ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speech
Renmin University of China（中国人民大学）；University of Science and Technology of China（中国科学技术大学）；South China University of Technology（华南理工大学）；University of Surrey（萨里大学）；MSRA（微软亚洲研究院）；Microsoft Azure Speech（微软Azure语音）；Imperial College London（帝国理工学院）
Zehua Chen, Yihan Wu, Yichong Leng, Jiawei Chen, Haohe Liu, Xu Tan, Yang Cui, Ke Wang, Lei He, Sheng Zhao, Jiang Bian, Danilo Mandic
Denoising Diffusion Probabilistic Models (DDPMs) are emerging in text-to-speech (TTS) synthesis because of their strong capability of generating high-fidelity samples. However, their iterative refinement process in high-dimensional data space results in slow inference speed, which restricts their application in real-time systems. Previous works have explored speeding up by minimizing the number of inference steps but at the cost of sample quality. In this work, to improve the inference speed for DDPM-based TTS model while achieving high sample quality, we propose ResGrad, a lightweight diffusion model which learns to refine the output spectrogram of an existing TTS model (e.g., FastSpeech 2) by predicting the residual between the model output and the corresponding ground-truth speech. ResGrad has several advantages: 1) Compare with other acceleration methods for DDPM which need to synthesize speech from scratch, ResGrad reduces the complexity of task by changing the generation target from ground-truth mel-spectrogram to the residual, resulting into a more lightweight model and thus a smaller real-time factor. 2) ResGrad is employed in the inference process of the existing TTS model in a plug-and-play way, without re-training this model. We verify ResGrad on the single-speaker dataset LJSpeech and two more challenging datasets with multiple speakers (LibriTTS) and high sampling rate (VCTK). Experimental results show that in comparison with other speed-up methods of DDPMs: 1) ResGrad achieves better sample quality with the same inference speed measured by real-time factor; 2) with similar speech quality, ResGrad synthesizes speech faster than baseline methods by more than 10 times. Audio samples are available at https://resgrad1.github.io/.
Denoising diffusion probabilistic models (DDPMs) are expressive generative models that have been used to solve a variety of speech synthesis problems. However, because of their high sampling costs, DDPMs are difficult to use in real-time speech processing applications. In this paper, we introduce DiffGAN-TTS, a novel DDPM-based text-to-speech (TTS) model achieving high-fidelity and efficient speech synthesis. DiffGAN-TTS is based on denoising diffusion generative adversarial networks (GANs), which adopt an adversarially-trained expressive model to approximate the denoising distribution. We sho…
McGill University（麦吉尔大学）；National Institute of Informatics（国立信息学研究所）
This paper proposes a deep denoising auto-encoder technique to extract better acoustic features for speech synthesis. The technique allows us to automatically extract low-dimensional features from high dimensional spectral features in a non-linear, data-driven, unsupervised way. We compared the new stochastic feature extractor with conventional mel-cepstral analysis in analysis-by-synthesis and text-to-speech experiments. Our results confirm that the proposed method increases the quality of synthetic speech in both experiments.
