We examine the speech modeling potential of generative spoken language modeling (GSLM), which involves using learned symbols derived from data rather than phonemes for speech analysis and synthesis. Since GSLM facilitates textless spoken language processing, exploring its effectiveness is critical for paving the way for novel paradigms in spoken-language processing. This paper presents the findings of GSLM's encoding and decoding effectiveness at the spoken-language and speech levels. Through speech resynthesis experiments, we revealed that resynthesis errors occur at the levels ranging from phonology to syntactics and GSLM frequently resynthesizes natural but content-altered speech.
The LCLS2 Free Electron Laser FEL will generate xray pulses to beamline experiments at up to 1Mhz These experimentals will require new ultrahigh rate UHR detectors that can operate at rates above 100 kHz and generate data throughputs upwards of 1 TBs a data velocity which requires prohibitively large investments in storage infrastructure Machine Learning has demonstrated the potential to digest large datasets to extract relevant insights however current implementations show latencies that are too high for realtime data reduction objectives SLAC has endeavored on the creation of a software framework which translates MLs structures for deployment on Field Programmable Gate Arrays FPGAs deployed at the Edge of the data chain close to the instrumentation This framework leverages Xilinxs HLS framework presenting an API modeled after the open source Keras interface to the TensorFlow library This SLAC Neural Network Library SNL framework is designed with a streaming data approach optimizing the data flow between layers while minimizing the buffer data buffering requirements The goal is to ensure the highest possible framerate while keeping the maximum latency constrained to the needs of the experiment Our framework is designed to ensure the RTL implementation of the network layers supporting full redeployment of weights and biases without requiring resynthesis after training The ability to reduce the precision of the implemented networks through quantization is necessary to optimize the use of both DSP and memory resources in the FPGA We currently have a preliminary version of the toolset and are experimenting with both general purpose example networks and networks being designed for specific LCLS2 experiments.
To build speech processing methods that can handle speech as naturally as humans, researchers have explored multiple ways of building an invertible mapping from speech to an interpretable space. The articulatory space is a promising inversion target, since this space captures the mechanics of speech production. To this end, we build an acoustic-to-articulatory inversion (AAI) model that leverages self-supervision to generalize to unseen speakers. Our approach obtains 0.784 correlation on an electromagnetic articulography (EMA) dataset, improving the state-of-the-art by 12.5\%. Additionally, we show the interpretability of these representations through directly comparing the behavior of estimated representations with speech production behavior. Finally, we propose a resynthesis-based AAI evaluation metric that does not rely on articulatory labels, demonstrating its efficacy with an 18-speaker dataset.
This work profoundly analyzes discrete self-supervised speech representations (units) through the eyes of Generative Spoken Language Modeling (GSLM). Following the findings of such an analysis, we propose practical improvements to the discrete unit for the GSLM. First, we start comprehending these units by analyzing them in three axes: interpretation, visualization, and resynthesis. Our analysis finds a high correlation between the speech units to phonemes and phoneme families, while their correlation with speaker or gender is weaker. Additionally, we found redundancies in the extracted units and claim that one reason may be the units' context. Following this analysis, we propose a new, unsupervised metric to measure unit redundancies. Finally, we use this metric to develop new methods that improve the robustness of units' clustering and show significant improvement considering zero-resource speech metrics such as ABX. Code and analysis tools are available under the following link: https://github.com/slp-rl/SLM-Discrete-Representations
Prior works on improving speech quality with visual input typically study each type of auditory distortion separately (e.g., separation, inpainting, video-to-speech) and present tailored algorithms. This paper proposes to unify these subjects and study Generalized Speech Enhancement, where the goal is not to reconstruct the exact reference clean signal, but to focus on improving certain aspects of speech. In particular, this paper concerns intelligibility, quality, and video synchronization. We cast the problem as audio-visual speech resynthesis, which is composed of two steps: pseudo audio-visual speech recognition (P-AVSR) and pseudo text-to-speech synthesis (P-TTS). P-AVSR and P-TTS are connected by discrete units derived from a self-supervised speech model. Moreover, we utilize self-supervised audio-visual speech model to initialize P-AVSR. The proposed model is coined ReVISE. ReVISE is the first high-quality model for in-the-wild video-to-speech synthesis and achieves superior performance on all LRS3 audio-visual enhancement tasks with a single model. To demonstrates its applicability in the real world, ReVISE is also evaluated on EasyCom, an audio-visual benchmark collected under challenging acoustic conditions with only 1.6 hours of training data. Similarly, ReVISE greatly suppresses noise and improves quality. Project page: https://wnhsu.github.io/ReVISE.
