arXiv subjects

Dan Su

Publications and source records attributed to Dan Su.

At least 73 records · Page 4Linked to original sources

arXiv2021

Simple Attention Module based Speaker Verification with Iterative noisy label detection

Recently, the attention mechanism such as squeeze-and-excitation module (SE) and convolutional block attention module (CBAM) has achieved great success in deep learning-based speaker verification system. This paper introduces an alternative effective yet simple one, i.e., simple attention module (SimAM), for speaker verification. The SimAM module is a plug-and-play module without extra modal parameters. In addition, we propose a noisy label detection method to iteratively filter out the data samples with a noisy label from the training data, considering that a large-scale dataset labeled with human annotation or other automated processes may contain noisy labels. Data with the noisy label may over parameterize a deep neural network (DNN) and result in a performance drop due to the memorization effect of the DNN. Experiments are conducted on VoxCeleb dataset. The speaker verification model with SimAM achieves the 0.675% equal error rate (EER) on VoxCeleb1 original test trials. Our proposed iterative noisy label detection method further reduces the EER to 0.643%.

cs.SD↗

arXiv2021

Giant magnetostriction and nonsaturating electric polarization up to 60 T in the polar magnet CaBaCo4O7

Giant magnetostriction in insulating magnetic materials is highly required for applications but is rarely observed. Here we show that giant magnetostriction (> 1500 ppm) can be achieved in an insulating transition metal oxide CaBaCo4O7 where the ferrimagnetic ordering at TC ~ 62 K is associated with a huge change in the lattice. Moreover, because this material is pyroelectric with a non-switchable electric polarization (P), the giant magnetostriction results in a record-breaking magnetoelectric effect - a gigantic change of electric polarization (deltaP ~ 1.6 μC/cm2) in response to the applied magnetic field up to 60 T. Geometric frustration as well as the orbital instability of Co2+/Co3+ ions is believed to play a crucial role in the giant magnetostriction. Our study provides new insights on how to achieve both giant magnetostriction and pronounced magnetoelectric effect in insulating transition metal oxides.

cond-mat.str-el↗

arXiv2021

Latency-Controlled Neural Architecture Search for Streaming Speech Recognition

Neural architecture search (NAS) has attracted much attention and has been explored for automatic speech recognition (ASR). In this work, we focus on streaming ASR scenarios and propose the latency-controlled NAS for acoustic modeling. First, based on the vanilla neural architecture, normal cells are altered to causal cells to control the total latency of the architecture. Second, a revised operation space with a smaller receptive field is proposed to generate the final architecture with low latency. Extensive experiments show that: 1) Based on the proposed neural architecture, the neural networks with a medium latency of 550ms (millisecond) and a low latency of 190ms can be learned in the vanilla and revised operation space respectively. 2) For the low latency setting, the evaluation network can achieve more than 19\% (average on the four test sets) relative improvements compared with the hybrid CLDNN baseline, on a 10k-hour large-scale dataset.

eess.AS↗

arXiv2021

Bilateral Denoising Diffusion Models

Denoising diffusion probabilistic models (DDPMs) have emerged as competitive generative models yet brought challenges to efficient sampling. In this paper, we propose novel bilateral denoising diffusion models (BDDMs), which take significantly fewer steps to generate high-quality samples. From a bilateral modeling objective, BDDMs parameterize the forward and reverse processes with a score network and a scheduling network, respectively. We show that a new lower bound tighter than the standard evidence lower bound can be derived as a surrogate objective for training the two networks. In particular, BDDMs are efficient, simple-to-train, and capable of further improving any pre-trained DDPM by optimizing the inference noise schedules. Our experiments demonstrated that BDDMs can generate high-fidelity samples with as few as 3 sampling steps and produce comparable or even higher quality samples than DDPMs using 1000 steps with only 16 sampling steps (a 62x speedup).

cs.LG↗

arXiv2021

Referee: Towards reference-free cross-speaker style transfer with low-quality data for expressive speech synthesis