Automatic speech recognition (ASR) systems are of vital importance nowadays in commonplace tasks such as speech-to-text processing and language translation. This created the need for an ASR system that can operate in realistic crowded environments. Thus, speech enhancement is a valuable building block in ASR systems and other applications such as hearing aids, smartphones and teleconferencing systems. In this paper, a generative adversarial network (GAN) based framework is investigated for the task of speech enhancement, more specifically speech denoising of audio tracks. A new architecture ba…
Real-world audio recordings are often degraded by factors such as noise, reverberation, and equalization distortion. This paper introduces HiFi-GAN, a deep learning method to transform recorded speech to sound as though it had been recorded in a studio. We use an end-to-end feed-forward WaveNet architecture, trained with multi-scale adversarial discriminators in both the time domain and the time-frequency domain. It relies on the deep feature matching losses of the discriminators to improve the perceptual quality of enhanced speech. The proposed model generalizes well to new speakers, new spee…
Zhejiang University（浙江大学）；Microsoft Research Asia（微软亚洲研究院）；Microsoft Azure Speech（微软Azure语音部门）
While neural-based text to speech (TTS) models can synthesize natural and intelligible voice, they usually require high-quality speech data, which is costly to collect. In many scenarios, only noisy speech of a target speaker is available, which presents challenges for TTS model training for this speaker. Previous works usually address the challenge using two methods: 1) training the TTS model using the speech denoised with an enhancement model; 2) taking a single noise embedding as input when training with noisy speech. However, they usually cannot handle speech with real-world complicated no…
Seoul National University（首尔国立大学）；Neosapience, Inc.（Neosapience公司）
Although neural text-to-speech (TTS) models have attracted a lot of attention and succeeded in generating human-like speech, there is still room for improvements to its naturalness and architectural efficiency. In this work, we propose a novel non-autoregressive TTS model, namely Diff-TTS, which achieves highly natural and efficient speech synthesis. Given the text, Diff-TTS exploits a denoising diffusion framework to transform the noise signal into a mel-spectrogram via diffusion time steps. In order to learn the mel-spectrogram distribution conditioned on the text, we present a likelihood-ba…
Diffusion probabilistic models (DPMs) and their extensions have emerged as competitive generative models yet confront challenges of efficient sampling. We propose a new bilateral denoising diffusion model (BDDM) that parameterizes both the forward and reverse processes with a schedule network and a score network, which can train with a novel bilateral modeling objective. We show that the new surrogate objective can achieve a lower bound of the log marginal likelihood tighter than a conventional surrogate. We also find that BDDM allows inheriting pre-trained score network parameters from any DP…
National Institute of Informatics（国立信息学研究所）；KDDI Research Inc.（KDDI研究所）
We investigated the impact of noisy linguistic features on the performance of a Japanese speech synthesis system based on neural network that uses WaveNet vocoder. We compared an ideal system that uses manually corrected linguistic features including phoneme and prosodic information in training and test sets against a few other systems that use corrupted linguistic features. Both subjective and objective results demonstrate that corrupted linguistic features, especially those in the test set, affected the ideal system's performance significantly in a statistical sense due to a mismatched condi…
Tel Aviv University（特拉维夫大学）；Facebook AI Research（脸书人工智能研究院）
We present a novel way of conditioning a pretrained denoising diffusion speech model to produce speech in the voice of a novel person unseen during training. The method requires a short (~3 seconds) sample from the target person, and generation is steered at inference time, without any training steps. At the heart of the method lies a sampling process that combines the estimation of the denoising model with a low-pass version of the new speaker's sample. The objective and subjective evaluations show that our sampling method can generate a voice similar to that of the target speaker in terms of…
In a conventional voice conversion (VC) framework, a VC model is often trained with a clean dataset consisting of speech data carefully recorded and selected by minimizing background interference. However, collecting such a high-quality dataset is expensive and time-consuming. Leveraging crowd-sourced speech data in training is more economical. Moreover, for some real-world VC scenarios such as VC in video and VC-based data augmentation for speech recognition systems, the background sounds themselves are also informative and need to be maintained. In this paper, to explore VC with the flexibil…
Improving Noise Robustness of LLM-based Zero-shot TTS via Discrete Acoustic Token Denoising
University of Science and Technology of China（中国科学技术大学）；National Engineering Research Center of Speech and Language Information Processing（语音与语言信息处理国家工程研究中心）
Speech Driven Video Editing via an Audio-Conditioned Diffusion Model
University of Galway（高威大学）；University of Wrocław（弗罗茨瓦夫大学）；Wrocław University of Science and Technology（弗罗茨瓦夫理工大学）；Tooploox（Tooploox公司）；Trinity College Dublin（都柏林圣三一学院）
