In this study, we propose a modulation decoupling based single channel speech enhancement subspace framework, in which the spectrogram of noisy speech is decoupled as the product of a spectral envelop subspace and a spectral details subspace. This decoupling approach provides a method to specifically work on elimination of those noises that greatly affect the intelligibility. Two supervised low-rank and sparse decomposition schemes are developed in the spectral envelop subspace to obtain a robust recovery of speech components. A Bayesian formulation of non-negative factorization is used to learn the speech dictionary from the spectral envelop subspace of clean speech samples. In the spectral details subspace, a standard robust principal component analysis is implemented to extract the speech components. The validation results show that compared with four speech enhancement algorithms, including MMSE-SPP, NMF-RPCA, RPCA, and LARC, the proposed MS based algorithms achieve satisfactory performance on improving perceptual quality, and especially speech intelligibility.
Wakayama University（和歌山大学）；NTT Communication Science Laboratories（NTT通信科学基础研究所）
In this study, we propose a new concept, the gammachirp envelope distortion index (GEDI), based on the signal-to-distortion ratio in the auditory envelope, SDRenv to predict the intelligibility of speech enhanced by nonlinear algorithms. The objective of GEDI is to calculate the distortion between enhanced and clean-speech representations in the domain of a temporal envelope extracted by the gammachirp auditory filterbank and modulation filterbank. We also extend GEDI with multi-resolution analysis (mr-GEDI) to predict the speech intelligibility of sounds under non-stationary noise conditions.…
For enhancing noisy signals, machine-learning based single-channel speech enhancement schemes exploit prior knowledge about typical speech spectral structures. To ensure a good generalization and to meet requirements in terms of computational complexity and memory consumption, certain methods restrict themselves to learning speech spectral envelopes. We refer to these approaches as machine-learning spectral envelope (MLSE)-based approaches. In this paper we show by means of theoretical and experimental analyses that for MLSE-based approaches, super-Gaussian priors allow for a reduction of nois…
Speech enhancement with frequency domain auto-regressive modeling
Indian Institute of Science（印度科学学院）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Johns Hopkins University（约翰斯·霍普金斯大学）；Samsung Research India（三星印度研究院）
The majority of deep neural network (DNN) based speech enhancement algorithms rely on the mean-square error (MSE) criterion of short-time spectral amplitudes (STSA), which has no apparent link to human perception, e.g. speech intelligibility. Short-Time Objective Intelligibility (STOI), a popular state-of-the-art speech intelligibility estimator, on the other hand, relies on linear correlation of speech temporal envelopes. This raises the question if a DNN training criterion based on envelope linear correlation (ELC) can lead to improved speech intelligibility performance of DNN based speech e…
Traditional speech enhancement techniques modify the magnitude of a speech in time-frequency domain, and use the phase of a noisy speech to resynthesize a time domain speech. This work proposes a complex-valued Gaussian process latent variable model (CGPLVM) to enhance directly the complex-valued noisy spectrum, modifying not only the magnitude but also the phase. The main idea that underlies the developed method is the modeling of short-time Fourier transform (STFT) coefficients across the time frames of a speech as a proper complex Gaussian process (GP) with noise added. The proposed method …
In this paper we propose a Deep Neural Network (DNN) based Speech Enhancement (SE) system that is designed to maximize an approximation of the Short-Time Objective Intelligibility (STOI) measure. We formalize an approximate-STOI cost function and derive analytical expressions for the gradients required for DNN training and show that these gradients have desirable properties when used together with gradient based optimization techniques. We show through simulation experiments that the proposed SE system achieves large improvements in estimated speech intelligibility, when tested on matched and …
Attempts to develop speech enhancement algorithms with improved speech intelligibility for cochlear implant (CI) users have met with limited success. To improve speech enhancement methods for CI users, we propose to perform speech enhancement in a cochlear filter-bank feature space, a feature-set specifically designed for CI users based on CI auditory stimuli. We leverage a convolutional neural network (CNN) to extract both stationary and non-stationary components of environmental acoustics and speech. We propose three CNN architectures: (1) vanilla CNN that directly generates the enhanced sig…
Budapest University of Technology and Economics（布达佩斯技术与经济大学）
Neural network-based Text-to-Speech has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron2, FastSpeech, FastPitch) usually generate Mel-spectrogram from text and then synthesize speech using vocoder (e.g., WaveNet, WaveGlow, HiFiGAN). Compared with traditional parametric approaches (e.g., STRAIGHT and WORLD), neural vocoder based end-to-end models suffer from slow inference speed, and the synthesized speech is usually not robust and lack of controllability. In this work, we propose a novel updated vocoder, which is a simple signal model to train and ea…
Indian Institute of Science（印度科学学院）；Learning and Extraction of Acoustic Patterns (LEAP) lab（声学模式学习与提取实验室（LEAP实验室））
