arXiv subjects

Lei Xie

Publications and source records attributed to Lei Xie.

At least 415 records · Page 23Linked to original sources

arXiv2021

Duality Temporal-channel-frequency Attention Enhanced Speaker Representation Learning

The use of channel-wise attention in CNN based speaker representation networks has achieved remarkable performance in speaker verification (SV). But these approaches do simple averaging on time and frequency feature maps before channel-wise attention learning and ignore the essential mutual interaction among temporal, channel as well as frequency scales. To address this problem, we propose the Duality Temporal-Channel-Frequency (DTCF) attention to re-calibrate the channel-wise features with aggregation of global context on temporal and frequency dimensions. Specifically, the duality attention - time-channel (T-C) attention as well as frequency-channel (F-C) attention - aims to focus on salient regions along the T-C and F-C feature maps that may have more considerable impact on the global context, leading to more discriminative speaker representations. We evaluate the effectiveness of the proposed DTCF attention on the CN-Celeb and VoxCeleb datasets. On the CN-Celeb evaluation set, the EER/minDCF of ResNet34-DTCF are reduced by 0.63%/0.0718 compared with those of ResNet34-SE. On VoxCeleb1-O, VoxCeleb1-E and VoxCeleb1-H evaluation sets, the EER/minDCF of ResNet34-DTCF achieve 0.36%/0.0263, 0.39%/0.0382 and 0.74%/0.0753 reductions compared with those of ResNet34-SE.

cs.SD↗

arXiv2021

Boundary and Context Aware Training for CIF-based Non-Autoregressive End-to-end ASR

Continuous integrate-and-fire (CIF) based models, which use a soft and monotonic alignment mechanism, have been well applied in non-autoregressive (NAR) speech recognition with competitive performance compared with other NAR methods. However, such an alignment learning strategy may suffer from an erroneous acoustic boundary estimation, severely hindering the convergence speed as well as the system performance. In this paper, we propose a boundary and context aware training approach for CIF based NAR models. Firstly, the connectionist temporal classification (CTC) spike information is utilized to guide the learning of acoustic boundaries in the CIF. Besides, an additional contextual decoder is introduced behind the CIF decoder, aiming to capture the linguistic dependencies within a sentence. Finally, we adopt a recently proposed Conformer architecture to improve the capacity of acoustic modeling. Experiments on the open-source Mandarin AISHELL-1 corpus show that the proposed method achieves a comparable character error rates (CERs) of 4.9% with only 1/24 latency compared with a state-of-the-art autoregressive (AR) Conformer model. Futhermore, when evaluating on an internal 7500 hours Mandarin corpus, our model still outperforms other NAR methods and even reaches the AR Conformer model on a challenging real-world noisy test set.

cs.SD↗

arXiv2021

Exploiting Different Levels of Parallelism in the Quantum Control Microarchitecture for Superconducting Qubits

As current Noisy Intermediate Scale Quantum (NISQ) devices suffer from decoherence errors, any delay in the instruction execution of quantum control microarchitecture can lead to the loss of quantum information and incorrect computation results. Hence, it is crucial for the control microarchitecture to issue quantum operations to the Quantum Processing Unit (QPU) in time. As in classical microarchitecture, parallelism in quantum programs needs to be exploited for speedup. However, three challenges emerge in the quantum scenario: 1) the quantum feedback control can introduce significant pipeline stall latency; 2) timing control is required for all quantum operations; 3) QPU requires a deterministic operation supply to prevent the accumulation of quantum errors. In this paper, we propose a novel control microarchitecture design to exploit Circuit Level Parallelism (CLP) and Quantum Operation Level Parallelism (QOLP). Firstly, we develop a Multiprocessor architecture to exploit CLP, which supports dynamic scheduling of different sub-circuits. This architecture can handle parallel feedback control and minimize the potential overhead that disrupts the timing control. Secondly, we propose a Quantum Superscalar approach that exploits QOLP by efficiently executing massive quantum instructions in parallel. Both methods issue quantum operations to QPU deterministically. In the benchmark test of a Shor syndrome measurement, a six-core implementation of our proposal achieves up to 2.59$\times$ speedup compared with a single core. For various canonical quantum computing algorithms, our superscalar approach achieves an average of 4.04$\times$ improvement over a baseline design. Finally, We perform a simultaneous randomized benchmarking (simRB) experiment on a real QPU using the proposed microarchitecture for validation.