Seoul National University（首尔国立大学）；Microsoft Research Asia（微软亚洲研究院）
Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of the data density. The framework defines the prior noise as a standard Gaussian distribution, whereas the corresponding data distribution may be more complicated than the standard Gaussian distribution, which potentially introduces inefficiency in denoising the prior noise into the data sample because of the discrepancy between the data and the prior. In this paper, we propose PriorGrad to improve the efficiency of the conditional diffusion model for speech synthes…
Tel-Aviv University（特拉维夫大学）；Facebook AI Research（脸书人工智能研究院）；École Normale Supérieure Paris-Saclay（巴黎-萨克雷高等师范学院）
Generative diffusion processes are an emerging and effective tool for image and speech generation. In the existing methods, the underline noise distribution of the diffusion process is Gaussian noise. However, fitting distributions with more degrees of freedom, could help the performance of such generative models. In this work, we investigate other types of noise distribution for the diffusion process. Specifically, we show that noise from Gamma distribution provides improved results for image and speech generation. Moreover, we show that using a mixture of Gaussian noise variables in the diff…
Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hinder their applications to text-to-speech deployment. Through the preliminary study on diffusion model parameterization, we find that previous gradient-based TTS models require hundreds or thousands of iterations to guarantee high sample quality, which poses a challenge for accelerating sampling. In this work, we propose ProDiff, on progressive fast diffusion model for high-quality text-to-speech. Unlike previous work e…
Automatic Speech Recognition (ASR) systems suffer considerably when source speech is corrupted with noise or room impulse responses (RIR). Typically, speech enhancement is applied in both mismatched and matched scenario training and testing. In matched setting, acoustic model (AM) is trained on dereverberated far-field features while in mismatched setting, AM is fixed. In recent past, mapping speech features from far-field to close-talk using denoising autoencoder (DA) has been explored. In this paper, we focus on matched scenario training and show that the proposed joint VAE based mapping ach…
This paper presents a new voice conversion (VC) framework capable of dealing with both additive noise and reverberation, and its performance evaluation. There have been studied some VC researches focusing on real-world circumstances where speech data are interfered with background noise and reverberation. To deal with more practical conditions where no clean target dataset is available, one possible approach is zero-shot VC, but its performance tends to degrade compared with VC using sufficient amount of target speech data. To leverage large amount of noisy-reverberant target speech data, we p…
Beyond the conventional voice conversion (VC) where the speaker information is converted without altering the linguistic content, the background sounds are informative and need to be retained in some real-world scenarios, such as VC in movie/video and VC in music where the voice is entangled with background sounds. As a new VC framework, we have developed a noisy-to-noisy (N2N) VC framework to convert the speaker's identity while preserving the background sounds. Although our framework consisting of a denoising module and a VC module well handles the background sounds, the VC module is sensiti…
Google LLC（谷歌有限责任公司）；Victoria University of Wellington（惠灵顿维多利亚大学）
Recent advances in neural-network based generative modeling of speech has shown great potential for speech coding. However, the performance of such models drops when the input is not clean speech, e.g., in the presence of background noise, preventing its use in practical applications. In this paper we examine the reason and discuss methods to overcome this issue. Placing a denoising preprocessing stage when extracting features and target clean speech during training is shown to be the best performing strategy.
Northwestern Polytechnical University（西北工业大学）；Bytedance AI Lab（字节跳动人工智能实验室）
Attention-based sequence-to-sequence (seq2seq) speech synthesis has achieved extraordinary performance. But a studio-quality corpus with manual transcription is necessary to train such seq2seq systems. In this paper, we propose an approach to build high-quality and stable seq2seq based speech synthesis system using challenging found data, where training speech contains noisy interferences (acoustic noise) and texts are imperfect speech recognition transcripts (textual noise). To deal with text-side noise, we propose a VQVAE based heuristic method to compensate erroneous linguistic feature with…
Existing deep learning-based speech denoising approaches require clean speech signals to be available for training. This paper presents a deep learning-based approach to improve speech denoising in real-world audio environments by not requiring the availability of clean speech signals in a self-supervised manner. A fully convolutional neural network is trained by using two noisy realizations of the same speech signal, one used as the input and the other as the output of the network. Extensive experimentations are conducted to show the superiority of the developed deep speech denoising approach…
