standing benchmark of the spectrogram approach to source separation is known as the ideal binary mask.…

Current state-of-the-art speech recognition systems build on recurrent neural networks for acoustic and/or language modeling, and rely on feature extraction pipelines to extract mel-filterbanks or cepstral coefficients. In this paper we…