Neural Speaker Embeddings for Ultrasound-based Silent Speech Interfaces
University of Szeged（塞格德大学）；MTA-SZTE Research Group on Artificial Intelligence（匈牙利科学院-塞格德大学人工智能研究组）；Budapest University of Technology and Economics（布达佩斯技术与经济大学）
Amin Honarmandi Shandiz, László Tóth, Gábor Gosztolya, Alexandra Markó, Tamás Gábor Csapó
Articulatory-to-acoustic mapping seeks to reconstruct speech from a recording of the articulatory movements, for example, an ultrasound video. Just like speech signals, these recordings represent not only the linguistic content, but are also highly specific to the actual speaker. Hence, due to the lack of multi-speaker data sets, researchers have so far concentrated on speaker-dependent modeling. Here, we present multi-speaker experiments using the recently published TaL80 corpus. To model speaker characteristics, we adjusted the x-vector framework popular in speech processing to operate with ultrasound tongue videos. Next, we performed speaker recognition experiments using 50 speakers from the corpus. Then, we created speaker embedding vectors and evaluated them on the remaining speakers. Finally, we examined how the embedding vector influences the accuracy of our ultrasound-to-speech conversion network in a multi-speaker scenario. In the experiments we attained speaker recognition error rates below 3%, and we also found that the embedding vectors generalize nicely to unseen speakers. Our first attempt to apply them in a multi-speaker silent speech framework brought about a marginal reduction in the error rate of the spectral estimation step.
Voice-activated systems are integrated into a variety of desktop, mobile, and Internet-of-Things (IoT) devices. However, voice spoofing attacks, such as impersonation and replay attacks, in which malicious attackers synthesize the voice of a victim or simply replay it, have brought growing security concerns. Existing speaker verification techniques distinguish individual speakers via the spectrographic features extracted from an audible frequency range of voice commands. However, they often have high error rates and/or long delays. In this paper, we explore a new direction of human voice resea…
Speaking Without Sound: Multi-speaker Silent Speech Voicing with Facial Inputs Only
Music and Audio Research Group (MARG)（音乐与音频研究组）；Department of Intelligence and Information（智能与信息系）；Interdisciplinary Program in Artificial Intelligence（人工智能跨学科项目）；Artificial Intelligence Institute, Seoul National University（首尔国立大学人工智能研究所）
Isolating the voice of a specific person while filtering out other voices or background noises is challenging when video is shot in noisy environments. We propose audio-visual methods to isolate the voice of a single speaker and eliminate unrelated sounds. First, face motions captured in the video are used to estimate the speaker's voice, by passing the silent video frames through a video-to-speech neural network-based model. Then the speech predictions are applied as a filter on the noisy input audio. This approach avoids using mixtures of sounds in the learning process, as the number of such…
We investigate multi-speaker speech recognition from ultrasound images of the tongue and video images of the lips. We train our systems on imaging data from modal speech, and evaluate on matched test sets of two speaking modes: silent and modal speech. We observe that silent speech recognition from imaging data underperforms compared to modal speech recognition, likely due to a speaking-mode mismatch between training and testing. We improve silent speech recognition performance using techniques that address the domain mismatch, such as fMLLR and unsupervised model adaptation. We also analyse t…
NTT Corporation（NTT公司）；Brno University of Technology（布尔诺理工大学）
Target speech extraction (TSE) extracts the speech of a target speaker in a mixture given auxiliary clues characterizing the speaker, such as an enrollment utterance. TSE addresses thus the challenging problem of simultaneously performing separation and speaker identification. There has been much progress in extraction performance following the recent development of neural networks for speech enhancement and separation. Most studies have focused on processing mixtures where the target speaker is actively speaking. However, the target speaker is sometimes silent in practice, i.e., inactive spea…
University Politehnica of Bucharest（布加勒斯特理工大学）；Technical University of Cluj-Napoca（克卢日-纳波卡技术大学）
The task of video-to-speech aims to translate silent video of lip movement to its corresponding audio signal. Previous approaches to this task are generally limited to the case of a single speaker, but a method that accounts for multiple speakers is desirable as it allows to i) leverage datasets with multiple speakers or few samples per speaker; and ii) control speaker identity at inference time. In this paper, we introduce a new video-to-speech architecture and explore ways of extending it to the multi-speaker scenario: we augment the network with an additional speaker-related input, through …
