This paper investigates a self-adaptation method for speech enhancement using auxiliary speaker-aware features; we extract a speaker representation used for adaptation directly from the test utterance. Conventional studies of deep neural network (DNN)--based speech enhancement mainly focus on building a speaker independent model. Meanwhile, in speech applications including speech recognition and synthesis, it is known that model adaptation to the target speaker improves the accuracy. Our research question is whether a DNN for speech enhancement can be adopted to unknown speakers without any auxiliary guidance signal in test-phase. To achieve this, we adopt multi-task learning of speech enhancement and speaker identification, and use the output of the final hidden layer of speaker identification branch as an auxiliary feature. In addition, we use multi-head self-attention for capturing long-term dependencies in the speech and noise. Experimental results on a public dataset show that our strategy achieves the state-of-the-art performance and also outperform conventional methods in terms of subjective quality.
Kyoto University（京都大学）；RIKEN（理化学研究所）；National Institute of Advanced Industrial Science and Technology (AIST)（产业技术综合研究所（AIST））；Institut Polytechnique de Paris（巴黎理工学院）
This paper describes noisy speech recognition for an augmented reality headset that helps verbal communication within real multiparty conversational environments. A major approach that has actively been studied in simulated environments is to sequentially perform speech enhancement and automatic speech recognition (ASR) based on deep neural networks (DNNs) trained in a supervised manner. In our task, however, such a pretrained system fails to work due to the mismatch between the training and test conditions and the head movements of the user. To enhance only the utterances of a target speaker,…
Head Orientation Estimation with Distributed Microphones Using Speech Radiation Patterns
2 Department of Electrical Engineering (ESAT), KU Leuven, Leuven, Belgium；Medical\；University\,of\；4 Department of Electronic Systems, Aalborg University, Aalborg, Denmark
Many hearing-impaired listeners struggle to localize sounds due to poor availability of binaural cues. Listeners with a cochlear implant and a contralateral hearing aid -- so-called bimodal listeners -- are amongst the worst performers, as both interaural time and level differences are poorly transmitted. We present a new method to enhance head shadow in the low frequencies. Head shadow enhancement is achieved with a fixed beamformer with contralateral attenuation in each ear. The method results in interaural level differences which vary monotonically with angle. It also improves low-frequency…
Hand-crafted spatial features, such as inter-channel intensity difference (IID) and inter-channel phase difference (IPD), play a fundamental role in recent deep learning based dual-microphone speech enhancement (DMSE) systems. However, learning the mutual relationship between artificially designed spatial and spectral features is hard in the end-to-end DMSE. In this work, a novel architecture for DMSE using a multi-head cross-attention based convolutional recurrent network (MHCA-CRN) is presented. The proposed MHCA-CRN model includes a channel-wise encoding structure for preserving intra-chann…
Newcastle University（纽卡斯尔大学）；University of Oxford（牛津大学）；University of Sheffield（谢菲尔德大学）
As a category of transfer learning, domain adaptation plays an important role in generalizing the model trained in one task and applying it to other similar tasks or settings. In speech enhancement, a well-trained acoustic model can be exploited to obtain the speech signal in the context of other languages, speakers, and environments. Recent domain adaptation research was developed more effectively with various neural networks and high-level abstract features. However, the related studies are more likely to transfer the well-trained model from a rich and more diverse domain to a limited and si…
Automatic speech recognition is a difficult problem in pattern recognition because several sources of variability exist in the speech input like the channel variations, the input might be clean or noisy, the speakers may have different accent and variations in the gender, etc. As a result, domain adaptation is important in speech recognition where we train the model for a particular source domain and test it on a different target domain. In this paper, we propose a technique to perform unsupervised gender-based domain adaptation in speech recognition using phonetic features. The experiments ar…
Northwestern Polytechnical University（西北工业大学）；Delft University of Technology（代尔夫特理工大学）
Automatically generating videos in which synthesized speech is synchronized with lip movements in a talking head has great potential in many human-computer interaction scenarios. In this paper, we present an automatic method to generate synchronized speech and talking-head videos on the basis of text and a single face image of an arbitrary person as input. In contrast to previous text-driven talking head generation methods, which can only synthesize the voice of a specific person, the proposed method is capable of synthesizing speech for any person that is inaccessible in the training stage. S…