Recent progress in self-supervised or unsupervised machine learning has opened the possibility of building a full speech processing system from raw audio without using any textual representations or expert labels such as phonemes, dictionaries or parse trees. The contribution of the Zero Resource Speech Challenge series since 2015 has been to break down this long-term objective into four well-defined tasks -- Acoustic Unit Discovery, Spoken Term Discovery, Discrete Resynthesis, and Spoken Language Modeling -- and introduce associated metrics and benchmarks enabling model comparison and cumulative progress. We present an overview of the six editions of this challenge series since 2015, discuss the lessons learned, and outline the areas which need more work or give puzzling results.
Modern speech synthesis uses neural vocoders to model raw waveform samples directly. This increased versatility has expanded the scope of vocoders from speech to other domains, such as music. We address another interesting domain of bio-acoustics. We provide initial comparative analysis-resynthesis experiments of birdsong using traditional (WORLD) and two neural (WaveNet autoencoder, parallel WaveGAN) vocoders. Our subjective results indicate no difference in the three vocoders in terms of species discrimination (ABX test). Nonetheless, the WORLD vocoder samples were rated higher in terms of retaining bird-like qualities (MOS test). All vocoders faced issues with pitch and voicing. Our results indicate some of the challenges in processing low-quality wildlife audio data.
FM Synthesis is a well-known algorithm used to generate complex timbre from a compact set of design primitives. Typically featuring a MIDI interface, it is usually impractical to control it from an audio source. On the other hand, Differentiable Digital Signal Processing (DDSP) has enabled nuanced audio rendering by Deep Neural Networks (DNNs) that learn to control differentiable synthesis layers from arbitrary sound inputs. The training process involves a corpus of audio for supervision, and spectral reconstruction loss functions. Such functions, while being great to match spectral amplitudes, present a lack of pitch direction which can hinder the joint optimization of the parameters of FM synthesizers. In this paper, we take steps towards enabling continuous control of a well-established FM synthesis architecture from an audio input. Firstly, we discuss a set of design constraints that ease spectral optimization of a differentiable FM synthesizer via a standard reconstruction loss. Next, we present Differentiable DX7 (DDX7), a lightweight architecture for neural FM resynthesis of musical instrument sounds in terms of a compact set of parameters. We train the model on instrument samples extracted from the URMP dataset, and quantitatively demonstrate its comparable audio quality against selected benchmarks.
Great progress has been achieved in the community of autonomous driving in the past few years. As a safety-critical problem, however, anomaly detection is a huge hurdle towards a large-scale deployment of autonomous vehicles in the real world. While many approaches, such as uncertainty estimation or segmentation-based image resynthesis, are extremely promising, there is more to be explored. Especially inspired by works on anomaly detection based on image resynthesis, we propose a novel approach for anomaly detection through style transfer. We leverage generative models to map an image from its original style domain of road traffic to an arbitrary one and back to generate pixelwise anomaly scores. However, our experiments have proven our hypothesis wrong, and we were unable to produce significant results. Nevertheless, we want to share our findings, so that others can learn from our experiments.
