Jian Wu

Sanyuan Chen, Yu Wu, Zhuo Chen et al.

Transformer has been successfully applied to speech separation recently with its strong long-dependency modeling capacity using a self-attention mechanism. However, Transformer tends to have heavy run-time costs due to the deep encoder layers, which hinders its deployment on edge devices. A small Transformer model with fewer encoder layers is preferred for computational efficiency, but it is prone to performance degradation. In this paper, an ultra fast speech separation Transformer model is proposed to achieve both better performance and efficiency with teacher student learning (T-S learning). We introduce layer-wise T-S learning and objective shifting mechanisms to guide the small student model to learn intermediate representations from the large teacher model. Compared with the small Transformer model trained from scratch, the proposed T-S learning method reduces the word error rate (WER) by more than 5% for both multi-channel and single-channel speech separation on LibriCSS dataset. Utilizing more unlabeled speech data, our ultra fast speech separation models achieve more than 10% relative WER reduction.

Jing Pan, Jian Wu, Yashesh Gaur et al.

We present a cost-effective method to integrate speech into a large language model (LLM), resulting in a Contextual Speech Model with Instruction-following/in-context-learning Capabilities (COSMIC) multi-modal LLM. Using GPT-3.5, we generate Speech Comprehension Test Question-Answer (SQA) pairs from speech transcriptions for supervised instruction tuning. With under 30 million trainable parameters and only 450 hours of English speech data, COSMIC demonstrates emerging capabilities in instruction-following and in-context learning. Equipped with such capabilities, COSMIC achieves a maximum 33.18 BLEU score in 0-shot EN-to-X speech to text translation (S2TT) and a significant boost in the 1-shot setting. Additionally, there is an average 25.8\% relative Word Error Rate (WER) reduction for 1-shot cross-domain adaptation. COSMIC exhibits a significant automatic speech recognition (ASR) accuracy gain in contextual biasing tasks due to its instruction-following capability.

Mohammad Soleymanpour, Mahmoud Al Ismail, Fahimeh Bahmaninezhad et al.

We introduce a bilingual solution to support English as secondary locale for most primary locales in hybrid automatic speech recognition (ASR) settings. Our key developments constitute: (a) pronunciation lexicon with grapheme units instead of phone units, (b) a fully bilingual alignment model and subsequently bilingual streaming transformer model, (c) a parallel encoder structure with language identification (LID) loss, (d) parallel encoder with an auxiliary loss for monolingual projections. We conclude that in comparison to LID loss, our proposed auxiliary loss is superior in specializing the parallel encoders to respective monolingual locales, and that contributes to stronger bilingual learning. We evaluate our work on large-scale training and test tasks for bilingual Spanish (ES) and bilingual Italian (IT) applications. Our bilingual models demonstrate strong English code-mixing capability. In particular, the bilingual IT model improves the word error rate (WER) for a code-mix IT task from 46.5% to 13.8%, while also achieving a close parity (9.6%) with the monolingual IT model (9.5%) over IT tests.

Jiahuan Yan, Bo Zheng, Hongxia Xu et al.

The transferability of deep neural networks (DNNs) has made significant progress in image and language processing. However, due to the heterogeneity among tables, such DNN bonus is still far from being well exploited on tabular data prediction (e.g., regression or classification tasks). Condensing knowledge from diverse domains, language models (LMs) possess the capability to comprehend feature names from various tables, potentially serving as versatile learners in transferring knowledge across distinct tables and diverse prediction tasks, but their discrete text representation space is inherently incompatible with numerical feature values in tables. In this paper, we present TP-BERTa, a specifically pre-trained LM for tabular data prediction. Concretely, a novel relative magnitude tokenization converts scalar numerical feature values to finely discrete, high-dimensional tokens, and an intra-feature attention approach integrates feature values with the corresponding feature names. Comprehensive experiments demonstrate that our pre-trained TP-BERTa leads the performance among tabular DNNs and is competitive with Gradient Boosted Decision Tree models in typical tabular data regime.

Shangde Gao, Yichao Fu, Ke Liu et al.