Neural network based end-to-end Text-to-Speech (TTS) has greatly improved the quality of synthesized speech. While how to use massive spontaneous speech without transcription efficiently still remains an open problem. In this paper, we propose MHTTS, a fast multi-speaker TTS system that is robust to transcription errors and speaking style speech data. Specifically, we introduce a multi-head model and transfer text information from high-quality corpus with manual transcription to spontaneous speech with imperfectly recognized transcription by jointly training them. MHTTS has three advantages: 1…
National Institute of Informatics（国立信息学研究所）；Unversity of Edinburgh（爱丁堡大学）
This paper proposes a new architecture for speaker adaptation of multi-speaker neural-network speech synthesis systems, in which an unseen speaker's voice can be built using a relatively small amount of speech data without transcriptions. This is sometimes called "unsupervised speaker adaptation". More specifically, we concatenate the layers to the audio inputs when performing unsupervised speaker adaptation while we concatenate them to the text inputs when synthesizing speech from text. Two new training schemes for the new architecture are also proposed in this paper. These training schemes a…
University of Maryland, College Park（马里兰大学帕克分校）；Apple（苹果公司）
Synthesizing natural head motion to accompany speech for an embodied conversational agent is necessary for providing a rich interactive experience. Most prior works assess the quality of generated head motion by comparing them against a single ground-truth using an objective metric. Yet there are many plausible head motion sequences to accompany a speech utterance. In this work, we study the variation in the perceptual quality of head motions sampled from a generative model. We show that, despite providing more diverse head motions, the generative model produces motions with varying degrees of…
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, …
Speech recognizers trained on close-talking speech do not generalize to distant speech and the word error rate degradation can be as large as 40% absolute. Most studies focus on tackling distant speech recognition as a separate problem, leaving little effort to adapting close-talking speech recognizers to distant speech. In this work, we review several approaches from a domain adaptation perspective. These approaches, including speech enhancement, multi-condition training, data augmentation, and autoencoders, all involve a transformation of the data between domains. We conduct experiments on t…
This study investigates the direct use of speech waveforms to predict head motion for speech-driven head-motion synthesis, whereas the use of spectral features such as MFCC as basic input features together with additional features such as energy and F0 is common in the literature. We show that, rather than combining different features that originate from waveforms, it is more effective to use waveforms directly predicting corresponding head motion. The challenge with the waveform-based approach is that waveforms contain a large amount of information irrelevant to predict head motion, which hin…
Generating 3D speech-driven talking head has received more and more attention in recent years. Recent approaches mainly have following limitations: 1) most speaker-independent methods need handcrafted features that are time-consuming to design or unreliable; 2) there is no convincing method to support multilingual or mixlingual speech as input. In this work, we propose a novel approach using phonetic posteriorgrams (PPG). In this way, our method doesn't need hand-crafted features and is more robust to noise compared to recent approaches. Furthermore, our method can support multilingual speech …
Speech model adaptation is crucial to handle the discrepancy between server-side proxy training data and actual data received on local devices of users. With the use of federated learning (FL), we introduce an efficient approach on continuously adapting neural network language models (NNLMs) on private devices with applications on automatic speech recognition (ASR). To address the potential speech transcription errors in the on-device training corpus, we perform empirical studies on comparing various strategies of leveraging token-level confidence scores to improve the NNLM quality in the FL s…
Attention layers are an integral part of modern end-to-end automatic speech recognition systems, for instance as part of the Transformer or Conformer architecture. Attention is typically multi-headed, where each head has an independent set of learned parameters and operates on the same input feature sequence. The output of multi-headed attention is a fusion of the outputs from the individual heads. We empirically analyze the diversity between representations produced by the different attention heads and demonstrate that the heads become highly correlated during the course of training. We inves…
National Taiwan University（台湾大学）；Google Brain（谷歌大脑）
