Search

The majority of existing speech bandwidth extension (BWE) methods operate under the constraint of fixed source and target sampling rates, which limits their flexibility in practical applications. In this paper, we propose a multi-stage speech BWE model named MS-BWE, which can handle a set of source and target sampling rate pairs and achieve flexible extensions of frequency bandwidth. The proposed MS-BWE model comprises a cascade of BWE blocks, with each block featuring a dual-stream architecture to realize amplitude and phase extension, progressively painting the speech frequency bands stage by stage. The teacher-forcing strategy is employed to mitigate the discrepancy between training and inference. Experimental results demonstrate that our proposed MS-BWE is comparable to state-of-the-art speech BWE methods in speech quality. Regarding generation efficiency, the one-stage generation of MS-BWE can achieve over one thousand times real-time on GPU and about sixty times on CPU., Comment: Accepted by Interspeech 2024

This paper proposes a novel bidirectional neural vocoder, named BiVocoder, capable both of feature extraction and reverse waveform generation within the short-time Fourier transform (STFT) domain. For feature extraction, the BiVocoder takes amplitude and phase spectra derived from STFT as inputs, transforms them into long-frame-shift and low-dimensional features through convolutional neural networks. The extracted features are demonstrated suitable for direct prediction by acoustic models, supporting its application in text-to-speech (TTS) task. For waveform generation, the BiVocoder restores amplitude and phase spectra from the features by a symmetric network, followed by inverse STFT to reconstruct the speech waveform. Experimental results show that our proposed BiVocoder achieves better performance compared to some baseline vocoders, by comprehensively considering both synthesized speech quality and inference speed for both analysis-synthesis and TTS tasks., Comment: Accepted by Interspeech 2024

Our main result is a polynomial time algorithm for deciding realizability for the GXU sublogic of linear temporal logic. This logic is particularly suitable for the specification of embedded control systems, and it is more expressive than GR(1). Reactive control programs for GXU specifications are represented as Mealy machines, which are extended by the monitoring of input events. Now, realizability for GXU specifications is shown to be equivalent to solving a certain subclass of 2QBF satisfiability problems. These logical problems can be solved in cubic time in the size of GXU specifications. For unrealizable GXU specifications, stronger environment assumptions are mined from failed consistency checks based on Padoa's characterization of definability and Craig interpolation.

Recently, Large Language Models (LLMs) have been widely adopted in a wide range of tasks, leading to increasing attention towards the research on how scaling LLMs affects their performance. Existing works, termed Scaling Laws, have discovered that the final test loss of LLMs scales as power-laws with model size, computational budget, and dataset size. However, the temporal change of the test loss of an LLM throughout its pre-training process remains unexplored, though it is valuable in many aspects, such as selecting better hyperparameters \textit{directly} on the target LLM. In this paper, we propose the novel concept of Temporal Scaling Law, studying how the test loss of an LLM evolves as the training steps scale up. In contrast to modeling the test loss as a whole in a coarse-grained manner, we break it down and dive into the fine-grained test loss of each token position, and further develop a dynamic hyperbolic-law. Afterwards, we derive the much more precise temporal scaling law by studying the temporal patterns of the parameters in the dynamic hyperbolic-law. Results on both in-distribution (ID) and out-of-distribution (OOD) validation datasets demonstrate that our temporal scaling law accurately predicts the test loss of LLMs across training steps. Our temporal scaling law has broad practical applications. First, it enables direct and efficient hyperparameter selection on the target LLM, such as data mixture proportions. Secondly, viewing the LLM pre-training dynamics from the token position granularity provides some insights to enhance the understanding of LLM pre-training., Comment: 8 pages, 3 figures; Under review

Reinforcement learning (RL) based autonomous driving has emerged as a promising alternative to data-driven imitation learning approaches. However, crafting effective reward functions for RL poses challenges due to the complexity of defining and quantifying good driving behaviors across diverse scenarios. Recently, large pretrained models have gained significant attention as zero-shot reward models for tasks specified with desired linguistic goals. However, the desired linguistic goals for autonomous driving such as "drive safely" are ambiguous and incomprehensible by pretrained models. On the other hand, undesired linguistic goals like "collision" are more concrete and tractable. In this work, we introduce LORD, a novel large models based opposite reward design through undesired linguistic goals to enable the efficient use of large pretrained models as zero-shot reward models. Through extensive experiments, our proposed framework shows its efficiency in leveraging the power of large pretrained models for achieving safe and enhanced autonomous driving. Moreover, the proposed approach shows improved generalization capabilities as it outperforms counterpart methods across diverse and challenging driving scenarios.