quant-ph↗

arXiv2021

AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person

Automatically generating videos in which synthesized speech is synchronized with lip movements in a talking head has great potential in many human-computer interaction scenarios. In this paper, we present an automatic method to generate synchronized speech and talking-head videos on the basis of text and a single face image of an arbitrary person as input. In contrast to previous text-driven talking head generation methods, which can only synthesize the voice of a specific person, the proposed method is capable of synthesizing speech for any person that is inaccessible in the training stage. Specifically, the proposed method decomposes the generation of synchronized speech and talking head videos into two stages, i.e., a text-to-speech (TTS) stage and a speech-driven talking head generation stage. The proposed TTS module is a face-conditioned multi-speaker TTS model that gets the speaker identity information from face images instead of speech, which allows us to synthesize a personalized voice on the basis of the input face image. To generate the talking head videos from the face images, a facial landmark-based method that can predict both lip movements and head rotations is proposed. Extensive experiments demonstrate that the proposed method is able to generate synchronized speech and talking head videos for arbitrary persons and non-persons. Synthesized speech shows consistency with the given face regarding to the synthesized voice's timbre and one's appearance in the image, and the proposed landmark-based talking head method outperforms the state-of-the-art landmark-based method on generating natural talking head videos.

cs.CV↗

arXiv2021

Darts-Conformer: Towards Efficient Gradient-Based Neural Architecture Search For End-to-End ASR

Neural architecture search (NAS) has been successfully applied to tasks like image classification and language modeling for finding efficient high-performance network architectures. In ASR field especially end-to-end ASR, the related research is still in its infancy. In this work, we focus on applying NAS on the most popular manually designed model: Conformer, and then propose an efficient ASR model searching method that benefits from the natural advantage of differentiable architecture search (Darts) in reducing computational overheads. We fuse Darts mutator and Conformer blocks to form a complete search space, within which a modified architecture called Darts-Conformer cell is found automatically. The entire searching process on AISHELL-1 dataset costs only 0.7 GPU days. Replacing the Conformer encoder by stacking searched cell, we get an end-to-end ASR model (named as Darts-Conformner) that outperforms the Conformer baseline by 4.7\% on the open-source AISHELL-1 dataset. Besides, we verify the transferability of the architecture searched on a small dataset to a larger 2k-hour dataset. To the best of our knowledge, this is the first successful attempt to apply gradient-based architecture search in the attention-based encoder-decoder ASR model.

cs.SD↗

arXiv2021

AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario

In this paper, we present AISHELL-4, a sizable real-recorded Mandarin speech dataset collected by 8-channel circular microphone array for speech processing in conference scenario. The dataset consists of 211 recorded meeting sessions, each containing 4 to 8 speakers, with a total length of 120 hours. This dataset aims to bridge the advanced research on multi-speaker processing and the practical application scenario in three aspects. With real recorded meetings, AISHELL-4 provides realistic acoustics and rich natural speech characteristics in conversation such as short pause, speech overlap, quick speaker turn, noise, etc. Meanwhile, accurate transcription and speaker voice activity are provided for each meeting in AISHELL-4. This allows the researchers to explore different aspects in meeting processing, ranging from individual tasks such as speech front-end processing, speech recognition and speaker diarization, to multi-modality modeling and joint optimization of relevant tasks. Given most open source dataset for multi-speaker tasks are in English, AISHELL-4 is the only Mandarin dataset for conversation speech, providing additional value for data diversity in speech community. We also release a PyTorch-based training and evaluation framework as baseline system to promote reproducible research in this field.

cs.SD↗

arXiv2021

Enriching Source Style Transfer in Recognition-Synthesis based Non-Parallel Voice Conversion

Current voice conversion (VC) methods can successfully convert timbre of the audio. As modeling source audio's prosody effectively is a challenging task, there are still limitations of transferring source style to the converted speech. This study proposes a source style transfer method based on recognition-synthesis framework. Previously in speech generation task, prosody can be modeled explicitly with prosodic features or implicitly with a latent prosody extractor. In this paper, taking advantages of both, we model the prosody in a hybrid manner, which effectively combines explicit and implicit methods in a proposed prosody module. Specifically, prosodic features are used to explicit model prosody, while VAE and reference encoder are used to implicitly model prosody, which take Mel spectrum and bottleneck feature as input respectively. Furthermore, adversarial training is introduced to remove speaker-related information from the VAE outputs, avoiding leaking source speaker information while transferring style. Finally, we use a modified self-attention based encoder to extract sentential context from bottleneck features, which also implicitly aggregates the prosodic aspects of source speech from the layered representations. Experiments show that our approach is superior to the baseline and a competitive system in terms of style transfer; meanwhile, the speech quality and speaker similarity are well maintained.

