arXiv subjects

Ning Cheng

Publications and source records attributed to Ning Cheng.

103 records · Page 6Linked to original sources

arXiv2021

Joint Intent Detection And Slot Filling Based on Continual Learning Model

Slot filling and intent detection have become a significant theme in the field of natural language understanding. Even though slot filling is intensively associated with intent detection, the characteristics of the information required for both tasks are different while most of those approaches may not fully aware of this problem. In addition, balancing the accuracy of two tasks effectively is an inevitable problem for the joint learning model. In this paper, a Continual Learning Interrelated Model (CLIM) is proposed to consider semantic information with different characteristics and balance the accuracy between intent detection and slot filling effectively. The experimental results show that CLIM achieves state-of-the-art performace on slot filling and intent detection on ATIS and Snips.

cs.CL↗

arXiv2021

Applying Wav2vec2.0 to Speech Recognition in Various Low-resource Languages

There are several domains that own corresponding widely used feature extractors, such as ResNet, BERT, and GPT-x. These models are usually pre-trained on large amounts of unlabeled data by self-supervision and can be effectively applied to downstream tasks. In the speech domain, wav2vec2.0 starts to show its powerful representation ability and feasibility of ultra-low resource speech recognition on the Librispeech corpus, which belongs to the audiobook domain. However, wav2vec2.0 has not been examined on real spoken scenarios and languages other than English. To verify its universality over languages, we apply pre-trained models to solve low-resource speech recognition tasks in various spoken languages. We achieve more than 20% relative improvements in six languages compared with previous work. Among these languages, English achieves a gain of 52.4%. Moreover, using coarse-grained modeling units, such as subword or character, achieves better results than fine-grained modeling units, such as phone or letter.

cs.CL↗

arXiv2020

MelGlow: Efficient Waveform Generative Network Based on Location-Variable Convolution

Recent neural vocoders usually use a WaveNet-like network to capture the long-term dependencies of the waveform, but a large number of parameters are required to obtain good modeling capabilities. In this paper, an efficient network, named location-variable convolution, is proposed to model the dependencies of waveforms. Different from the use of unified convolution kernels in WaveNet to capture the dependencies of arbitrary waveforms, location-variable convolutions utilizes a kernel predictor to generate multiple sets of convolution kernels based on the mel-spectrum, where each set of convolution kernels is used to perform convolution operations on the associated waveform intervals. Combining WaveGlow and location-variable convolutions, an efficient vocoder, named MelGlow, is designed. Experiments on the LJSpeech dataset show that MelGlow achieves better performance than WaveGlow at small model sizes, which verifies the effectiveness and potential optimization space of location-variable convolutions.

cs.SD↗

arXiv2020

GraphPB: Graphical Representations of Prosody Boundary in Speech Synthesis

This paper introduces a graphical representation approach of prosody boundary (GraphPB) in the task of Chinese speech synthesis, intending to parse the semantic and syntactic relationship of input sequences in a graphical domain for improving the prosody performance. The nodes of the graph embedding are formed by prosodic words, and the edges are formed by the other prosodic boundaries, namely prosodic phrase boundary (PPH) and intonation phrase boundary (IPH). Different Graph Neural Networks (GNN) like Gated Graph Neural Network (GGNN) and Graph Long Short-term Memory (G-LSTM) are utilised as graph encoders to exploit the graphical prosody boundary information. Graph-to-sequence model is proposed and formed by a graph encoder and an attentional decoder. Two techniques are proposed to embed sequential information into the graph-to-sequence text-to-speech model. The experimental results show that this proposed approach can encode the phonetic and prosody rhythm of an utterance. The mean opinion score (MOS) of these GNN models shows comparative results with the state-of-the-art sequence-to-sequence models with better performance in the aspect of prosody. This provides an alternative approach for prosody modelling in end-to-end speech synthesis.

eess.AS↗

arXiv2020

Multi-QuartzNet: Multi-Resolution Convolution for Speech Recognition with Multi-Layer Feature Fusion