Recently, many foundation models for medical image analysis such as MedSAM, SwinUNETR have been released and proven to be useful in multiple tasks. However, considering the inherent heterogeneity and inhomogeneity of real-world medical data, directly applying these models to specific medical image segmentation tasks often leads to negative domain shift effects, which can severely weaken the model's segmentation capabilities. To this end, we propose an adaptive amalgamation knowledge framework that aims to train a versatile foundation model to handle the joint goals of multiple expert models, each specialized for a distinct task. Specifically, we first train an nnUNet-based expert model for each task, and reuse the pre-trained SwinUNTER as the target foundation model. Then, the input data for all challenging tasks are encoded in the foundation model and the expert models, respectively, and their backbone features are jointly projected into the adaptive amalgamation layer. Within the hidden layer, the hierarchical attention mechanisms are designed to achieve adaptive merging of the target model to the hidden layer feature knowledge of all experts, which significantly reduces the domain shift arising from the inter-task differences. Finally, the gold amalgamated features and the prompt features are fed into the mask decoder to obtain the segmentation results. Extensive experiments conducted in these challenging tasks demonstrate the effectiveness and adaptability of our foundation model for real-world medical image segmentation.

Sanyuan Chen, Chengyi Wang, Zhengyang Chen et al.

Self-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks. As speech signal contains multi-faceted information including speaker identity, paralinguistics, spoken content, etc., learning universal representations for all speech tasks is challenging. To tackle the problem, we propose a new pre-trained model, WavLM, to solve full-stack downstream speech tasks. WavLM jointly learns masked speech prediction and denoising in pre-training. By this means, WavLM does not only keep the speech content modeling capability by the masked speech prediction, but also improves the potential to non-ASR tasks by the speech denoising. In addition, WavLM employs gated relative position bias for the Transformer structure to better capture the sequence ordering of input speech. We also scale up the training dataset from 60k hours to 94k hours. WavLM Large achieves state-of-the-art performance on the SUPERB benchmark, and brings significant improvements for various speech processing tasks on their representative benchmarks. The code and pre-trained models are available at https://aka.ms/wavlm.

Mingzhi Yu, Diane Litman, Shuang Ma et al.

Linguistic entrainment is a phenomenon where people tend to mimic each other in conversation. The core instrument to quantify entrainment is a linguistic similarity measure between conversational partners. Most of the current similarity measures are based on bag-of-words approaches that rely on linguistic markers, ignoring the overall language structure and dialogue context. To address this issue, we propose to use a neural network model to perform the similarity measure for entrainment. Our model is context-aware, and it further leverages a novel component to learn the shared high-level linguistic features across dialogues. We first investigate the effectiveness of our novel component. Then we use the model to perform similarity measure in a corpus-based entrainment analysis. We observe promising results for both evaluation tasks.

Naoyuki Kanda, Xiong Xiao, Jian Wu et al.

Speaker-attributed automatic speech recognition (SA-ASR) is a task to recognize "who spoke what" from multi-talker recordings. An SA-ASR system usually consists of multiple modules such as speech separation, speaker diarization and ASR. On the other hand, considering the joint optimization, an end-to-end (E2E) SA-ASR model has recently been proposed with promising results on simulation data. In this paper, we present our recent study on the comparison of such modular and joint approaches towards SA-ASR on real monaural recordings. We develop state-of-the-art SA-ASR systems for both modular and joint approaches by leveraging large-scale training data, including 75 thousand hours of ASR training data and the VoxCeleb corpus for speaker representation learning. We also propose a new pipeline that performs the E2E SA-ASR model after speaker clustering. Our evaluation on the AMI meeting corpus reveals that after fine-tuning with a small real data, the joint system performs 8.9--29.9% better in accuracy compared to the best modular system while the modular system performs better before such fine-tuning. We also conduct various error analyses to show the remaining issues for the monaural SA-ASR.

Jian Wu, Zhuo Chen, Sanyuan Chen et al.