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

Improving robustness of one-shot voice conversion with deep discriminative speaker encoder

One-shot voice conversion has received significant attention since only one utterance from source speaker and target speaker respectively is required. Moreover, source speaker and target speaker do not need to be seen during training. However, available one-shot voice conversion approaches are not stable for unseen speakers as the speaker embedding extracted from one utterance of an unseen speaker is not reliable. In this paper, we propose a deep discriminative speaker encoder to extract speaker embedding from one utterance more effectively. Specifically, the speaker encoder first integrates residual network and squeeze-and-excitation network to extract discriminative speaker information in frame level by modeling frame-wise and channel-wise interdependence in features. Then attention mechanism is introduced to further emphasize speaker related information via assigning different weights to frame level speaker information. Finally a statistic pooling layer is used to aggregate weighted frame level speaker information to form utterance level speaker embedding. The experimental results demonstrate that our proposed speaker encoder can improve the robustness of one-shot voice conversion for unseen speakers and outperforms baseline systems in terms of speech quality and speaker similarity.

cs.SD↗

arXiv2021

Improving Performance of Seen and Unseen Speech Style Transfer in End-to-end Neural TTS

End-to-end neural TTS training has shown improved performance in speech style transfer. However, the improvement is still limited by the training data in both target styles and speakers. Inadequate style transfer performance occurs when the trained TTS tries to transfer the speech to a target style from a new speaker with an unknown, arbitrary style. In this paper, we propose a new approach to style transfer for both seen and unseen styles, with disjoint, multi-style datasets, i.e., datasets of different styles are recorded, each individual style is by one speaker with multiple utterances. To encode the style information, we adopt an inverse autoregressive flow (IAF) structure to improve the variational inference. The whole system is optimized to minimize a weighed sum of four different loss functions: 1) a reconstruction loss to measure the distortions in both source and target reconstructions; 2) an adversarial loss to "fool" a well-trained discriminator; 3) a style distortion loss to measure the expected style loss after the transfer; 4) a cycle consistency loss to preserve the speaker identity of the source after the transfer. Experiments demonstrate, both objectively and subjectively, the effectiveness of the proposed approach for seen and unseen style transfer tasks. The performance of the new approach is better and more robust than those of four baseline systems of the prior art.

cs.SD↗

arXiv2021

Efficient Conformer with Prob-Sparse Attention Mechanism for End-to-EndSpeech Recognition

End-to-end models are favored in automatic speech recognition (ASR) because of their simplified system structure and superior performance. Among these models, Transformer and Conformer have achieved state-of-the-art recognition accuracy in which self-attention plays a vital role in capturing important global information. However, the time and memory complexity of self-attention increases squarely with the length of the sentence. In this paper, a prob-sparse self-attention mechanism is introduced into Conformer to sparse the computing process of self-attention in order to accelerate inference speed and reduce space consumption. Specifically, we adopt a Kullback-Leibler divergence based sparsity measurement for each query to decide whether we compute the attention function on this query. By using the prob-sparse attention mechanism, we achieve impressively 8% to 45% inference speed-up and 15% to 45% memory usage reduction of the self-attention module of Conformer Transducer while maintaining the same level of error rate.

cs.SD↗

arXiv2021

Multi-Level Transfer Learning from Near-Field to Far-Field Speaker Verification

In far-field speaker verification, the performance of speaker embeddings is susceptible to degradation when there is a mismatch between the conditions of enrollment and test speech. To solve this problem, we propose the feature-level and instance-level transfer learning in the teacher-student framework to learn a domain-invariant embedding space. For the feature-level knowledge transfer, we develop the contrastive loss to transfer knowledge from teacher model to student model, which can not only decrease the intra-class distance, but also enlarge the inter-class distance. Moreover, we propose the instance-level pairwise distance transfer method to force the student model to preserve pairwise instances distance from the well optimized embedding space of the teacher model. On FFSVC 2020 evaluation set, our EER on Full-eval trials is relatively reduced by 13.9% compared with the fusion system result on Partial-eval trials of Task2. On Task1, compared with the winner's DenseNet result on Partial-eval trials, our minDCF on Full-eval trials is relatively reduced by 6.3%. On Task3, the EER and minDCF of our proposed method on Full-eval trials are very close to the result of the fusion system on Partial-eval trials. Our results also outperform other competitive domain adaptation methods.

cs.SD↗

arXiv2021

Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain

Non-autoregressive (NAR) models have achieved a large inference computation reduction and comparable results with autoregressive (AR) models on various sequence to sequence tasks. However, there has been limited research aiming to explore the NAR approaches on sequence to multi-sequence problems, like multi-speaker automatic speech recognition (ASR). In this study, we extend our proposed conditional chain model to NAR multi-speaker ASR. Specifically, the output of each speaker is inferred one-by-one using both the input mixture speech and previously-estimated conditional speaker features. In each step, a NAR connectionist temporal classification (CTC) encoder is used to perform parallel computation. With this design, the total inference steps will be restricted to the number of mixed speakers. Besides, we also adopt the Conformer and incorporate an intermediate CTC loss to improve the performance. Experiments on WSJ0-Mix and LibriMix corpora show that our model outperforms other NAR models with only a slight increase of latency, achieving WERs of 22.3% and 24.9%, respectively. Moreover, by including the data of variable numbers of speakers, our model can even better than the PIT-Conformer AR model with only 1/7 latency, obtaining WERs of 19.9% and 34.3% on WSJ0-2mix and WSJ0-3mix sets. All of our codes are publicly available at https://github.com/pengchengguo/espnet/tree/conditional-multispk.

