Related papers: TSTNN: Two-stage Transformer based Neural Network …

Speaker diarization is connected to semantic segmentation in computer vision. Inspired from MaskFormer \cite{cheng2021per} which treats semantic segmentation as a set-prediction problem, we propose an end-to-end approach to predict a set of…

The rising interest in single-channel multi-speaker speech separation sparked development of End-to-End (E2E) approaches to multi-speaker speech recognition. However, up until now, state-of-the-art neural network-based time domain source…

In recent years, neural network based methods for multi-speaker text-to-speech synthesis (TTS) have made significant progress. However, the current speaker encoder models used in these methods still cannot capture enough speaker…

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…

Recently, deep learning-based beamforming algorithms have shown promising performance in target speech extraction tasks. However, most systems do not fully utilize spatial information. In this paper, we propose a target speech extraction…

This paper proposes a novel neural denoising vocoder that can generate clean speech waveforms from noisy mel-spectrograms. The proposed neural denoising vocoder consists of two components, i.e., a spectrum predictor and a enhancement…

End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the…

Reconstructing natural speech from neural activity is vital for enabling direct communication via brain-computer interfaces. Previous efforts have explored the conversion of neural recordings into speech using complex deep neural network…

In ICASSP 2023 speech signal improvement challenge, we developed a dual-stage neural model which improves speech signal quality induced by different distortions in a stage-wise divide-and-conquer fashion. Specifically, in the first stage,…

From hearing aids to augmented and virtual reality devices, binaural speech enhancement algorithms have been established as state-of-the-art techniques to improve speech intelligibility and listening comfort. In this paper, we present an…

Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of…

We study the use of the Wave-U-Net architecture for speech enhancement, a model introduced by Stoller et al for the separation of music vocals and accompaniment. This end-to-end learning method for audio source separation operates directly…

In speech separation, time-domain approaches have successfully replaced the time-frequency domain with latent sequence feature from a learnable encoder. Conventionally, the feature is separated into speaker-specific ones at the final stage…

Sequence-to-sequence models have been widely used in end-to-end speech processing, for example, automatic speech recognition (ASR), speech translation (ST), and text-to-speech (TTS). This paper focuses on an emergent sequence-to-sequence…

This paper presents a novel streaming end-to-end target-speaker speech recognition that addresses two critical limitations in systems: the handling of noisy enrollment utterances and specific enrollment phrase requirements. This paper…

We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST). Our models are based on the original Transformer architecture (Vaswani et…

Deep neural network (DNN)-based speech enhancement algorithms in microphone arrays have now proven to be efficient solutions to speech understanding and speech recognition in noisy environments. However, in the context of ad-hoc microphone…

While most deployed speech recognition systems today still run on servers, we are in the midst of a transition towards deployments on edge devices. This leap to the edge is powered by the progression from traditional speech recognition…

This paper proposes a dual-stage, low complexity, and reconfigurable technique to enhance the speech contaminated by various types of noise sources. Driven by input data and audio contents, the proposed dual-stage speech enhancement…

Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic features for automatic speech recognition (ASR). Hybrid speech recognition systems incorporating CNNs…