Speech separation has been successfully applied as a frontend processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic speech recognition (ASR). However, a speech separation model often introduces target speech distortion, resulting in a sub-optimum word error rate (WER). In this paper, we describe our efforts to improve the performance of a single channel speech separation system. Specifically, we investigate a two-stage training scheme that firstly applies a feature level optimization criterion for pretraining, followed by an ASR-oriented optimization criterion using an end-to-end (E2E) speech recognition model. Meanwhile, to keep the model light-weight, we introduce a modified teacher-student learning technique for model compression. By combining those approaches, we achieve a absolute average WER improvement of 2.70% and 0.77% using models with less than 10M parameters compared with the previous state-of-the-art results on the LibriCSS dataset for utterance-wise evaluation and continuous evaluation, respectively

Amber Afshan, Kshitiz Kumar, Jian Wu

Scores from traditional confidence classifiers (CCs) in automatic speech recognition (ASR) systems lack universal interpretation and vary with updates to the underlying confidence or acoustic models (AMs). In this work, we build interpretable confidence scores with an objective to closely align with ASR accuracy. We propose a new sequence-level CC with a richer context providing CC scores highly correlated with ASR accuracy and scores stable across CC updates. Hence, expanding CC applications. Recently, AM customization has gained traction with the widespread use of unified models. Conventional adaptation strategies that customize AM expect well-matched data for the target domain with gold-standard transcriptions. We propose a cost-effective method of using CC scores to select an optimal adaptation data set, where we maximize ASR gains from minimal data. We study data in various confidence ranges and optimally choose data for AM adaptation with KL-Divergence regularization. On the Microsoft voice search task, data selection for supervised adaptation using the sequence-level confidence scores achieves word error rate reduction (WERR) of 8.5% for row-convolution LSTM (RC-LSTM) and 5.2% for latency-controlled bidirectional LSTM (LC-BLSTM). In the semi-supervised case, with ASR hypotheses as labels, our method provides WERR of 5.9% and 2.8% for RC-LSTM and LC-BLSTM, respectively.

Jixuan Wang, Xiong Xiao, Jian Wu et al.

Speaker attribution is required in many real-world applications, such as meeting transcription, where speaker identity is assigned to each utterance according to speaker voice profiles. In this paper, we propose to solve the speaker attribution problem by using graph-based semi-supervised learning methods. A graph of speech segments is built for each session, on which segments from voice profiles are represented by labeled nodes while segments from test utterances are unlabeled nodes. The weight of edges between nodes is evaluated by the similarities between the pretrained speaker embeddings of speech segments. Speaker attribution then becomes a semi-supervised learning problem on graphs, on which two graph-based methods are applied: label propagation (LP) and graph neural networks (GNNs). The proposed approaches are able to utilize the structural information of the graph to improve speaker attribution performance. Experimental results on real meeting data show that the graph based approaches reduce speaker attribution error by up to 68% compared to a baseline speaker identification approach that processes each utterance independently.

Yuxiang Kong, Jian Wu, Quandong Wang et al.

The front-end module in multi-channel automatic speech recognition (ASR) systems mainly use microphone array techniques to produce enhanced signals in noisy conditions with reverberation and echos. Recently, neural network (NN) based front-end has shown promising improvement over the conventional signal processing methods. In this paper, we propose to adopt the architecture of deep complex Unet (DCUnet) - a powerful complex-valued Unet-structured speech enhancement model - as the front-end of the multi-channel acoustic model, and integrate them in a multi-task learning (MTL) framework along with cascaded framework for comparison. Meanwhile, we investigate the proposed methods with several training strategies to improve the recognition accuracy on the 1000-hours real-world XiaoMi smart speaker data with echos. Experiments show that our proposed DCUnet-MTL method brings about 12.2% relative character error rate (CER) reduction compared with the traditional approach with array processing plus single-channel acoustic model. It also achieves superior performance than the recently proposed neural beamforming method.

Yihui Fu, Jian Wu, Yanxin Hu et al.