eess.AS↗

arXiv2021

DCCRN+: Channel-wise Subband DCCRN with SNR Estimation for Speech Enhancement

Deep complex convolution recurrent network (DCCRN), which extends CRN with complex structure, has achieved superior performance in MOS evaluation in Interspeech 2020 deep noise suppression challenge (DNS2020). This paper further extends DCCRN with the following significant revisions. We first extend the model to sub-band processing where the bands are split and merged by learnable neural network filters instead of engineered FIR filters, leading to a faster noise suppressor trained in an end-to-end manner. Then the LSTM is further substituted with a complex TF-LSTM to better model temporal dependencies along both time and frequency axes. Moreover, instead of simply concatenating the output of each encoder layer to the input of the corresponding decoder layer, we use convolution blocks to first aggregate essential information from the encoder output before feeding it to the decoder layers. We specifically formulate the decoder with an extra a priori SNR estimation module to maintain good speech quality while removing noise. Finally a post-processing module is adopted to further suppress the unnatural residual noise. The new model, named DCCRN+, has surpassed the original DCCRN as well as several competitive models in terms of PESQ and DNSMOS, and has achieved superior performance in the new Interspeech 2021 DNS challenge

eess.AS↗

arXiv2021

F-T-LSTM based Complex Network for Joint Acoustic Echo Cancellation and Speech Enhancement

With the increasing demand for audio communication and online conference, ensuring the robustness of Acoustic Echo Cancellation (AEC) under the complicated acoustic scenario including noise, reverberation and nonlinear distortion has become a top issue. Although there have been some traditional methods that consider nonlinear distortion, they are still inefficient for echo suppression and the performance will be attenuated when noise is present. In this paper, we present a real-time AEC approach using complex neural network to better modeling the important phase information and frequency-time-LSTMs (F-T-LSTM), which scan both frequency and time axis, for better temporal modeling. Moreover, we utilize modified SI-SNR as cost function to make the model to have better echo cancellation and noise suppression (NS) performance. With only 1.4M parameters, the proposed approach outperforms the AEC-challenge baseline by 0.27 in terms of Mean Opinion Score (MOS).

cs.SD↗

arXiv2021

The Multi-speaker Multi-style Voice Cloning Challenge 2021

The Multi-speaker Multi-style Voice Cloning Challenge (M2VoC) aims to provide a common sizable dataset as well as a fair testbed for the benchmarking of the popular voice cloning task. Specifically, we formulate the challenge to adapt an average TTS model to the stylistic target voice with limited data from target speaker, evaluated by speaker identity and style similarity. The challenge consists of two tracks, namely few-shot track and one-shot track, where the participants are required to clone multiple target voices with 100 and 5 samples respectively. There are also two sub-tracks in each track. For sub-track a, to fairly compare different strategies, the participants are allowed to use only the training data provided by the organizer strictly. For sub-track b, the participants are allowed to use any data publicly available. In this paper, we present a detailed explanation on the tasks and data used in the challenge, followed by a summary of submitted systems and evaluation results.

eess.AS↗

arXiv2021

Cross-Validated Tuning of Shrinkage Factors for MVDR Beamforming Based on Regularized Covariance Matrix Estimation

This paper considers the regularized estimation of covariance matrices (CM) of high-dimensional (compound) Gaussian data for minimum variance distortionless response (MVDR) beamforming. Linear shrinkage is applied to improve the accuracy and condition number of the CM estimate for low-sample-support cases. We focus on data-driven techniques that automatically choose the linear shrinkage factors for shrinkage sample covariance matrix ($\text{S}^2$CM) and shrinkage Tyler's estimator (STE) by exploiting cross validation (CV). We propose leave-one-out cross-validation (LOOCV) choices for the shrinkage factors to optimize the beamforming performance, referred to as $\text{S}^2$CM-CV and STE-CV. The (weighted) out-of-sample output power of the beamfomer is chosen as a proxy of the beamformer performance and concise expressions of the LOOCV cost function are derived to allow fast optimization. For the large system regime, asymptotic approximations of the LOOCV cost functions are derived, yielding the $\text{S}^2$CM-AE and STE-AE. In general, the proposed algorithms are able to achieve near-oracle performance in choosing the linear shrinkage factors for MVDR beamforming. Simulation results are provided for validating the proposed methods.

eess.SP↗