Optical spectroscopy plays an essential role across scientific research and industry for non-contact materials analysis1-3, increasingly through in-situ or portable platforms4-6. However, when considering low-light-level applications, conventional spectrometer designs necessitate a compromise between their resolution and sensitivity7,8, especially as device and detector dimensions are scaled down. Here, we report on a miniaturizable spectrometer platform where light throughput onto the detector is instead enhanced as the resolution is increased. This planar, CMOS-compatible platform is based around metasurface encoders designed to exhibit photonic bound states in the continuum9, where operational range can be altered or extended simply through adjusting geometric parameters. This system can enhance photon collection efficiency by up to two orders of magnitude versus conventional designs; we demonstrate this sensitivity advantage through ultra-low-intensity fluorescent and astrophotonic spectroscopy. This work represents a step forward for the practical utility of spectrometers, affording a route to integrated, chip-based devices that maintain high resolution and SNR without requiring prohibitively long integration times.

This paper introduces a novel neural audio codec targeting high waveform sampling rates and low bitrates named APCodec, which seamlessly integrates the strengths of parametric codecs and waveform codecs. The APCodec revolutionizes the process of audio encoding and decoding by concurrently handling the amplitude and phase spectra as audio parametric characteristics like parametric codecs. It is composed of an encoder and a decoder with the modified ConvNeXt v2 network as the backbone, connected by a quantizer based on the residual vector quantization (RVQ) mechanism. The encoder compresses the audio amplitude and phase spectra in parallel, amalgamating them into a continuous latent code at a reduced temporal resolution. This code is subsequently quantized by the quantizer. Ultimately, the decoder reconstructs the audio amplitude and phase spectra in parallel, and the decoded waveform is obtained by inverse short-time Fourier transform. To ensure the fidelity of decoded audio like waveform codecs, spectral-level loss, quantization loss, and generative adversarial network (GAN) based loss are collectively employed for training the APCodec. To support low-latency streamable inference, we employ feed-forward layers and causal convolutional layers in APCodec, incorporating a knowledge distillation training strategy to enhance the quality of decoded audio. Experimental results confirm that our proposed APCodec can encode 48 kHz audio at bitrate of just 6 kbps, with no significant degradation in the quality of the decoded audio. At the same bitrate, our proposed APCodec also demonstrates superior decoded audio quality and faster generation speed compared to well-known codecs, such as SoundStream, Encodec, HiFi-Codec and AudioDec., Comment: Submitted to IEEE/ACM Transactions on Audio, Speech, and Language Processing

Speech bandwidth extension (BWE) refers to widening the frequency bandwidth range of speech signals, enhancing the speech quality towards brighter and fuller. This paper proposes a generative adversarial network (GAN) based BWE model with parallel prediction of Amplitude and Phase spectra, named AP-BWE, which achieves both high-quality and efficient wideband speech waveform generation. The proposed AP-BWE generator is entirely based on convolutional neural networks (CNNs). It features a dual-stream architecture with mutual interaction, where the amplitude stream and the phase stream communicate with each other and respectively extend the high-frequency components from the input narrowband amplitude and phase spectra. To improve the naturalness of the extended speech signals, we employ a multi-period discriminator at the waveform level and design a pair of multi-resolution amplitude and phase discriminators at the spectral level, respectively. Experimental results demonstrate that our proposed AP-BWE achieves state-of-the-art performance in terms of speech quality for BWE tasks targeting sampling rates of both 16 kHz and 48 kHz. In terms of generation efficiency, due to the all-convolutional architecture and all-frame-level operations, the proposed AP-BWE can generate 48 kHz waveform samples 292.3 times faster than real-time on a single RTX 4090 GPU and 18.1 times faster than real-time on a single CPU. Notably, to our knowledge, AP-BWE is the first to achieve the direct extension of the high-frequency phase spectrum, which is beneficial for improving the effectiveness of existing BWE methods., Comment: Submitted to IEEE/ACM Transactions on Audio, Speech, and Language Processing

In kidney exchange programmes (KEP) patients may swap their incompatible donors leading to cycles of kidney transplants. Nowadays, countries try to merge their national patient-donor pools leading to international KEPs (IKEPs). As shown in the literature, long-term stability of an IKEP can be achieved through a credit-based system. In each round, every country is prescribed a "fair" initial allocation of kidney transplants. The initial allocation, which we obtain by using solution concepts from cooperative game theory, is adjusted by incorporating credits from the previous round, yielding the target allocation. The goal is to find, in each round, an optimal solution that closely approximates this target allocation. There is a known polynomial-time algorithm for finding an optimal solution that lexicographically minimizes the country deviations from the target allocation if only $2$-cycles (matchings) are permitted. In practice, kidney swaps along longer cycles may be performed. However, the problem of computing optimal solutions for maximum cycle length $\ell$ is NP-hard for every $\ell\geq 3$. This situation changes back to polynomial time once we allow unbounded cycle length. However, in contrast to the case where $\ell=2$, we show that for $\ell=\infty$, lexicographical minimization is only polynomial-time solvable under additional conditions (assuming P $\neq$ NP). Nevertheless, the fact that the optimal solutions themselves can be computed in polynomial time if $\ell=\infty$ still enables us to perform a large scale experimental study for showing how stability and total social welfare are affected when we set $\ell=\infty$ instead of $\ell=2$.

