Related papers: Improving Reverberant Speech Training Using Diffus…

We propose a computational model of speech production combining a pre-trained neural articulatory synthesizer able to reproduce complex speech stimuli from a limited set of interpretable articulatory parameters, a DNN-based internal forward…

Reverberation not only degrades the quality of speech for human perception, but also severely impacts the accuracy of automatic speech recognition. Prior work attempts to remove reverberation based on the audio modality only. Our idea is to…

Deepfake speech utterances can be forged by replacing one or more words in a bona fide utterance with semantically different words synthesized with speech-generative models. While a dedicated synthetic word detector could be developed, we…

Enhancing speech signal quality in adverse acoustic environments is a persistent challenge in speech processing. Existing deep learning based enhancement methods often struggle to effectively remove background noise and reverberation in…

Large-scale distributed training of deep acoustic models plays an important role in today's high-performance automatic speech recognition (ASR). In this paper we investigate a variety of asynchronous decentralized distributed training…

With the advance in self-supervised learning for audio and visual modalities, it has become possible to learn a robust audio-visual speech representation. This would be beneficial for improving the audio-visual speech recognition (AVSR)…

In mobile speech communication applications, wind noise can lead to a severe reduction of speech quality and intelligibility. Since the performance of speech enhancement algorithms using acoustic microphones tends to substantially degrade…

In this paper, we address the problem of single-microphone speech separation in the presence of ambient noise. We propose a generative unsupervised technique that directly models both clean speech and structured noise components, training…

Acoustics-to-word models are end-to-end speech recognizers that use words as targets without relying on pronunciation dictionaries or graphemes. These models are notoriously difficult to train due to the lack of linguistic knowledge. It is…

This work proposes an efficient method to enhance the quality of corrupted speech signals by leveraging both acoustic and visual cues. While existing diffusion-based approaches have demonstrated remarkable quality, their applicability is…

Multi-channel speech enhancement with ad-hoc sensors has been a challenging task. Speech model guided beamforming algorithms are able to recover natural sounding speech, but the speech models tend to be oversimplified or the inference would…

This paper proposes a deep speech enhancement method which exploits the high potential of residual connections in a wide neural network architecture, a topology known as Wide Residual Network. This is supported on single dimensional…

This paper explores the outcome of training state-of-the-art dereverberation models with supervision settings ranging from weakly-supervised to virtually unsupervised, relying solely on reverberant signals and an acoustic model for…

Replay attacks remain a critical vulnerability for automatic speaker verification systems, particularly in real-time voice assistant applications. In this work, we propose acoustic maps as a novel spatial feature representation for replay…

Sequence discriminative training is a great tool to improve the performance of an automatic speech recognition system. It does, however, necessitate a sum over all possible word sequences, which is intractable to compute in practice.…

In this paper, we describe how to efficiently implement an acoustic room simulator to generate large-scale simulated data for training deep neural networks. Even though Google Room Simulator in [1] was shown to be quite effective in…

Recently, motivated by the outstanding achievements of diffusion models, the diffusion process has been employed to strengthen representation learning in recommendation systems. Most diffusion-based recommendation models typically utilize…

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…

Quality of data plays an important role in most deep learning tasks. In the speech community, transcription of speech recording is indispensable. Since the transcription is usually generated artificially, automatically finding errors in…

We propose a method for generating low-frequency compensated synthetic impulse responses that improve the performance of far-field speech recognition systems trained on artificially augmented datasets. We design linear-phase filters that…