CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR

In this work, we propose CleanMel, a single-channel Mel-spectrogram denoising and dereverberation network for improving both speech quality and automatic speech recognition (ASR) performance. The proposed network takes as input the noisy and reverberant microphone recording and predicts the corresponding clean Mel-spectrogram. The enhanced Mel-spectrogram can be either transformed to speech waveform with a neural vocoder or directly used for ASR. The proposed network is composed of interleaved cross-band and narrow-band processing in the Mel-frequency domain, for learning the full-band spectral pattern and the narrow-band properties of signals, respectively. Compared to linear-frequency domain or time-domain speech enhancement, the key advantage of Mel-spectrogram enhancement is that Mel-frequency presents speech in a more compact way and thus is easier to learn, which will benefit both speech quality and ASR. Experimental results on four English and one Chinese datasets demonstrate a significant improvement in both speech quality and ASR performance achieved by the proposed model. Code and audio examples of our model are available online in https://audio.westlake.edu.cn/Research/CleanMel.html.

VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identification

Reverberant speech, denoting the speech signal degraded by the process of reverberation, contains crucial knowledge of both anechoic source speech and room impulse response (RIR). This work proposes a variational Bayesian inference (VBI) framework with neural speech prior (VINP) for joint speech dereverberation and blind RIR identification. In VINP, a probabilistic signal model is constructed in the time-frequency (T-F) domain based on convolution transfer function (CTF) approximation. For the first time, we propose using an arbitrary discriminative dereverberation deep neural network (DNN) to predict the prior distribution of anechoic speech within a probabilistic model. By integrating both reverberant speech and the anechoic speech prior, VINP yields the maximum a posteriori (MAP) and maximum likelihood (ML) estimations of the anechoic speech spectrum and CTF filter, respectively. After simple transformations, the waveforms of anechoic speech and RIR are estimated. Moreover, VINP is effective for automatic speech recognition (ASR) systems, which sets it apart from most deep learning (DL)-based single-channel dereverberation approaches. Experiments on single-channel speech dereverberation demonstrate that VINP reaches an advanced level in most metrics related to human perception and displays unquestionable state-of-the-art (SOTA) performance in ASR-related metrics. For blind RIR identification, experiments indicate that VINP attains the SOTA level in blind estimation of reverberation time at 60 dB (RT60) and direct-to-reverberation ratio (DRR). Codes and audio samples are available online.

Evaluating the Design Features of an Intelligent Tutoring System for Advanced Mathematics Learning

Xiaomai is an intelligent tutoring system (ITS) designed to help Chinese college students in learning advanced mathematics and preparing for the graduate school math entrance exam. This study investigates two distinctive features within Xiaomai: the incorporation of free-response questions with automatic feedback and the metacognitive element of reflecting on self-made errors.

RealMAN: A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and Localization

The training of deep learning-based multichannel speech enhancement and source localization systems relies heavily on the simulation of room impulse response and multichannel diffuse noise, due to the lack of large-scale real-recorded datasets. However, the acoustic mismatch between simulated and real-world data could degrade the model performance when applying in real-world scenarios. To bridge this simulation-to-real gap, this paper presents a new relatively large-scale Real-recorded and annotated Microphone Array speech&Noise (RealMAN) dataset. The proposed dataset is valuable in two aspects: 1) benchmarking speech enhancement and localization algorithms in real scenarios; 2) offering a substantial amount of real-world training data for potentially improving the performance of real-world applications. Specifically, a 32-channel array with high-fidelity microphones is used for recording. A loudspeaker is used for playing source speech signals. A total of 83-hour speech signals (48 hours for static speaker and 35 hours for moving speaker) are recorded in 32 different scenes, and 144 hours of background noise are recorded in 31 different scenes. Both speech and noise recording scenes cover various common indoor, outdoor, semi-outdoor and transportation environments, which enables the training of general-purpose speech enhancement and source localization networks. To obtain the task-specific annotations, the azimuth angle of the loudspeaker is annotated with an omni-direction fisheye camera by automatically detecting the loudspeaker. The direct-path signal is set as the target clean speech for speech enhancement, which is obtained by filtering the source speech signal with an estimated direct-path propagation filter.