In this paper, we propose a multi-channel network for simultaneous speech dereverberation, enhancement and separation (DESNet). To enable gradient propagation and joint optimization, we adopt the attentional selection mechanism of the multi-channel features, which is originally proposed in end-to-end unmixing, fixed-beamforming and extraction (E2E-UFE) structure. Furthermore, the novel deep complex convolutional recurrent network (DCCRN) is used as the structure of the speech unmixing and the neural network based weighted prediction error (WPE) is cascaded beforehand for speech dereverberation. We also introduce the staged SNR strategy and symphonic loss for the training of the network to further improve the final performance. Experiments show that in non-dereverberated case, the proposed DESNet outperforms DCCRN and most state-of-the-art structures in speech enhancement and separation, while in dereverberated scenario, DESNet also shows improvements over the cascaded WPE-DCCRN networks.

Xiong Xiao, Naoyuki Kanda, Zhuo Chen et al.

This paper describes the Microsoft speaker diarization system for monaural multi-talker recordings in the wild, evaluated at the diarization track of the VoxCeleb Speaker Recognition Challenge(VoxSRC) 2020. We will first explain our system design to address issues in handling real multi-talker recordings. We then present the details of the components, which include Res2Net-based speaker embedding extractor, conformer-based continuous speech separation with leakage filtering, and a modified DOVER (short for Diarization Output Voting Error Reduction) method for system fusion. We evaluate the systems with the data set provided by VoxSRCchallenge 2020, which contains real-life multi-talker audio collected from YouTube. Our best system achieves 3.71% and 6.23% of the diarization error rate (DER) on development set and evaluation set, respectively, being ranked the 1st at the diarization track of the challenge.

Jian Wu, Zhuo Chen, Jinyu Li et al.

Multi-speaker speech recognition has been one of the keychallenges in conversation transcription as it breaks the singleactive speaker assumption employed by most state-of-the-artspeech recognition systems. Speech separation is consideredas a remedy to this problem. Previously, we introduced a sys-tem, calledunmixing,fixed-beamformerandextraction(UFE),that was shown to be effective in addressing the speech over-lap problem in conversation transcription. With UFE, an inputmixed signal is processed by fixed beamformers, followed by aneural network post filtering. Although promising results wereobtained, the system contains multiple individually developedmodules, leading potentially sub-optimum performance. In thiswork, we introduce an end-to-end modeling version of UFE. Toenable gradient propagation all the way, an attentional selectionmodule is proposed, where an attentional weight is learnt foreach beamformer and spatial feature sampled over space. Ex-perimental results show that the proposed system achieves com-parable performance in an offline evaluation with the originalseparate processing-based pipeline, while producing remark-able improvements in an online evaluation.

Sanyuan Chen, Yu Wu, Zhuo Chen et al.

Continuous speech separation plays a vital role in complicated speech related tasks such as conversation transcription. The separation model extracts a single speaker signal from a mixed speech. In this paper, we use transformer and conformer in lieu of recurrent neural networks in the separation system, as we believe capturing global information with the self-attention based method is crucial for the speech separation. Evaluating on the LibriCSS dataset, the conformer separation model achieves state of the art results, with a relative 23.5% word error rate (WER) reduction from bi-directional LSTM (BLSTM) in the utterance-wise evaluation and a 15.4% WER reduction in the continuous evaluation.

Haohe Liu, Lei Xie, Jian Wu et al.

This paper presents a new input format, channel-wise subband input (CWS), for convolutional neural networks (CNN) based music source separation (MSS) models in the frequency domain. We aim to address the major issues in CNN-based high-resolution MSS model: high computational cost and weight sharing between distinctly different bands. Specifically, in this paper, we decompose the input mixture spectra into several bands and concatenate them channel-wise as the model input. The proposed approach enables effective weight sharing in each subband and introduces more flexibility between channels. For comparison purposes, we perform voice and accompaniment separation (VAS) on models with different scales, architectures, and CWS settings. Experiments show that the CWS input is beneficial in many aspects. We evaluate our method on musdb18hq test set, focusing on SDR, SIR and SAR metrics. Among all our experiments, CWS enables models to obtain 6.9% performance gain on the average metrics. With even a smaller number of parameters, less training data, and shorter training time, our MDenseNet with 8-bands CWS input still surpasses the original MMDenseNet with a large margin. Moreover, CWS also reduces computational cost and training time to a large extent.