In contemporary popular music production, drum sound design is commonly performed by cumbersome browsing and processing of pre-recorded samples in sound libraries. One can also use specialized synthesis hardware, typically controlled through low-level, musically meaningless parameters. Today, the field of Deep Learning offers methods to control the synthesis process via learned high-level features and allows generating a wide variety of sounds. In this paper, we present DrumGAN VST, a plugin for synthesizing drum sounds using a Generative Adversarial Network. DrumGAN VST operates on 44.1 kHz sample-rate audio, offers independent and continuous instrument class controls, and features an encoding neural network that maps sounds into the GAN's latent space, enabling resynthesis and manipulation of pre-existing drum sounds. We provide numerous sound examples and a demo of the proposed VST plugin.
Joint time-frequency scattering (JTFS) is a convolutional operator in the time-frequency domain which extracts spectrotemporal modulations at various rates and scales. It offers an idealized model of spectrotemporal receptive fields (STRF) in the primary auditory cortex, and thus may serve as a biological plausible surrogate for human perceptual judgments at the scale of isolated audio events. Yet, prior implementations of JTFS and STRF have remained outside of the standard toolkit of perceptual similarity measures and evaluation methods for audio generation. We trace this issue down to three limitations: differentiability, speed, and flexibility. In this paper, we present an implementation of time-frequency scattering in Python. Unlike prior implementations, ours accommodates NumPy, PyTorch, and TensorFlow as backends and is thus portable on both CPU and GPU. We demonstrate the usefulness of JTFS via three applications: unsupervised manifold learning of spectrotemporal modulations, supervised classification of musical instruments, and texture resynthesis of bioacoustic sounds.
This study focuses on the perception of music performances when contextual factors, such as room acoustics and instrument, change. We propose to distinguish the concept of "performance" from the one of "interpretation", which expresses the "artistic intention". Towards assessing this distinction, we carried out an experimental evaluation where 91 subjects were invited to listen to various audio recordings created by resynthesizing MIDI data obtained through Automatic Music Transcription (AMT) systems and a sensorized acoustic piano. During the resynthesis, we simulated different contexts and asked listeners to evaluate how much the interpretation changes when the context changes. Results show that: (1) MIDI format alone is not able to completely grasp the artistic intention of a music performance; (2) usual objective evaluation measures based on MIDI data present low correlations with the average subjective evaluation. To bridge this gap, we propose a novel measure which is meaningfully correlated with the outcome of the tests. In addition, we investigate multimodal machine learning by providing a new score-informed AMT method and propose an approximation algorithm for the $p$-dispersion problem.
Textless spoken language processing research aims to extend the applicability of standard NLP toolset onto spoken language and languages with few or no textual resources. In this paper, we introduce textless-lib, a PyTorch-based library aimed to facilitate research in this research area. We describe the building blocks that the library provides and demonstrate its usability by discuss three different use-case examples: (i) speaker probing, (ii) speech resynthesis and compression, and (iii) speech continuation. We believe that textless-lib substantially simplifies research the textless setting and will be handful not only for speech researchers but also for the NLP community at large. The code, documentation, and pre-trained models are available at https://github.com/facebookresearch/textlesslib/ .
Voice conversion for speaker anonymization is an emerging field in speech processing research. Many state-of-the-art approaches are based on the resynthesis of the phoneme posteriorgrams (PPG), the fundamental frequency (F0) of the input signal together with modified X-vectors. Our research focuses on the role of F0 for speaker anonymization, which is an understudied area. Utilizing the VoicePrivacy Challenge 2020 framework and its datasets we developed and evaluated eight low-complexity F0 modifications prior resynthesis. We found that modifying the F0 can improve speaker anonymization by as much as 8% with minor word-error rate degradation.
We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representations for speech content, prosodic information, and speaker identity. This allows to synthesize speech in a controllable manner. We analyze various state-of-the-art, self-supervised representation learning methods and shed light on the advantages of each method while considering reconstruction quality and disentanglement properties. Specifically, we evaluate the F0 reconstruction, speaker identification performance (for both resynthesis and voice conversion), recordings' intelligibility, and overall quality using subjective human evaluation. Lastly, we demonstrate how these representations can be used for an ultra-lightweight speech codec. Using the obtained representations, we can get to a rate of 365 bits per second while providing better speech quality than the baseline methods. Audio samples can be found under the following link: speechbot.github.io/resynthesis.