Cross-speaker style transfer (CSST) in text-to-speech (TTS) synthesis aims at transferring a speaking style to the synthesised speech in a target speaker's voice. Most previous CSST approaches rely on expensive high-quality data carrying desired speaking style during training and require a reference utterance to obtain speaking style descriptors as conditioning on the generation of a new sentence. This work presents Referee, a robust reference-free CSST approach for expressive TTS, which fully leverages low-quality data to learn speaking styles from text. Referee is built by cascading a text-to-style (T2S) model with a style-to-wave (S2W) model. Phonetic PosteriorGram (PPG), phoneme-level pitch and energy contours are adopted as fine-grained speaking style descriptors, which are predicted from text using the T2S model. A novel pretrain-refinement method is adopted to learn a robust T2S model by only using readily accessible low-quality data. The S2W model is trained with high-quality target data, which is adopted to effectively aggregate style descriptors and generate high-fidelity speech in the target speaker's voice. Experimental results are presented, showing that Referee outperforms a global-style-token (GST)-based baseline approach in CSST.

eess.AS↗

arXiv2021

AppQ: Warm-starting App Recommendation Based on View Graphs

Current app ranking and recommendation systems are mainly based on user-generated information, e.g., number of downloads and ratings. However, new apps often have few (or even no) user feedback, suffering from the classic cold-start problem. How to quickly identify and then recommend new apps of high quality is a challenging issue. Here, a fundamental requirement is the capability to accurately measure an app's quality based on its inborn features, rather than user-generated features. Since users obtain first-hand experience of an app by interacting with its views, we speculate that the inborn features are largely related to the visual quality of individual views in an app and the ways the views switch to one another. In this work, we propose AppQ, a novel app quality grading and recommendation system that extracts inborn features of apps based on app source code. In particular, AppQ works in parallel to perform code analysis to extract app-level features as well as dynamic analysis to capture view-level layout hierarchy and the switching among views. Each app is then expressed as an attributed view graph, which is converted into a vector and fed to classifiers for recognizing its quality classes. Our evaluation with an app dataset from Google Play reports that AppQ achieves the best performance with accuracy of 85.0\%. This shows a lot of promise to warm-start app grading and recommendation systems with AppQ.

cs.IR↗

arXiv2021

TeCANet: Temporal-Contextual Attention Network for Environment-Aware Speech Dereverberation

In this paper, we exploit the effective way to leverage contextual information to improve the speech dereverberation performance in real-world reverberant environments. We propose a temporal-contextual attention approach on the deep neural network (DNN) for environment-aware speech dereverberation, which can adaptively attend to the contextual information. More specifically, a FullBand based Temporal Attention approach (FTA) is proposed, which models the correlations between the fullband information of the context frames. In addition, considering the difference between the attenuation of high frequency bands and low frequency bands (high frequency bands attenuate faster than low frequency bands) in the room impulse response (RIR), we also propose a SubBand based Temporal Attention approach (STA). In order to guide the network to be more aware of the reverberant environments, we jointly optimize the dereverberation network and the reverberation time (RT60) estimator in a multi-task manner. Our experimental results indicate that the proposed method outperforms our previously proposed reverberation-time-aware DNN and the learned attention weights are fully physical consistent. We also report a preliminary yet promising dereverberation and recognition experiment on real test data.

eess.AS↗

arXiv2021

Glow-WaveGAN: Learning Speech Representations from GAN-based Variational Auto-Encoder For High Fidelity Flow-based Speech Synthesis

Current two-stage TTS framework typically integrates an acoustic model with a vocoder -- the acoustic model predicts a low resolution intermediate representation such as Mel-spectrum while the vocoder generates waveform from the intermediate representation. Although the intermediate representation is served as a bridge, there still exists critical mismatch between the acoustic model and the vocoder as they are commonly separately learned and work on different distributions of representation, leading to inevitable artifacts in the synthesized speech. In this work, different from using pre-designed intermediate representation in most previous studies, we propose to use VAE combining with GAN to learn a latent representation directly from speech and then utilize a flow-based acoustic model to model the distribution of the latent representation from text. In this way, the mismatch problem is migrated as the two stages work on the same distribution. Results demonstrate that the flow-based acoustic model can exactly model the distribution of our learned speech representation and the proposed TTS framework, namely Glow-WaveGAN, can produce high fidelity speech outperforming the state-of-the-art GAN-based model.

eess.AS↗

arXiv2021

Controllable Context-aware Conversational Speech Synthesis

In spoken conversations, spontaneous behaviors like filled pause and prolongations always happen. Conversational partner tends to align features of their speech with their interlocutor which is known as entrainment. To produce human-like conversations, we propose a unified controllable spontaneous conversational speech synthesis framework to model the above two phenomena. Specifically, we use explicit labels to represent two typical spontaneous behaviors filled-pause and prolongation in the acoustic model and develop a neural network based predictor to predict the occurrences of the two behaviors from text. We subsequently develop an algorithm based on the predictor to control the occurrence frequency of the behaviors, making the synthesized speech vary from less disfluent to more disfluent. To model the speech entrainment at acoustic level, we utilize a context acoustic encoder to extract a global style embedding from the previous speech conditioning on the synthesizing of current speech. Furthermore, since the current and previous utterances belong to the different speakers in a conversation, we add a domain adversarial training module to eliminate the speaker-related information in the acoustic encoder while maintaining the style-related information. Experiments show that our proposed approach can synthesize realistic conversations and control the occurrences of the spontaneous behaviors naturally.