Li Zhang, Jian Wu, Lei Xie

This paper describes the NPU system submitted to Interspeech 2020 Far-Field Speaker Verification Challenge (FFSVC). We particularly focus on far-field text-dependent SV from single (task1) and multiple microphone arrays (task3). The major challenges in such scenarios are short utterance and cross-channel and distance mismatch for enrollment and test. With the belief that better speaker embedding can alleviate the effects from short utterance, we introduce a new speaker embedding architecture - ResNet-BAM, which integrates a bottleneck attention module with ResNet as a simple and efficient way to further improve the representation power of ResNet. This contribution brings up to 1% EER reduction. We further address the mismatch problem in three directions. First, domain adversarial training, which aims to learn domain-invariant features, can yield to 0.8% EER reduction. Second, front-end signal processing, including WPE and beamforming, has no obvious contribution, but together with data selection and domain adversarial training, can further contribute to 0.5% EER reduction. Finally, data augmentation, which works with a specifically-designed data selection strategy, can lead to 2% EER reduction. Together with the above contributions, in the middle challenge results, our single submission system (without multi-system fusion) achieves the first and second place on task 1 and task 3, respectively.

Yanxin Hu, Yun Liu, Shubo Lv et al.

Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods focus on predicting TF-masks or speech spectrum, via a naive convolution neural network (CNN) or recurrent neural network (RNN). Some recent studies use complex-valued spectrogram as a training target but train in a real-valued network, predicting the magnitude and phase component or real and imaginary part, respectively. Particularly, convolution recurrent network (CRN) integrates a convolutional encoder-decoder (CED) structure and long short-term memory (LSTM), which has been proven to be helpful for complex targets. In order to train the complex target more effectively, in this paper, we design a new network structure simulating the complex-valued operation, called Deep Complex Convolution Recurrent Network (DCCRN), where both CNN and RNN structures can handle complex-valued operation. The proposed DCCRN models are very competitive over other previous networks, either on objective or subjective metric. With only 3.7M parameters, our DCCRN models submitted to the Interspeech 2020 Deep Noise Suppression (DNS) challenge ranked first for the real-time-track and second for the non-real-time track in terms of Mean Opinion Score (MOS).

Tianyan Zhou, Yong Zhao, Jian Wu

The ResNet-based architecture has been widely adopted to extract speaker embeddings for text-independent speaker verification systems. By introducing the residual connections to the CNN and standardizing the residual blocks, the ResNet structure is capable of training deep networks to achieve highly competitive recognition performance. However, when the input feature space becomes more complicated, simply increasing the depth and width of the ResNet network may not fully realize its performance potential. In this paper, we present two extensions of the ResNet architecture, ResNeXt and Res2Net, for speaker verification. Originally proposed for image recognition, the ResNeXt and Res2Net introduce two more dimensions, cardinality and scale, in addition to depth and width, to improve the model's representation capacity. By increasing the scale dimension, the Res2Net model can represent multi-scale features with various granularities, which particularly facilitates speaker verification for short utterances. We evaluate our proposed systems on three speaker verification tasks. Experiments on the VoxCeleb test set demonstrated that the ResNeXt and Res2Net can significantly outperform the conventional ResNet model. The Res2Net model achieved superior performance by reducing the EER by 18.5% relative. Experiments on the other two internal test sets of mismatched conditions further confirmed the generalization of the ResNeXt and Res2Net architectures against noisy environment and segment length variations.

Jixuan Wang, Xiong Xiao, Jian Wu et al.

Deep speaker embedding models have been commonly used as a building block for speaker diarization systems; however, the speaker embedding model is usually trained according to a global loss defined on the training data, which could be sub-optimal for distinguishing speakers locally in a specific meeting session. In this work we present the first use of graph neural networks (GNNs) for the speaker diarization problem, utilizing a GNN to refine speaker embeddings locally using the structural information between speech segments inside each session. The speaker embeddings extracted by a pre-trained model are remapped into a new embedding space, in which the different speakers within a single session are better separated. The model is trained for linkage prediction in a supervised manner by minimizing the difference between the affinity matrix constructed by the refined embeddings and the ground-truth adjacency matrix. Spectral clustering is then applied on top of the refined embeddings. We show that the clustering performance of the refined speaker embeddings outperforms the original embeddings significantly on both simulated and real meeting data, and our system achieves the state-of-the-art result on the NIST SRE 2000 CALLHOME database.

