Related papers: MatchboxNet: 1D Time-Channel Separable Convolution…
We study response selection for multi-turn conversation in retrieval-based chatbots. Existing work either concatenates utterances in context or matches a response with a highly abstract context vector finally, which may lose relationships…
We study transfer learning in convolutional network architectures applied to the task of recognizing audio, such as environmental sound events and speech commands. Our key finding is that not only is it possible to transfer representations…
Accurate recognition of aviation commands is vital for flight safety and efficiency, as pilots must follow air traffic control instructions precisely. This paper addresses challenges in speech command recognition, such as noisy environments…
Deep-learning based methods have shown their advantages in audio coding over traditional ones but limited attention has been paid on real-time communications (RTC). This paper proposes the TFNet, an end-to-end neural speech codec with low…
We present a state-of-the-art speech recognition system developed using end-to-end deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these…
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…
Today's Automatic Speech Recognition systems only rely on acoustic signals and often don't perform well under noisy conditions. Performing multi-modal speech recognition - processing acoustic speech signals and lip-reading video…
In recent years, many deep learning techniques for single-channel sound source separation have been proposed using recurrent, convolutional and transformer networks. When multiple microphones are available, spatial diversity between…
Distant speech recognition is a challenge, particularly due to the corruption of speech signals by reverberation caused by large distances between the speaker and microphone. In order to cope with a wide range of reverberations in…
Recently, open domain multi-turn chatbots have attracted much interest from lots of researchers in both academia and industry. The dominant retrieval-based methods use context-response matching mechanisms for multi-turn response selection.…
Deep learning based single-channel speech enhancement tries to train a neural network model for the prediction of clean speech signal. There are a variety of popular network structures for single-channel speech enhancement, such as TCNN,…
We present a novel model designed for resource-efficient multichannel speech enhancement in the time domain, with a focus on low latency, lightweight, and low computational requirements. The proposed model incorporates explicit spatial and…
Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output…
We describe Microsoft's conversational speech recognition system, in which we combine recent developments in neural-network-based acoustic and language modeling to advance the state of the art on the Switchboard recognition task. Inspired…
Recently, stunning improvements on multi-channel speech separation have been achieved by neural beamformers when direction information is available. However, most of them neglect to utilize speaker's 2-dimensional (2D) location cues…
Existing speech recognition systems are typically built at the sentence level, although it is known that dialog context, e.g. higher-level knowledge that spans across sentences or speakers, can help the processing of long conversations. The…
Neural multi-channel speech enhancement models, in particular those based on the U-Net architecture, demonstrate promising performance and generalization potential. These models typically encode input channels independently, and integrate…
Modern deep learning architectures produce highly accurate results on many challenging semantic segmentation datasets. State-of-the-art methods are, however, not directly transferable to real-time applications or embedded devices, since…
In this paper we aim to automatically discover high quality frame-level speech features and acoustic tokens directly from unlabeled speech data. A Multi-granular Acoustic Tokenizer (MAT) was proposed for automatic discovery of multiple sets…
FullSubNet is our recently proposed real-time single-channel speech enhancement network that achieves outstanding performance on the Deep Noise Suppression (DNS) Challenge dataset. A number of variants of FullSubNet have been proposed, but…