eess.AS↗

arXiv2021

GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio

This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for semi-supervised and unsupervised training. Around 40,000 hours of transcribed audio is first collected from audiobooks, podcasts and YouTube, covering both read and spontaneous speaking styles, and a variety of topics, such as arts, science, sports, etc. A new forced alignment and segmentation pipeline is proposed to create sentence segments suitable for speech recognition training, and to filter out segments with low-quality transcription. For system training, GigaSpeech provides five subsets of different sizes, 10h, 250h, 1000h, 2500h, and 10000h. For our 10,000-hour XL training subset, we cap the word error rate at 4% during the filtering/validation stage, and for all our other smaller training subsets, we cap it at 0%. The DEV and TEST evaluation sets, on the other hand, are re-processed by professional human transcribers to ensure high transcription quality. Baseline systems are provided for popular speech recognition toolkits, namely Athena, ESPnet, Kaldi and Pika.

cs.SD↗

arXiv2021

Raw Waveform Encoder with Multi-Scale Globally Attentive Locally Recurrent Networks for End-to-End Speech Recognition

End-to-end speech recognition generally uses hand-engineered acoustic features as input and excludes the feature extraction module from its joint optimization. To extract learnable and adaptive features and mitigate information loss, we propose a new encoder that adopts globally attentive locally recurrent (GALR) networks and directly takes raw waveform as input. We observe improved ASR performance and robustness by applying GALR on different window lengths to aggregate fine-grain temporal information into multi-scale acoustic features. Experiments are conducted on a benchmark dataset AISHELL-2 and two large-scale Mandarin speech corpus of 5,000 hours and 21,000 hours. With faster speed and comparable model size, our proposed multi-scale GALR waveform encoder achieved consistent character error rate reductions (CERRs) from 7.9% to 28.1% relative over strong baselines, including Conformer and TDNN-Conformer. In particular, our approach demonstrated notable robustness than the traditional handcrafted features and outperformed the baseline MFCC-based TDNN-Conformer model by a 15.2% CERR on a music-mixed real-world speech test set.

cs.SD↗

arXiv2021

Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance

Query focused summarization (QFS) models aim to generate summaries from source documents that can answer the given query. Most previous work on QFS only considers the query relevance criterion when producing the summary. However, studying the effect of answer relevance in the summary generating process is also important. In this paper, we propose QFS-BART, a model that incorporates the explicit answer relevance of the source documents given the query via a question answering model, to generate coherent and answer-related summaries. Furthermore, our model can take advantage of large pre-trained models which improve the summarization performance significantly. Empirical results on the Debatepedia dataset show that the proposed model achieves the new state-of-the-art performance.

cs.CL↗

arXiv2021

DiffSVC: A Diffusion Probabilistic Model for Singing Voice Conversion

Singing voice conversion (SVC) is one promising technique which can enrich the way of human-computer interaction by endowing a computer the ability to produce high-fidelity and expressive singing voice. In this paper, we propose DiffSVC, an SVC system based on denoising diffusion probabilistic model. DiffSVC uses phonetic posteriorgrams (PPGs) as content features. A denoising module is trained in DiffSVC, which takes destroyed mel spectrogram produced by the diffusion/forward process and its corresponding step information as input to predict the added Gaussian noise. We use PPGs, fundamental frequency features and loudness features as auxiliary input to assist the denoising process. Experiments show that DiffSVC can achieve superior conversion performance in terms of naturalness and voice similarity to current state-of-the-art SVC approaches.

eess.AS↗

arXiv2021

FastSVC: Fast Cross-Domain Singing Voice Conversion with Feature-wise Linear Modulation