Although current neural text-to-speech (TTS) models are able to generate high-quality speech, intensity controllable emotional TTS is still a challenging task. Most existing methods need external optimizations for intensity calculation, leading to suboptimal results or degraded quality. In this paper, we propose EmoDiff, a diffusion-based TTS model where emotion intensity can be manipulated by a proposed soft-label guidance technique derived from classifier guidance. Specifically, instead of being guided with a one-hot vector for the specified emotion, EmoDiff is guided with a soft label where…
This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio-denoising methods by showing that it is possible to train deep speech denoising networks using only noisy speech samples. Conventional wisdom dictates that in order to achieve good speech denoising performance, there is a requirement for a large quantity of both noisy speech samples and perfectly clean speech samples, resulting in a need for expensive audio recording equipment and extremely controlled soundproof recording studios. These requirements pose significant challenges in d…
This paper presents a review of multi-objective deep learning methods that have been introduced in the literature for speech denoising. After stating an overview of conventional, single objective deep learning, and hybrid or combined conventional and deep learning methods, a review of the mathematical framework of the multi-objective deep learning methods for speech denoising is provided. A representative method from each speech denoising category, whose codes are publicly available, is selected and a comparison is carried out by considering the same public domain dataset and four widely used …
Columbia University（哥伦比亚大学）；SoftBank Group Corp.（软银集团）
We introduce a deep learning model for speech denoising, a long-standing challenge in audio analysis arising in numerous applications. Our approach is based on a key observation about human speech: there is often a short pause between each sentence or word. In a recorded speech signal, those pauses introduce a series of time periods during which only noise is present. We leverage these incidental silent intervals to learn a model for automatic speech denoising given only mono-channel audio. Detected silent intervals over time expose not just pure noise but its time-varying features, allowing t…
National Taiwan University（国立台湾大学）；Research Center for Information Technology Innovation, Academia Sinica（中央研究院资讯科技创新研究中心）
Speech data collected in real-world scenarios often encounters two issues. First, multiple sources may exist simultaneously, and the number of sources may vary with time. Second, the existence of background noise in recording is inevitable. To handle the first issue, we refer to speech separation approaches, that separate speech from an unknown number of speakers. To address the second issue, we refer to speech denoising approaches, which remove noise components and retrieve pure speech signals. Numerous deep learning based methods for speech separation and denoising have been proposed that sh…
The CUNY Graduate Center（纽约市立大学研究生中心）；Brooklyn College（布鲁克林学院）
This work proposes the use of clean speech vocoder parameters as the target for a neural network performing speech enhancement. These parameters have been designed for text-to-speech synthesis so that they both produce high-quality resyntheses and also are straightforward to model with neural networks, but have not been utilized in speech enhancement until now. In comparison to a matched text-to-speech system that is given the ground truth transcripts of the noisy speech, our model is able to produce more natural speech because it has access to the true prosody in the noisy speech. In comparis…
Department of Electrical Engineering, Columbia University（哥伦比亚大学电气工程系）；Google Research（谷歌研究院）
This work describes a speech denoising system for machine ears that aims to improve speech intelligibility and the overall listening experience in noisy environments. We recorded approximately 100 hours of audio data with reverberation and moderate environmental noise using a pair of microphone arrays placed around each of the two ears and then mixed sound recordings to simulate adverse acoustic scenes. Then, we trained a multi-channel speech denoising network (MCSDN) on the mixture of recordings. To improve the training, we employ an unsupervised method, complex angular central Gaussian mixtu…
In this work, we present CleanUNet, a causal speech denoising model on the raw waveform. The proposed model is based on an encoder-decoder architecture combined with several self-attention blocks to refine its bottleneck representations, which is crucial to obtain good results. The model is optimized through a set of losses defined over both waveform and multi-resolution spectrograms. The proposed method outperforms the state-of-the-art models in terms of denoised speech quality from various objective and subjective evaluation metrics. We release our code and models at https://github.com/nvidi…
Southeast University（东南大学）；Centre de Recherche en Information Biomédicale Sino-français (CRIBs)（中法生物医学信息研究中心）；The 28th Research Institute of China Electronics Technology Group Corporation（中国电子科技集团公司第二十八研究所）；Univ Rennes（雷恩大学）