Zhuo Chen, Takuya Yoshioka, Liang Lu et al.

This paper describes a dataset and protocols for evaluating continuous speech separation algorithms. Most prior studies on speech separation use pre-segmented signals of artificially mixed speech utterances which are mostly \emph{fully} overlapped, and the algorithms are evaluated based on signal-to-distortion ratio or similar performance metrics. However, in natural conversations, a speech signal is continuous, containing both overlapped and overlap-free components. In addition, the signal-based metrics have very weak correlations with automatic speech recognition (ASR) accuracy. We think that not only does this make it hard to assess the practical relevance of the tested algorithms, it also hinders researchers from developing systems that can be readily applied to real scenarios. In this paper, we define continuous speech separation (CSS) as a task of generating a set of non-overlapped speech signals from a \textit{continuous} audio stream that contains multiple utterances that are \emph{partially} overlapped by a varying degree. A new real recorded dataset, called LibriCSS, is derived from LibriSpeech by concatenating the corpus utterances to simulate a conversation and capturing the audio replays with far-field microphones. A Kaldi-based ASR evaluation protocol is also established by using a well-trained multi-conditional acoustic model. By using this dataset, several aspects of a recently proposed speaker-independent CSS algorithm are investigated. The dataset and evaluation scripts are available to facilitate the research in this direction.

Jianwei Yu, Shi-Xiong Zhang, Jian Wu et al.

Automatic recognition of overlapped speech remains a highly challenging task to date. Motivated by the bimodal nature of human speech perception, this paper investigates the use of audio-visual technologies for overlapped speech recognition. Three issues associated with the construction of audio-visual speech recognition (AVSR) systems are addressed. First, the basic architecture designs i.e. end-to-end and hybrid of AVSR systems are investigated. Second, purposefully designed modality fusion gates are used to robustly integrate the audio and visual features. Third, in contrast to a traditional pipelined architecture containing explicit speech separation and recognition components, a streamlined and integrated AVSR system optimized consistently using the lattice-free MMI (LF-MMI) discriminative criterion is also proposed. The proposed LF-MMI time-delay neural network (TDNN) system establishes the state-of-the-art for the LRS2 dataset. Experiments on overlapped speech simulated from the LRS2 dataset suggest the proposed AVSR system outperformed the audio only baseline LF-MMI DNN system by up to 29.98\% absolute in word error rate (WER) reduction, and produced recognition performance comparable to a more complex pipelined system. Consistent performance improvements of 4.89\% absolute in WER reduction over the baseline AVSR system using feature fusion are also obtained.

Fahimeh Bahmaninezhad, Jian Wu, Rongzhi Gu et al.

Speech separation has been studied widely for single-channel close-talk microphone recordings over the past few years; developed solutions are mostly in frequency-domain. Recently, a raw audio waveform separation network (TasNet) is introduced for single-channel data, with achieving high Si-SNR (scale-invariant source-to-noise ratio) and SDR (source-to-distortion ratio) comparing against the state-of-the-art solution in frequency-domain. In this study, we incorporate effective components of the TasNet into a frequency-domain separation method. We compare both for alternative scenarios. We introduce a solution for directly optimizing the separation criterion in frequency-domain networks. In addition to speech separation objective and subjective measurements, we evaluate the separation performance on a speech recognition task as well. We study the speech separation problem for far-field data (more similar to naturalistic audio streams) and develop multi-channel solutions for both frequency and time-domain separators with utilizing spectral, spatial and speaker location information. For our experiments, we simulated multi-channel spatialized reverberate WSJ0-2mix dataset. Our experimental results show that spectrogram separation can achieve competitive performance with better network design. Multi-channel framework as well is shown to improve the single-channel performance relatively up to +35.5% and +46% in terms of WER and SDR, respectively.

Xingde Ying, Heng Guo, Kai Ma et al.