This paper presents FastSVC, a light-weight cross-domain singing voice conversion (SVC) system, which can achieve high conversion performance, with inference speed 4x faster than real-time on CPUs. FastSVC uses Conformer-based phoneme recognizer to extract singer-agnostic linguistic features from singing signals. A feature-wise linear modulation based generator is used to synthesize waveform directly from linguistic features, leveraging information from sine-excitation signals and loudness features. The waveform generator can be trained conveniently using a multi-resolution spectral loss and an adversarial loss. Experimental results show that the proposed FastSVC system, compared with a computationally heavy baseline system, can achieve comparable conversion performance in some scenarios and significantly better conversion performance in other scenarios. Moreover, the proposed FastSVC system achieves desirable cross-lingual singing conversion performance. The inference speed of the FastSVC system is 3x and 70x faster than the baseline system on GPUs and CPUs, respectively.

eess.AS↗

arXiv2021

Learned Transferable Architectures Can Surpass Hand-Designed Architectures for Large Scale Speech Recognition

In this paper, we explore the neural architecture search (NAS) for automatic speech recognition (ASR) systems. With reference to the previous works in the computer vision field, the transferability of the searched architecture is the main focus of our work. The architecture search is conducted on the small proxy dataset, and then the evaluation network, constructed with the searched architecture, is evaluated on the large dataset. Especially, we propose a revised search space for speech recognition tasks which theoretically facilitates the search algorithm to explore the architectures with low complexity. Extensive experiments show that: (i) the architecture searched on the small proxy dataset can be transferred to the large dataset for the speech recognition tasks. (ii) the architecture learned in the revised search space can greatly reduce the computational overhead and GPU memory usage with mild performance degradation. (iii) the searched architecture can achieve more than 20% and 15% (average on the four test sets) relative improvements respectively on the AISHELL-2 dataset and the large (10k hours) dataset, compared with our best hand-designed DFSMN-SAN architecture. To the best of our knowledge, this is the first report of NAS results with large scale dataset (up to 10K hours), indicating the promising application of NAS to industrial ASR systems.

eess.AS↗

arXiv2021

SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts

Recently, Mixture of Experts (MoE) based Transformer has shown promising results in many domains. This is largely due to the following advantages of this architecture: firstly, MoE based Transformer can increase model capacity without computational cost increasing both at training and inference time. Besides, MoE based Transformer is a dynamic network which can adapt to the varying complexity of input instances in realworld applications. In this work, we explore the MoE based model for speech recognition, named SpeechMoE. To further control the sparsity of router activation and improve the diversity of gate values, we propose a sparsity L1 loss and a mean importance loss respectively. In addition, a new router architecture is used in SpeechMoE which can simultaneously utilize the information from a shared embedding network and the hierarchical representation of different MoE layers. Experimental results show that SpeechMoE can achieve lower character error rate (CER) with comparable computation cost than traditional static networks, providing 7.0%-23.0% relative CER improvements on four evaluation datasets.

cs.SD↗

arXiv2021

Non-Autoregressive Transformer ASR with CTC-Enhanced Decoder Input

Non-autoregressive (NAR) transformer models have achieved significantly inference speedup but at the cost of inferior accuracy compared to autoregressive (AR) models in automatic speech recognition (ASR). Most of the NAR transformers take a fixed-length sequence filled with MASK tokens or a redundant sequence copied from encoder states as decoder input, they cannot provide efficient target-side information thus leading to accuracy degradation. To address this problem, we propose a CTC-enhanced NAR transformer, which generates target sequence by refining predictions of the CTC module. Experimental results show that our method outperforms all previous NAR counterparts and achieves 50x faster decoding speed than a strong AR baseline with only 0.0 ~ 0.3 absolute CER degradation on Aishell-1 and Aishell-2 datasets.

cs.SD↗

arXiv2021

Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation

One of the leading single-channel speech separation (SS) models is based on a TasNet with a dual-path segmentation technique, where the size of each segment remains unchanged throughout all layers. In contrast, our key finding is that multi-granularity features are essential for enhancing contextual modeling and computational efficiency. We introduce a self-attentive network with a novel sandglass-shape, namely Sandglasset, which advances the state-of-the-art (SOTA) SS performance at significantly smaller model size and computational cost. Forward along each block inside Sandglasset, the temporal granularity of the features gradually becomes coarser until reaching half of the network blocks, and then successively turns finer towards the raw signal level. We also unfold that residual connections between features with the same granularity are critical for preserving information after passing through the bottleneck layer. Experiments show our Sandglasset with only 2.3M parameters has achieved the best results on two benchmark SS datasets -- WSJ0-2mix and WSJ0-3mix, where the SI-SNRi scores have been improved by absolute 0.8 dB and 2.4 dB, respectively, comparing to the prior SOTA results.

eess.AS↗