In traditional speech denoising tasks, clean audio signals are often used as the training target, but absolutely clean signals are collected from expensive recording equipment or in studios with the strict environments. To overcome this drawback, we propose an end-to-end self-supervised speech denoising training scheme using only noisy audio signals, named Only-Noisy Training (ONT), without extra training conditions. The proposed ONT strategy constructs training pairs only from each single noisy audio, and it contains two modules: training audio pairs generated module and speech denoising modu…
Research Center for Information Technology Innovation, Academia Sinica（中央研究院资讯科技创新研究中心）；National Taiwan University（台湾大学）；Institute of Linguistics, Academia Sinica（中央研究院语言学研究所）
Speech perception is key to verbal communication. For people with hearing loss, the capability to recognize speech is restricted, particularly in a noisy environment or the situations without visual cues, such as lip-reading unavailable via phone call. This study aimed to understand the improvement of vocoded speech intelligibility in cochlear implant (CI) simulation through two potential methods: Speech Enhancement (SE) and Audiovisual Integration. A fully convolutional neural network (FCN) using an intelligibility-oriented objective function was recently proposed and proven to effectively fa…
Indiana University（印第安纳大学）；Electronics and Telecommunications Research Institute（韩国电子通信研究院）
We present a psychoacoustically enhanced cost function to balance network complexity and perceptual performance of deep neural networks for speech denoising. While training the network, we utilize perceptual weights added to the ordinary mean-squared error to emphasize contribution from frequency bins which are most audible while ignoring error from inaudible bins. To generate the weights, we employ psychoacoustic models to compute the global masking threshold from the clean speech spectra. We then evaluate the speech denoising performance of our perceptually guided neural network by using bot…
We describe a monaural speech enhancement algorithm based on modulation-domain Kalman filtering to blindly track the time-frequency log-magnitude spectra of speech and reverberation. We propose an adaptive algorithm that performs blind joint denoising and dereverberation, while accounting for the inter-frame speech dynamics, by estimating the posterior distribution of the speech log-magnitude spectrum given the log-magnitude spectrum of the noisy reverberant speech. The Kalman filter update step models the non-linear relations between the speech, noise and reverberation log-spectra. The Kalman…
For speech-related applications in IoT environments, identifying effective methods to handle interference noises and compress the amount of data in transmissions is essential to achieve high-quality services. In this study, we propose a novel multi-input multi-output speech compression and enhancement (MIMO-SCE) system based on a convolutional denoising autoencoder (CDAE) model to simultaneously improve speech quality and reduce the dimensions of transmission data. Compared with conventional single-channel and multi-input single-output systems, MIMO systems can be employed in applications that…
We present an end-to-end deep learning approach to denoising speech signals by processing the raw waveform directly. Given input audio containing speech corrupted by an additive background signal, the system aims to produce a processed signal that contains only the speech content. Recent approaches have shown promising results using various deep network architectures. In this paper, we propose to train a fully-convolutional context aggregation network using a deep feature loss. That loss is based on comparing the internal feature activations in a different network, trained for acoustic environ…
In this paper, we investigate a deep learning approach for speech denoising through an efficient ensemble of specialist neural networks. By splitting up the speech denoising task into non-overlapping subproblems and introducing a classifier, we are able to improve denoising performance while also reducing computational complexity. More specifically, the proposed model incorporates a gating network which assigns noisy speech signals to an appropriate specialist network based on either speech degradation level or speaker gender. In our experiments, a baseline recurrent network is compared agains…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Monaural speech dereverberation is a very challenging task because no spatial cues can be used. When the additive noises exist, this task becomes more challenging. In this paper, we propose a joint training method for simultaneous speech denoising and dereverberation using deep embedding features, which is based on the deep clustering (DC). DC is a state-of-the-art method for speech separation that includes embedding learning and K-means clustering. As for our proposed method, it contains two stages: denoising and dereverberation. At the denoising stage, the DC network is leveraged to extract …
Although supervised learning based on a deep neural network has recently achieved substantial improvement on speech enhancement, the existing schemes have either of two critical issues: spectrum or metric mismatches. The spectrum mismatch is a well known issue that any spectrum modification after short-time Fourier transform (STFT), in general, cannot be fully recovered after inverse short-time Fourier transform (ISTFT). The metric mismatch is that a conventional mean square error (MSE) loss function is typically sub-optimal to maximize perceptual speech measure such as signal-to-distortion ra…