In this paper, we propose an end-to-end speech recognition network based on Nvidia's previous QuartzNet model. We try to promote the model performance, and design three components: (1) Multi-Resolution Convolution Module, replaces the original 1D time-channel separable convolution with multi-stream convolutions. Each stream has a unique dilated stride on convolutional operations. (2) Channel-Wise Attention Module, calculates the attention weight of each convolutional stream by spatial channel-wise pooling. (3) Multi-Layer Feature Fusion Module, reweights each convolutional block by global multi-layer feature maps. Our experiments demonstrate that Multi-QuartzNet model achieves CER 6.77% on AISHELL-1 data set, which outperforms original QuartzNet and is close to state-of-art result.

eess.AS↗

arXiv2020

End-to-end Silent Speech Recognition with Acoustic Sensing

Silent speech interfaces (SSI) has been an exciting area of recent interest. In this paper, we present a non-invasive silent speech interface that uses inaudible acoustic signals to capture people's lip movements when they speak. We exploit the speaker and microphone of the smartphone to emit signals and listen to their reflections, respectively. The extracted phase features of these reflections are fed into the deep learning networks to recognize speech. And we also propose an end-to-end recognition framework, which combines the CNN and attention-based encoder-decoder network. Evaluation results on a limited vocabulary (54 sentences) yield word error rates of 8.4% in speaker-independent and environment-independent settings, and 8.1% for unseen sentence testing.

eess.AS↗

arXiv2020

A Real-time Robot-based Auxiliary System for Risk Evaluation of COVID-19 Infection

In this paper, we propose a real-time robot-based auxiliary system for risk evaluation of COVID-19 infection. It combines real-time speech recognition, temperature measurement, keyword detection, cough detection and other functions in order to convert live audio into actionable structured data to achieve the COVID-19 infection risk assessment function. In order to better evaluate the COVID-19 infection, we propose an end-to-end method for cough detection and classification for our proposed system. It is based on real conversation data from human-robot, which processes speech signals to detect cough and classifies it if detected. The structure of our model are maintained concise to be implemented for real-time applications. And we further embed this entire auxiliary diagnostic system in the robot and it is placed in the communities, hospitals and supermarkets to support COVID-19 testing. The system can be further leveraged within a business rules engine, thus serving as a foundation for real-time supervision and assistance applications. Our model utilizes a pretrained, robust training environment that allows for efficient creation and customization of customer-specific health states.

eess.AS↗

arXiv2020

MLNET: An Adaptive Multiple Receptive-field Attention Neural Network for Voice Activity Detection

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 conventional signal processing methods. The existed DNNbased models always handcrafted a fixed window to make use of the contextual speech information to improve the performance of VAD. However, the fixed window of contextual speech information can't handle various unpredicatable noise environments and highlight the critical speech information to VAD task. In order to solve this problem, this paper proposed an adaptive multiple receptive-field attention neural network, called MLNET, to finish VAD task. The MLNET leveraged multi-branches to extract multiple contextual speech information and investigated an effective attention block to weight the most crucial parts of the context for final classification. Experiments in real-world scenarios demonstrated that the proposed MLNET-based model outperformed other baselines.

eess.AS↗

arXiv2020

Prosody Learning Mechanism for Speech Synthesis System Without Text Length Limit

Recent neural speech synthesis systems have gradually focused on the control of prosody to improve the quality of synthesized speech, but they rarely consider the variability of prosody and the correlation between prosody and semantics together. In this paper, a prosody learning mechanism is proposed to model the prosody of speech based on TTS system, where the prosody information of speech is extracted from the melspectrum by a prosody learner and combined with the phoneme sequence to reconstruct the mel-spectrum. Meanwhile, the sematic features of text from the pre-trained language model is introduced to improve the prosody prediction results. In addition, a novel self-attention structure, named as local attention, is proposed to lift this restriction of input text length, where the relative position information of the sequence is modeled by the relative position matrices so that the position encodings is no longer needed. Experiments on English and Mandarin show that speech with more satisfactory prosody has obtained in our model. Especially in Mandarin synthesis, our proposed model outperforms baseline model with a MOS gap of 0.08, and the overall naturalness of the synthesized speech has been significantly improved.