Computed tomography (CT) can provide a 3D view of the patient's internal organs, facilitating disease diagnosis, but it incurs more radiation dose to a patient and a CT scanner is much more cost prohibitive than an X-ray machine too. Traditional CT reconstruction methods require hundreds of X-ray projections through a full rotational scan of the body, which cannot be performed on a typical X-ray machine. In this work, we propose to reconstruct CT from two orthogonal X-rays using the generative adversarial network (GAN) framework. A specially designed generator network is exploited to increase data dimension from 2D (X-rays) to 3D (CT), which is not addressed in previous research of GAN. A novel feature fusion method is proposed to combine information from two X-rays.The mean squared error (MSE) loss and adversarial loss are combined to train the generator, resulting in a high-quality CT volume both visually and quantitatively. Extensive experiments on a publicly available chest CT dataset demonstrate the effectiveness of the proposed method. It could be a nice enhancement of a low-cost X-ray machine to provide physicians a CT-like 3D volume in several niche applications.

Rongzhi Gu, Jian Wu, Shi-Xiong Zhang et al.

The end-to-end approach for single-channel speech separation has been studied recently and shown promising results. This paper extended the previous approach and proposed a new end-to-end model for multi-channel speech separation. The primary contributions of this work include 1) an integrated waveform-in waveform-out separation system in a single neural network architecture. 2) We reformulate the traditional short time Fourier transform (STFT) and inter-channel phase difference (IPD) as a function of time-domain convolution with a special kernel. 3) We further relaxed those fixed kernels to be learnable, so that the entire architecture becomes purely data-driven and can be trained from end-to-end. We demonstrate on the WSJ0 far-field speech separation task that, with the benefit of learnable spatial features, our proposed end-to-end multi-channel model significantly improved the performance of previous end-to-end single-channel method and traditional multi-channel methods.

Jian Wu, Yong Xu, Shi-Xiong Zhang et al.

This paper summarizes several follow-up contributions for improving our submitted NWPU speaker-dependent system for CHiME-5 challenge, which aims to solve the problem of multi-channel, highly-overlapped conversational speech recognition in a dinner party scenario with reverberations and non-stationary noises. We adopt a speaker-aware training method by using i-vector as the target speaker information for multi-talker speech separation. With only one unified separation model for all speakers, we achieve a 10\% absolute improvement in terms of word error rate (WER) over the previous baseline of 80.28\% on the development set by leveraging our newly proposed data processing techniques and beamforming approach. With our improved back-end acoustic model, we further reduce WER to 60.15\% which surpasses the result of our submitted CHiME-5 challenge system without applying any fusion techniques.

Jian Wu, Yong Xu, Shi-Xiong Zhang et al.

Audio-visual multi-modal modeling has been demonstrated to be effective in many speech related tasks, such as speech recognition and speech enhancement. This paper introduces a new time-domain audio-visual architecture for target speaker extraction from monaural mixtures. The architecture generalizes the previous TasNet (time-domain speech separation network) to enable multi-modal learning and at meanwhile it extends the classical audio-visual speech separation from frequency-domain to time-domain. The main components of proposed architecture include an audio encoder, a video encoder that extracts lip embedding from video streams, a multi-modal separation network and an audio decoder. Experiments on simulated mixtures based on recently released LRS2 dataset show that our method can bring 3dB+ and 4dB+ Si-SNR improvements on two- and three-speaker cases respectively, compared to audio-only TasNet and frequency-domain audio-visual networks

Jian Wu, Changran Hu, Yulong Wang et al.

In recent years, neural networks have been used to generate symbolic melodies. However, the long-term structure in the melody has posed great difficulty for designing a good model. In this paper, we present a hierarchical recurrent neural network for melody generation, which consists of three Long-Short-Term-Memory (LSTM) subnetworks working in a coarse-to-fine manner along time. Specifically, the three subnetworks generate bar profiles, beat profiles and notes in turn, and the output of the high-level subnetworks are fed into the low-level subnetworks, serving as guidance for generating the finer time-scale melody components in low-level subnetworks. Two human behavior experiments demonstrate the advantage of this structure over the single-layer LSTM which attempts to learn all hidden structures in melodies. Compared with the state-of-the-art models MidiNet and MusicVAE, the hierarchical recurrent neural network produces better melodies evaluated by humans.