Related papers: AMNet: An Acoustic Model Network for Enhanced Mand…

Improving the efficiency of state-of-the-art methods in semantic segmentation requires overcoming the increasing computational cost as well as issues such as fusing semantic information from global and local contexts. Based on the recent…

Although neural machine translation (NMT) has achieved impressive progress recently, it is usually trained on the clean parallel data set and hence cannot work well when the input sentence is the production of the automatic speech…

While deep learning has made impressive progress in speech synthesis and voice conversion, the assessment of the synthesized speech is still carried out by human participants. Several recent papers have proposed deep-learning-based…

In this paper, we investigate a deep learning approach for speech denoising through an efficient ensemble of specialist neural networks. By splitting up the speech denoising task into non-overlapping subproblems and introducing a…

Despite the rapid progress of end-to-end (E2E) automatic speech recognition (ASR), it has been shown that incorporating external language models (LMs) into the decoding can further improve the recognition performance of E2E ASR systems. To…

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…

We introduce VampNet, a masked acoustic token modeling approach to music synthesis, compression, inpainting, and variation. We use a variable masking schedule during training which allows us to sample coherent music from the model by…

End-to-end models are favored in automatic speech recognition (ASR) because of its simplified system structure and superior performance. Among these models, recurrent neural network transducer (RNN-T) has achieved significant progress in…

We propose TalkNet, a convolutional non-autoregressive neural model for speech synthesis. The model consists of two feed-forward convolutional networks. The first network predicts grapheme durations. An input text is expanded by repeating…

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…

It has been shown that the intelligibility of noisy speech can be improved by speech enhancement algorithms. However, speech enhancement has not been established as an effective frontend for robust automatic speech recognition (ASR) in…

Voice activity detection (VAD) makes a distinction between speech and non-speech and its performance is of crucial importance for speech based services. Recently, deep neural network (DNN)-based VADs have achieved better performance than…

Existing deep learning approaches leave out the semantic cues that are crucial in semantic segmentation present in complex scenarios including cluttered backgrounds and translucent objects, etc. To handle these challenges, we propose a…

In this work, we extend our previously proposed offline SpatialNet for long-term streaming multichannel speech enhancement in both static and moving speaker scenarios. SpatialNet exploits spatial information, such as the spatial/steering…

This paper proposes a novel pipeline for automatic grammar augmentation that provides a significant improvement in the voice command recognition accuracy for systems with small footprint acoustic model (AM). The improvement is achieved by…

Distributed microphone array (DMA) is a promising next-generation platform for speech interaction, where speech enhancement (SE) is still required to improve the speech quality in noisy cases. Existing SE methods usually first gather raw…

Closed-Set speaker identification aims to assign a speech utterance to one of a predefined set of enrolled speakers and requires robust modeling of speaker-specific characteristics across multiple temporal scales. While recent deep learning…

End-to-end models have gradually become the preferred option for automatic speech recognition (ASR) applications. During the training of end-to-end ASR, data augmentation is a quite effective technique for regularizing the neural networks.…

This research presents a novel approach to enhancing automatic speech recognition systems by integrating noise detection capabilities directly into the recognition architecture. Building upon the wav2vec2 framework, the proposed method…

Speech signals in real-world environments are frequently affected by various distortions such as additive noise, reverberation, and bandwidth limitation, which may appear individually or in combination. Traditional speech enhancement…