eess.AS↗

arXiv2020

Large-scale Transfer Learning for Low-resource Spoken Language Understanding

End-to-end Spoken Language Understanding (SLU) models are made increasingly large and complex to achieve the state-ofthe-art accuracy. However, the increased complexity of a model can also introduce high risk of over-fitting, which is a major challenge in SLU tasks due to the limitation of available data. In this paper, we propose an attention-based SLU model together with three encoder enhancement strategies to overcome data sparsity challenge. The first strategy focuses on the transferlearning approach to improve feature extraction capability of the encoder. It is implemented by pre-training the encoder component with a quantity of Automatic Speech Recognition annotated data relying on the standard Transformer architecture and then fine-tuning the SLU model with a small amount of target labelled data. The second strategy adopts multitask learning strategy, the SLU model integrates the speech recognition model by sharing the same underlying encoder, such that improving robustness and generalization ability. The third strategy, learning from Component Fusion (CF) idea, involves a Bidirectional Encoder Representation from Transformer (BERT) model and aims to boost the capability of the decoder with an auxiliary network. It hence reduces the risk of over-fitting and augments the ability of the underlying encoder, indirectly. Experiments on the FluentAI dataset show that cross-language transfer learning and multi-task strategies have been improved by up to 4:52% and 3:89% respectively, compared to the baseline.

eess.AS↗

arXiv2020

GraphTTS: graph-to-sequence modelling in neural text-to-speech

This paper leverages the graph-to-sequence method in neural text-to-speech (GraphTTS), which maps the graph embedding of the input sequence to spectrograms. The graphical inputs consist of node and edge representations constructed from input texts. The encoding of these graphical inputs incorporates syntax information by a GNN encoder module. Besides, applying the encoder of GraphTTS as a graph auxiliary encoder (GAE) can analyse prosody information from the semantic structure of texts. This can remove the manual selection of reference audios process and makes prosody modelling an end-to-end procedure. Experimental analysis shows that GraphTTS outperforms the state-of-the-art sequence-to-sequence models by 0.24 in Mean Opinion Score (MOS). GAE can adjust the pause, ventilation and tones of synthesised audios automatically. This experimental conclusion may give some inspiration to researchers working on improving speech synthesis prosody.

eess.AS↗

arXiv2020

AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment

Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a Feed-Forward Transformer which generates mel-spectrum from a sequence of characters, and the duration of each character is determined by a duration predictor.Instead of adopting the attention mechanism in Transformer TTS to align text to mel-spectrum, the alignment loss is presented to consider all possible alignments in training by use of dynamic programming. Experiments on the LJSpeech dataset show that our model achieves not only state-of-the-art performance which outperforms Transformer TTS by 0.03 in mean option score (MOS), but also a high efficiency which is more than 50 times faster than real-time.

eess.AS↗

arXiv2018

Novel methods for measuring the optical parameters of the water Cherenkov detector

In this paper, novel methods are presented to measure the optical properties of muon detectors (MDs) in the Large High-Altitude Air Shower Observatory (LHAASO), which can also be used by other experiments. Each MD consists of a cylindrical water Cherenkov detector, with a Tyvek liner containing pure water, and a photomultiplier tube (PMT) mounted on the top. The time distribution of the photons collected by the PMT in the water Cherenkov detector have an approximately exponential distribution, and their decay factor is determined by the photon absorption length in the water, the reflectivity of the inner Tyvek surface, the mean reflecting step length of photons reflected by the inner surface, and the ratio of reflectional Tyvek area to the total inner surface area. By considering the principles of photon propagation in the water Cherenkov detector, we have developed novel methods to measure the water absorption length, the Tyvek reflectivity, and the mean step length of photons. The step length of photons can be determined by measuring the time distribution of the reflected photons hitting the PMT after multiple photons with single wavelength are generated in the tank, with slightly different ratios of the inner Tyvek to the total inner area. The water absorption length and Tyvek reflectivity can be measured simultaneously by the PMT by changing the height of the water, while the step length and Tyvek reflectivity in air can also be measured simultaneously. The proposed novel methods are supported by deduction of formulae and verified by GEANT4 simulations and the prototype experiment.

physics.ins-det↗