Motion prediction has been an essential component of autonomous driving systems since it handles highly uncertain and complex scenarios involving moving agents of different types. In this paper, we propose a Multi-Granular TRansformer (MGTR) framework, an encoder-decoder network that exploits context features in different granularities for different kinds of traffic agents. To further enhance MGTR's capabilities, we leverage LiDAR point cloud data by incorporating LiDAR semantic features from an off-the-shelf LiDAR feature extractor. We evaluate MGTR on Waymo Open Dataset motion prediction benchmark and show that the proposed method achieved state-of-the-art performance, ranking 1st on its leaderboard (https://waymo.com/open/challenges/2023/motion-prediction/)., Comment: Accepted to ICRA 2024

Retinal disease is one of the primary causes of visual impairment, and early diagnosis is essential for preventing further deterioration. Nowadays, many works have explored Transformers for diagnosing diseases due to their strong visual representation capabilities. However, retinal diseases exhibit milder forms and often present with overlapping signs, which pose great difficulties for accurate multi-class classification. Therefore, we propose a new framework named Multi-Scale Patch Message Passing Swin Transformer for multi-class retinal disease classification. Specifically, we design a Patch Message Passing (PMP) module based on the Message Passing mechanism to establish global interaction for pathological semantic features and to exploit the subtle differences further between different diseases. Moreover, considering the various scale of pathological features we integrate multiple PMP modules for different patch sizes. For evaluation, we have constructed a new dataset, named OPTOS dataset, consisting of 1,033 high-resolution fundus images photographed by Optos camera and conducted comprehensive experiments to validate the efficacy of our proposed method. And the results on both the public dataset and our dataset demonstrate that our method achieves remarkable performance compared to state-of-the-art methods., Comment: 9 pages, 7 figures

In our previous work, we proposed a neural vocoder called APNet, which directly predicts speech amplitude and phase spectra with a 5 ms frame shift in parallel from the input acoustic features, and then reconstructs the 16 kHz speech waveform using inverse short-time Fourier transform (ISTFT). APNet demonstrates the capability to generate synthesized speech of comparable quality to the HiFi-GAN vocoder but with a considerably improved inference speed. However, the performance of the APNet vocoder is constrained by the waveform sampling rate and spectral frame shift, limiting its practicality for high-quality speech synthesis. Therefore, this paper proposes an improved iteration of APNet, named APNet2. The proposed APNet2 vocoder adopts ConvNeXt v2 as the backbone network for amplitude and phase predictions, expecting to enhance the modeling capability. Additionally, we introduce a multi-resolution discriminator (MRD) into the GAN-based losses and optimize the form of certain losses. At a common configuration with a waveform sampling rate of 22.05 kHz and spectral frame shift of 256 points (i.e., approximately 11.6ms), our proposed APNet2 vocoder outperformed the original APNet and Vocos vocoders in terms of synthesized speech quality. The synthesized speech quality of APNet2 is also comparable to that of HiFi-GAN and iSTFTNet, while offering a significantly faster inference speed.

Phase information has a significant impact on speech perceptual quality and intelligibility. However, existing speech enhancement methods encounter limitations in explicit phase estimation due to the non-structural nature and wrapping characteristics of the phase, leading to a bottleneck in enhanced speech quality. To overcome the above issue, in this paper, we proposed MP-SENet, a novel Speech Enhancement Network that explicitly enhances Magnitude and Phase spectra in parallel. The proposed MP-SENet comprises a Transformer-embedded encoder-decoder architecture. The encoder aims to encode the input distorted magnitude and phase spectra into time-frequency representations, which are further fed into time-frequency Transformers for alternatively capturing time and frequency dependencies. The decoder comprises a magnitude mask decoder and a phase decoder, directly enhancing magnitude and wrapped phase spectra by incorporating a magnitude masking architecture and a phase parallel estimation architecture, respectively. Multi-level loss functions explicitly defined on the magnitude spectra, wrapped phase spectra, and short-time complex spectra are adopted to jointly train the MP-SENet model. A metric discriminator is further employed to compensate for the incomplete correlation between these losses and human auditory perception. Experimental results demonstrate that our proposed MP-SENet achieves state-of-the-art performance across multiple speech enhancement tasks, including speech denoising, dereverberation, and bandwidth extension. Compared to existing phase-aware speech enhancement methods, it further mitigates the compensation effect between the magnitude and phase by explicit phase estimation, elevating the perceptual quality of enhanced speech., Comment: Submmited to IEEE Transactions on Audio, Speech and Language Processing