We introduce Generative Spoken Language Modeling, the task of learning the acoustic and linguistic characteristics of a language from raw audio (no text, no labels), and a set of metrics to automatically evaluate the learned representations at acoustic and linguistic levels for both encoding and generation. We set up baseline systems consisting of a discrete speech encoder (returning pseudo-text units), a generative language model (trained on pseudo-text), and a speech decoder (generating a waveform from pseudo-text) all trained without supervision and validate the proposed metrics with human evaluation. Across 3 speech encoders (CPC, wav2vec 2.0, HuBERT), we find that the number of discrete units (50, 100, or 200) matters in a task-dependent and encoder-dependent way, and that some combinations approach text-based systems.
The presence of oscillations in aggregated COVID-19 data not only raises questions about the data's accuracy, it hinders understanding of the pandemic. Spectral analysis is used to reveal additional properties of the data, and the oscillations are replicated using sinusoidal resynthesis. The precise behavior of the seven-day moving average is also discussed, specifically, the cause of its jaggedness and the phase error it introduces. In comparison, other filtering techniques and Fourier processing produce superior smoothing and have zero phase error. Both of these are presented, and they are extended to isolate several frequency ranges. This extracts some of the same short-term variability that is resynthesized, and it shows that fluctuations with periods between 8 and 21 days are present in U.S. mortality data. These methods have applications that include modeling epidemiological time-series data as well as identifying less obvious properties of the data.
Variational autoencoders (VAEs) are powerful deep generative models widely used to represent high-dimensional complex data through a low-dimensional latent space learned in an unsupervised manner. In the original VAE model, the input data vectors are processed independently. Recently, a series of papers have presented different extensions of the VAE to process sequential data, which model not only the latent space but also the temporal dependencies within a sequence of data vectors and corresponding latent vectors, relying on recurrent neural networks or state-space models. In this paper, we perform a literature review of these models. We introduce and discuss a general class of models, called dynamical variational autoencoders (DVAEs), which encompasses a large subset of these temporal VAE extensions. Then, we present in detail seven recently proposed DVAE models, with an aim to homogenize the notations and presentation lines, as well as to relate these models with existing classical temporal models. We have reimplemented those seven DVAE models and present the results of an experimental benchmark conducted on the speech analysis-resynthesis task (the PyTorch code is made publicly available). The paper concludes with a discussion on important issues concerning the DVAE class of models and future research guidelines.
Traditional speech enhancement systems produce speech with compromised quality. Here we propose to use the high quality speech generation capability of neural vocoders for better quality speech enhancement. We term this parametric resynthesis (PR). In previous work, we showed that PR systems generate high quality speech for a single speaker using two neural vocoders, WaveNet and WaveGlow. Both these vocoders are traditionally speaker dependent. Here we first show that when trained on data from enough speakers, these vocoders can generate speech from unseen speakers, both male and female, with similar quality as seen speakers in training. Next using these two vocoders and a new vocoder LPCNet, we evaluate the noise reduction quality of PR on unseen speakers and show that objective signal and overall quality is higher than the state-of-the-art speech enhancement systems Wave-U-Net, Wavenet-denoise, and SEGAN. Moreover, in subjective quality, multiple-speaker PR out-performs the oracle Wiener mask.
Noise suppression systems generally produce output speech with compromised quality. We propose to utilize the high quality speech generation capability of neural vocoders for noise suppression. We use a neural network to predict clean mel-spectrogram features from noisy speech and then compare two neural vocoders, WaveNet and WaveGlow, for synthesizing clean speech from the predicted mel spectrogram. Both WaveNet and WaveGlow achieve better subjective and objective quality scores than the source separation model Chimera++. Further, WaveNet and WaveGlow also achieve significantly better subjective quality ratings than the oracle Wiener mask. Moreover, we observe that between WaveNet and WaveGlow, WaveNet achieves the best subjective quality scores, although at the cost of much slower waveform generation.