Speech distortions are a long-standing problem that degrades the performance of supervisely trained speech processing models. It is high time that we enhance the robustness of speech processing models to obtain good performance when encountering speech distortions while not hurting the original performance on clean speech. In this work, we propose to improve the robustness of speech processing models by domain adversarial training (DAT). We conducted experiments based on the SUPERB framework on five different speech processing tasks. In case we do not always have knowledge of the distortion ty…
National Institute of Informatics（国立信息学研究所）；SOKENDAI (The Graduate University for Advanced Studies)（综合研究大学院大学）；University of Edinburgh（爱丁堡大学）
By representing speaker characteristic as a single fixed-length vector extracted solely from speech, we can train a neural multi-speaker speech synthesis model by conditioning the model on those vectors. This model can also be adapted to unseen speakers regardless of whether the transcript of adaptation data is available or not. However, this setup restricts the speaker component to just a single bias vector, which in turn limits the performance of adaptation process. In this study, we propose a novel speech synthesis model, which can be adapted to unseen speakers by fine-tuning part of or all…
Southern University of Science and Technology（南方科技大学）；Microsoft China（微软中国）
Machine Speech Chain, which integrates both end-to-end (E2E) automatic speech recognition (ASR) and text-to-speech (TTS) into one circle for joint training, has been proven to be effective in data augmentation by leveraging large amounts of unpaired data. In this paper, we explore the TTS->ASR pipeline in speech chain to do domain adaptation for both neural TTS and E2E ASR models, with only text data from target domain. We conduct experiments by adapting from audiobook domain (LibriSpeech) to presentation domain (TED-LIUM), there is a relative word error rate (WER) reduction of 10% for the E2E…
University of Edinburgh（爱丁堡大学）；JPMorgan Chase（摩根大通）；Microsoft Corporation（微软公司）；University of New South Wales（新南威尔士大学）；Apple（苹果公司）
We present a structured overview of adaptation algorithms for neural network-based speech recognition, considering both hybrid hidden Markov model / neural network systems and end-to-end neural network systems, with a focus on speaker adaptation, domain adaptation, and accent adaptation. The overview characterizes adaptation algorithms as based on embeddings, model parameter adaptation, or data augmentation. We present a meta-analysis of the performance of speech recognition adaptation algorithms, based on relative error rate reductions as reported in the literature.
Automatic Speech Recognition (ASR) systems are often optimized to work best for speakers with canonical speech patterns. Unfortunately, these systems perform poorly when tested on atypical speech and heavily accented speech. It has previously been shown that personalization through model fine-tuning substantially improves performance. However, maintaining such large models per speaker is costly and difficult to scale. We show that by adding a relatively small number of extra parameters to the encoder layers via so-called residual adapter, we can achieve similar adaptation gains compared to mod…
For supervised speech enhancement, contextual information is important for accurate spectral mapping. However, commonly used deep neural networks (DNNs) are limited in capturing temporal contexts. To leverage long-term contexts for tracking a target speaker, this paper treats the speech enhancement as sequence-to-sequence mapping, and propose a novel monaural speech enhancement U-net structure based on Transformer, dubbed U-Former. The key idea is to model long-term correlations and dependencies, which are crucial for accurate noisy speech modeling, through the multi-head attention mechanisms.…
Speaker adaptation methods aim to create fair quality synthesis speech voice font for target speakers while only limited resources available. Recently, as deep neural networks based statistical parametric speech synthesis (SPSS) methods become dominant in SPSS TTS back-end modeling, speaker adaptation under the neural network based SPSS framework has also became an important task. In this paper, linear networks (LN) is inserted in multiple neural network layers and fine-tuned together with output layer for best speaker adaptation performance. When adaptation data is extremely small, the low-ra…
Automatic speech recognition models are often adapted to improve their accuracy in a new domain. A potential drawback of model adaptation to new domains is catastrophic forgetting, where the Word Error Rate on the original domain is significantly degraded. This paper addresses the situation when we want to simultaneously adapt automatic speech recognition models to a new domain and limit the degradation of accuracy on the original domain without access to the original training dataset. We propose several techniques such as a limited training strategy and regularized adapter modules for the Tra…