Speech phase prediction, which is a significant research focus in the field of signal processing, aims to recover speech phase spectra from amplitude-related features. However, existing speech phase prediction methods are constrained to recovering phase spectra with short frame shifts, which are considerably smaller than the theoretical upper bound required for exact waveform reconstruction of short-time Fourier transform (STFT). To tackle this issue, we present a novel long-frame-shift neural speech phase prediction (LFS-NSPP) method which enables precise prediction of long-frame-shift phase spectra from long-frame-shift log amplitude spectra. The proposed method consists of three stages: interpolation, prediction and decimation. The short-frame-shift log amplitude spectra are first constructed from long-frame-shift ones through frequency-by-frequency interpolation to enhance the spectral continuity, and then employed to predict short-frame-shift phase spectra using an NSPP model, thereby compensating for interpolation errors. Ultimately, the long-frame-shift phase spectra are obtained from short-frame-shift ones through frame-by-frame decimation. Experimental results show that the proposed LFS-NSPP method can yield superior quality in predicting long-frame-shift phase spectra than the original NSPP model and other signal-processing-based phase estimation algorithms., Comment: Published at IEEE Signal Processing Letters

The spatial photonic Ising machine has achieved remarkable advancements in solving combinatorial optimization problems. However, it still remains a huge challenge to flexibly mapping an arbitrary problem to Ising model. In this paper, we propose a general spatial photonic Ising machine based on interaction matrix eigendecomposition method. Arbitrary interaction matrix can be configured in the two-dimensional Fourier transformation based spatial photonic Ising model by using values generated by matrix eigendecomposition. The error in the structural representation of the Hamiltonian decreases substantially with the growing number of eigenvalues utilized to form the Ising machine. In combination with the optimization algorithm, as low as 65% of the eigenvalues is required by intensity modulation to guarantee the best probability of optimal solution for a 20-vertex graph Max-cut problem, and this probability decreases to below 20% for zero best chance. Our work provides a viable approach for spatial photonic Ising machines to solve arbitrary combinatorial optimization problems with the help of multi-dimensional optical property.

This paper proposes MP-SENet, a novel Speech Enhancement Network which directly denoises Magnitude and Phase spectra in parallel. The proposed MP-SENet adopts a codec architecture in which the encoder and decoder are bridged by convolution-augmented transformers. The encoder aims to encode time-frequency representations from the input noisy magnitude and phase spectra. The decoder is composed of parallel magnitude mask decoder and phase decoder, directly recovering clean magnitude spectra and clean-wrapped phase spectra by incorporating learnable sigmoid activation and parallel phase estimation architecture, respectively. Multi-level losses defined on magnitude spectra, phase spectra, short-time complex spectra, and time-domain waveforms are used to train the MP-SENet model jointly. Experimental results show that our proposed MP-SENet achieves a PESQ of 3.50 on the public VoiceBank+DEMAND dataset and outperforms existing advanced speech enhancement methods., Comment: Accepted by Interspeech 2023

This paper proposes a source-filter-based generative adversarial neural vocoder named SF-GAN, which achieves high-fidelity waveform generation from input acoustic features by introducing F0-based source excitation signals to a neural filter framework. The SF-GAN vocoder is composed of a source module and a resolution-wise conditional filter module and is trained based on generative adversarial strategies. The source module produces an excitation signal from the F0 information, then the resolution-wise convolutional filter module combines the excitation signal with processed acoustic features at various temporal resolutions and finally reconstructs the raw waveform. The experimental results show that our proposed SF-GAN vocoder outperforms the state-of-the-art HiFi-GAN and Fre-GAN in both analysis-synthesis (AS) and text-to-speech (TTS) tasks, and the synthesized speech quality of SF-GAN is comparable to the ground-truth audio., Comment: Accepted by NCMMSC 2022

To tackle challenging combinatorial optimization problems, analog computing machines based on the nature-inspired Ising model are attracting increasing attentions in order to disruptively overcome the impending limitations on conventional electronic computers. Photonic spatial Ising machine has become an unique and primitive solution with all-to-all connections to solve large-scale Max-cut problems. However, spin configuration and flipping requires two independent sets of spatial light modulators (SLMs) for amplitude and phase modulation, which will lead to tremendous engineering difficulty of optical alignment and coupling. We report a novel quadrature photonic spatial-Euler Ising machine to realize large-scale and flexible spin-interaction configuration and spin-flip in a single spatial light modulator, and develop a noise enhancement approach by adding digital white noise onto detected optical signals. We experimentally show that such proposal accelerates solving (un)weighted, (non)fully connected, 20736-node Max-cut problems, which offers obvious advantages over simulation and heuristic algorithm results in digital computers., Comment: 8 pages,3 figures