Converting High-Performance and Low-Latency SNNs through Explicit Modelling of Residual Error in ANNs

Spiking neural networks (SNNs) have garnered interest due to their energy efficiency and superior effectiveness on neuromorphic chips compared with traditional artificial neural networks (ANNs). One of the mainstream approaches to implementing deep SNNs is the ANN-SNN conversion, which integrates the efficient training strategy of ANNs with the energy-saving potential and fast inference capability of SNNs. However, under extreme low-latency conditions, the existing conversion theory suggests that the problem of misrepresentation of residual membrane potentials in SNNs, i.e., the inability of IF neurons with a reset-by-subtraction mechanism to respond to residual membrane potentials beyond the range from resting potential to threshold, leads to a performance gap in the converted SNNs compared to the original ANNs. This severely limits the possibility of practical application of SNNs on delay-sensitive edge devices. Existing conversion methods addressing this problem usually involve modifying the state of the conversion spiking neurons. However, these methods do not consider their adaptability and compatibility with neuromorphic chips. We propose a new approach based on explicit modeling of residual errors as additive noise. The noise is incorporated into the activation function of the source ANN, which effectively reduces the residual error. Our experiments on the CIFAR10/100 dataset verify that our approach exceeds the prevailing ANN-SNN conversion methods and directly trained SNNs concerning accuracy and the required time steps. Overall, our method provides new ideas for improving SNN performance under ultra-low-latency conditions and is expected to promote practical neuromorphic hardware applications for further development.

Mel-FullSubNet: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR

In this work, we propose Mel-FullSubNet, a single-channel Mel-spectrogram denoising and dereverberation network for improving both speech quality and automatic speech recognition (ASR) performance. Mel-FullSubNet takes as input the noisy and reverberant Mel-spectrogram and predicts the corresponding clean Mel-spectrogram. The enhanced Mel-spectrogram can be either transformed to speech waveform with a neural vocoder or directly used for ASR. Mel-FullSubNet encapsulates interleaved full-band and sub-band networks, for learning the full-band spectral pattern of signals and the sub-band/narrow-band properties of signals, respectively. Compared to linear-frequency domain or time-domain speech enhancement, the major advantage of Mel-spectrogram enhancement is that Mel-frequency presents speech in a more compact way and thus is easier to learn, which will benefit both speech quality and ASR. Experimental results demonstrate a significant improvement in both speech quality and ASR performance achieved by the proposed model.

Unimodal Aggregation for CTC-based Speech Recognition

This paper works on non-autoregressive automatic speech recognition. A unimodal aggregation (UMA) is proposed to segment and integrate the feature frames that belong to the same text token, and thus to learn better feature representations for text tokens. The frame-wise features and weights are both derived from an encoder. Then, the feature frames with unimodal weights are integrated and further processed by a decoder. Connectionist temporal classification (CTC) loss is applied for training. Compared to the regular CTC, the proposed method learns better feature representations and shortens the sequence length, resulting in lower recognition error and computational complexity. Experiments on three Mandarin datasets show that UMA demonstrates superior or comparable performance to other advanced non-autoregressive methods, such as self-conditioned CTC. Moreover, by integrating self-conditioned CTC into the proposed framework, the performance can be further noticeably improved.

Autoencoder Based Residual Deep Networks for Robust Regression Prediction and Spatiotemporal Estimation

To have a superior generalization, a deep learning neural network often involves a large size of training sample. With increase of hidden layers in order to increase learning ability, neural network has potential degradation in accuracy. Both could seriously limit applicability of deep learning in some domains particularly involving predictions of continuous variables with a small size of samples. Inspired by residual convolutional neural network in computer vision and recent findings of crucial shortcuts in the brains in neuroscience, we propose an autoencoder-based residual deep network for robust prediction. In a nested way, we leverage shortcut connections to implement residual mapping with a balanced structure for efficient propagation of error signals. The novel method is demonstrated by multiple datasets, imputation of high spatiotemporal resolution non-randomness missing values of aerosol optical depth, and spatiotemporal estimation of fine particulate matter <2.5 \mu m, achieving the cutting edge of accuracy and efficiency. Our approach is also a general-purpose regression learner to be applicable in diverse domains.