End-to-end speech-to-text translation models are often initialized with pre-trained speech encoder and pre-trained text decoder. This leads to a significant training gap between pre-training and fine-tuning, largely due to the modality differences between speech outputs from the encoder and text inputs to the decoder. In this work, we aim to bridge the modality gap between speech and text to improve translation quality. We propose M-Adapter, a novel Transformer-based module, to adapt speech representations to text. While shrinking the speech sequence, M-Adapter produces features desired for sp…
University College London（伦敦大学学院）；Nokia Bell Labs（诺基亚贝尔实验室）；University of Oxford（牛津大学）
This paper introduces a new dataset, Libri-Adapt, to support unsupervised domain adaptation research on speech recognition models. Built on top of the LibriSpeech corpus, Libri-Adapt contains English speech recorded on mobile and embedded-scale microphones, and spans 72 different domains that are representative of the challenging practical scenarios encountered by ASR models. More specifically, Libri-Adapt facilitates the study of domain shifts in ASR models caused by a) different acoustic environments, b) variations in speaker accents, c) heterogeneity in the hardware and platform software of…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；RIKEN（理化学研究所）
In previous work, we developed a closed-loop speech chain model based on deep learning, in which the architecture enabled the automatic speech recognition (ASR) and text-to-speech synthesis (TTS) components to mutually improve their performance. This was accomplished by the two parts teaching each other using both labeled and unlabeled data. This approach could significantly improve model performance within a single-speaker speech dataset, but only a slight increase could be gained in multi-speaker tasks. Furthermore, the model is still unable to handle unseen speakers. In this paper, we prese…
South China University of Technology（华南理工大学）；Tencent（腾讯）
The attention mechanism of the Listen, Attend and Spell (LAS) model requires the whole input sequence to calculate the attention context and thus is not suitable for online speech recognition. To deal with this problem, we propose multi-head monotonic chunk-wise attention (MTH-MoChA), an improved version of MoChA. MTH-MoChA splits the input sequence into small chunks and computes multi-head attentions over the chunks. We also explore useful training strategies such as LSTM pooling, minimum world error rate training and SpecAugment to further improve the performance of MTH-MoChA. Experiments on…
On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition
The Chinese University of Hong Kong（香港中文大学）；Chinese Academy of Sciences（中国科学院）；China National Research Council Canada（中国国家研究委员会加拿大）；Institute of Software（软件研究所）
Streaming end-to-end speech recognition models have been widely applied to mobile devices and show significant improvement in efficiency. These models are typically trained on the server using transcribed speech data. However, the server data distribution can be very different from the data distribution on user devices, which could affect the model performance. There are two main challenges for on device training, limited reliable labels and limited training memory. While self-supervised learning algorithms can mitigate the mismatch between domains using unlabeled data, they are not applicable…
Chinese University of Hong Kong（香港中文大学）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）
Despite the rapid progress of automatic speech recognition (ASR) technologies targeting normal speech in recent decades, accurate recognition of dysarthric and elderly speech remains highly challenging tasks to date. Sources of heterogeneity commonly found in normal speech including accent or gender, when further compounded with the variability over age and speech pathology severity level, create large diversity among speakers. To this end, speaker adaptation techniques play a key role in personalization of ASR systems for such users. Motivated by the spectro-temporal level differences between…
Despite the fact that neural networks are widely used for speech-driven head motion synthesis, it is well-known that the output of neural networks is noisy or discontinuous due to the limited capability of deep neural networks in predicting human motion. Thus, post-processing is required to obtain smooth head motion trajectories for animation. It is common to apply a linear filter or consider keyframes as post-processing. However, neither approach is optimal as there is always a trade-off between smoothness and accuracy. We propose to employ a neural network trained in a way that it is capable…
Multidisciplinary Institute of Artificial Intelligence (MIAI)（多学科人工智能研究所）
This paper investigates the impact of head movements on audio-visual speech enhancement (AVSE). Although being a common conversational feature, head movements have been ignored by past and recent studies: they challenge today's learning-based methods as they often degrade the performance of models that are trained on clean, frontal, and steady face images. To alleviate this problem, we propose to use robust face frontalization (RFF) in combination with an AVSE method based on a variational auto-encoder (VAE) model. We briefly describe the basic ingredients of the proposed pipeline and we perfo…