Automatic speech recognition in reverberant conditions is a challenging task as the long-term envelopes of the reverberant speech are temporally smeared. In this paper, we propose a neural model for enhancement of sub-band temporal envelopes for dereverberation of speech. The temporal envelopes are derived using the autoregressive modeling framework of frequency domain linear prediction (FDLP). The neural enhancement model proposed in this paper performs an envelop gain based enhancement of temporal envelopes and it consists of a series of convolutional and recurrent neural network layers. The…
International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院）
In this paper we propose a technique for spectral envelope estimation using maximum values in the sub-bands of Fourier magnitude spectrum (MSASB). Most other methods in the literature parametrize spectral envelope in cepstral domain such as Mel-generalized cepstrum etc. Such cepstral domain representations, although compact, are not readily interpretable. This difficulty is overcome by our method which parametrizes in the spectral domain itself. In our experiments, spectral envelope estimated using MSASB method was incorporated in the STRAIGHT vocoder. Both objective and subjective results of …
Evidence Subspace Projection: Measuring How Much Evidence Explains Deepfake Detection in Self-Supervised Speech Models
University of Stuttgart（斯图加特大学）；National Institute of Informatics（日本信息处理研究所）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；Technical University of Berlin（柏林技术大学）
DeCodec: Rethinking Audio Codecs as Universal Disentangled Representation Learners
Jiutian Artificial Intelligence Research Institute, China Mobile, China State Key Laboratory of Multimedia Information Processing, Peking University, China（九天人工智能研究院，中国移动，国家多媒体信息处理重点实验室，北京大学）
As one of the major branches of automatic speech recognition, attention-based models greatly improves the feature representation ability of the model. In particular, the multi-head mechanism is employed in the attention, hoping to learn speech features of more aspects in different attention subspaces. For speech recognition of complex languages, on the one hand, a small head size will lead to an obvious shortage of learnable aspects. On the other hand, we need to reduce the dimension of each subspace to keep the size of the overall feature space unchanged when we increase the number of heads, …
CentraleSupélec（巴黎中央理工-高等电力学院）；IETR UMR CNRS 6164（法国国家科学研究中心电子与电信研究所（UMR 6164））；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；CNRS（法国国家科学研究中心）；Grenoble-INP（格勒诺布尔国立理工学院）；GIPSA-lab（格勒诺布尔图像、语音、信号与自动化实验室）；Inria（法国国家信息与自动化研究所）；LJK（让·昆塞曼实验室）
Understanding and controlling latent representations in deep generative models is a challenging yet important problem for analyzing, transforming and generating various types of data. In speech processing, inspiring from the anatomical mechanisms of phonation, the source-filter model considers that speech signals are produced from a few independent and physically meaningful continuous latent factors, among which the fundamental frequency $f_0$ and the formants are of primary importance. In this work, we start from a variational autoencoder (VAE) trained in an unsupervised manner on a large dat…
Frequency-Specific Neural Response and Cross-Correlation Analysis of Envelope Following Responses to Native Speech and Music Using Multichannel EEG Signals: A Case Study
Department of Electrical and Electronic Engineering, Khulna University of Engineering & Technology（电气与电子工程系，库尔纳大学工程与技术学院）；School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University（电气工程、计算与数学科学学院， Curtin 大学）
This paper extends recent work on nonlinear Independent Component Analysis (ICA) by introducing a theoretical framework for nonlinear Independent Subspace Analysis (ISA) in the presence of auxiliary variables. Observed high dimensional acoustic features like log Mel spectrograms can be considered as surface level manifestations of nonlinear transformations over individual multivariate sources of information like speaker characteristics, phonological content etc. Under assumptions of energy based models we use the theory of nonlinear ISA to propose an algorithm that learns unsupervised speech r…
NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
Microsoft Research（微软研究院）；Microsoft Azure（微软Azure）；University of Science and Technology of China（中国科学技术大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Zhejiang University（浙江大学）；The University of Tokyo（东京大学）；Peking University（北京大学）
We define an alphabet, the IHA, of the 10-D phonetic-prosodic space. The dimensions of this space are perceptual observables, rather than articulatory specifications. Speech is defined as a random chain in time of the 4-D phonetic subspace, that is, a symbolic sequence, augmented with diacritics of the remaining 6-D prosodic subspace. The definitions here are based on the model of speech of oral billiards, and supersedes an earlier version. This paper only enumerates the IHA in detail as a supplement to the exposition of oral billiards in a separate paper. The IHA has been implemented as the t…
Zipper-LoRA: Dynamic Parameter Decoupling for Speech-LLM based Multilingual Speech Recognition
Shanghai Engineering Research Center of Intelligent Education and Bigdata, Shanghai Normal University（智能教育与大数据上海工程研究中心，上海师范大学）；SHNU-Unisound Natural Human-Computer Interaction Lab, Shanghai Normal University（上海师范大学Unisound自然人机交互实验室）；Unisound AI Technology Co., Ltd.（Unisound人工智能技术有限公司）
Auditory attention decoding (AAD) is a technique used to identify and amplify the talker that a listener is focused on in a noisy environment. This is done by comparing the listener's brainwaves to a representation of all the sound sources to find the closest match. The representation is typically the waveform or spectrogram of the sounds. The effectiveness of these representations for AAD is uncertain. In this study, we examined the use of self-supervised learned speech representation in improving the accuracy and speed of AAD. We recorded the brain activity of three subjects using invasive e…