Sogang University（西江大学）；Naver Corp.（NAVER公司）；Clova AI Research（Clova人工智能研究院）
In general, the performance of automatic speech recognition (ASR) systems is significantly degraded due to the mismatch between training and test environments. Recently, a deep-learning-based image-to-image translation technique to translate an image from a source domain to a desired domain was presented, and cycle-consistent adversarial network (CycleGAN) was applied to learn a mapping for speech-to-speech conversion from a speaker to a target speaker. However, this method might not be adequate to remove corrupting noise components for robust ASR because it was designed to convert speech itse…
Zero-shot speaker adaptation aims to clone an unseen speaker's voice without any adaptation time and parameters. Previous researches usually use a speaker encoder to extract a global fixed speaker embedding from reference speech, and several attempts have tried variable-length speaker embedding. However, they neglect to transfer the personal pronunciation characteristics related to phoneme content, leading to poor speaker similarity in terms of detailed speaking styles and pronunciation habits. To improve the ability of the speaker encoder to model personal pronunciation characteristics, we pr…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）；Microsoft Azure Speech（微软Azure语音）
Text to speech (TTS) is widely used to synthesize personal voice for a target speaker, where a well-trained source TTS model is fine-tuned with few paired adaptation data (speech and its transcripts) on this target speaker. However, in many scenarios, only untranscribed speech data is available for adaptation, which brings challenges to the previous TTS adaptation pipelines (e.g., AdaSpeech). In this paper, we develop AdaSpeech 2, an adaptive TTS system that only leverages untranscribed speech data for adaptation. Specifically, we introduce a mel-spectrogram encoder to a well-trained TTS model…
Institute for Infocomm Research, A*STAR（资讯通信研究院，新加坡科技研究局）
Acoustic modeling for child speech is challenging due to the high acoustic variability caused by physiological differences in the vocal tract. The dearth of publicly available datasets makes the task more challenging. In this work, we propose a feature adaptation approach by exploiting adversarial multi-task training to minimize acoustic mismatch at the senone (tied triphone states) level between adult and child speech and leverage large amounts of transcribed adult speech. We validate the proposed method on three tasks: child speech recognition, child pronunciation assessment, and child fluen…
The target speech extraction has attracted widespread attention in recent years. In this work, we focus on investigating the dynamic interaction between different mixtures and the target speaker to exploit the discriminative target speaker clues. We propose a special attention mechanism without introducing any additional parameters in a scaling adaptation layer to better adapt the network towards extracting the target speech. Furthermore, by introducing a mixture embedding matrix pooling method, our proposed attention-based scaling adaptation (ASA) can exploit the target speaker clues in a mor…
Accent variability has posed a huge challenge to automatic speech recognition~(ASR) modeling. Although one-hot accent vector based adaptation systems are commonly used, they require prior knowledge about the target accent and cannot handle unseen accents. Furthermore, simply concatenating accent embeddings does not make good use of accent knowledge, which has limited improvements. In this work, we aim to tackle these problems with a novel layer-wise adaptation structure injected into the E2E ASR model encoder. The adapter layer encodes an arbitrary accent in the accent space and assists the AS…
Institute for Natural Language Processing, University of Stuttgart（斯图加特大学自然语言处理研究所）
In this paper, we investigate the use of adversarial learning for unsupervised adaptation to unseen recording conditions, more specifically, single microphone far-field speech. We adapt neural networks based acoustic models trained with close-talk clean speech to the new recording conditions using untranscribed adaptation data. Our experimental results on Italian SPEECON data set show that our proposed method achieves 19.8% relative word error rate (WER) reduction compared to the unadapted models. Furthermore, this adaptation method is beneficial even when performed on data from another langua…
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）
Recently, synthesizing personalized speech by text-to-speech (TTS) application is highly demanded. But the previous TTS models require a mass of target speaker speeches for training. It is a high-cost task, and hard to record lots of utterances from the target speaker. Data augmentation of the speeches is a solution but leads to the low-quality synthesis speech problem. Some multi-speaker TTS models are proposed to address the issue. But the quantity of utterances of each speaker imbalance leads to the voice similarity problem. We propose the Target Domain Adaptation Speech Synthesis Network (…