Voice Activity Detection (VAD) is not easy task when the input audio signal is noisy, and it is even more complicated when the input is not even an audio recording. This is the case with Silent Speech Interfaces (SSI) where we record the movement of the articulatory organs during speech, and we aim to reconstruct the speech signal from this recording. Our SSI system synthesizes speech from ultrasonic videos of the tongue movement, and the quality of the resulting speech signals are evaluated by metrics such as the mean squared error loss function of the underlying neural network and the Mel-Ce…
Self-Supervised Learning (SSL) has made great strides recently. SSL speech models achieve decent performance on a wide range of downstream tasks, suggesting that they extract different aspects of information from speech. However, how SSL models store various information in hidden representations without interfering is still poorly understood. Taking the recently successful SSL model, HuBERT, as an example, we explore how the SSL model processes and stores speaker information in the representation. We found that HuBERT stores speaker information in representations whose positions correspond to …
Silent speech interfaces (SSI) aim to reconstruct the speech signal from a recording of the articulatory movement, such as an ultrasound video of the tongue. Currently, deep neural networks are the most successful technology for this task. The efficient solution requires methods that do not simply process single images, but are able to extract the tongue movement information from a sequence of video frames. One option for this is to apply recurrent neural structures such as the long short-term memory network (LSTM) in combination with 2D convolutional neural networks (CNNs). Here, we experimen…
NTT Communication Science Laboratories, NTT Corporation（NTT集团NTT通信科学实验室）；Paderborn University（帕德博恩大学）
Automatic meeting analysis comprises the tasks of speaker counting, speaker diarization, and the separation of overlapped speech, followed by automatic speech recognition. This all has to be carried out on arbitrarily long sessions and, ideally, in an online or block-online manner. While significant progress has been made on individual tasks, this paper presents for the first time an all-neural approach to simultaneous speaker counting, diarization and source separation. The NN-based estimator operates in a block-online fashion and tracks speakers even if they remain silent for a number of tim…
Budapest University of Technology and Economics（布达佩斯技术与经济大学）；MTA-SZTE Research Group on Artificial Intelligence（匈牙利科学院-塞格德大学人工智能研究组）；University of Szeged（塞格德大学）
Recently it was shown that within the Silent Speech Interface (SSI) field, the prediction of F0 is possible from Ultrasound Tongue Images (UTI) as the articulatory input, using Deep Neural Networks for articulatory-to-acoustic mapping. Moreover, text-to-speech synthesizers were shown to produce higher quality speech when using a continuous pitch estimate, which takes non-zero pitch values even when voicing is not present. Therefore, in this paper on UTI-based SSI, we use a simple continuous F0 tracker which does not apply a strict voiced / unvoiced decision. Continuous vocoder parameters (Cont…
MTA-SZTE Research Group on Artificial Intelligence（MTA-SZTE人工智能研究组）；University of Szeged（塞格德大学）；Eötvös Loránd University（厄特沃什·罗兰大学）；Budapest University of Technology and Economics（布达佩斯技术与经济大学）
When using ultrasound video as input, Deep Neural Network-based Silent Speech Interfaces usually rely on the whole image to estimate the spectral parameters required for the speech synthesis step. Although this approach is quite straightforward, and it permits the synthesis of understandable speech, it has several disadvantages as well. Besides the inability to capture the relations between close regions (i.e. pixels) of the image, this pixel-by-pixel representation of the image is also quite uneconomical. It is easy to see that a significant part of the image is irrelevant for the spectral pa…
Adaptation of Tongue Ultrasound-Based Silent Speech Interfaces Using Spatial Transformer Networks
University of Szeged（塞格德大学）；ELRN-SZTE Research Group on Artificial Intelligence（ELRN-塞格德大学人工智能研究组）；Budapest University of Technology and Economics（布达佩斯技术与经济大学）
Ultrasound tongue imaging (UTI) provides a convenient way to visualize the vocal tract during speech production. UTI is increasingly being used for speech therapy, making it important to develop automatic methods to assist various time-consuming manual tasks currently performed by speech therapists. A key challenge is to generalize the automatic processing of ultrasound tongue images to previously unseen speakers. In this work, we investigate the classification of phonetic segments (tongue shapes) from raw ultrasound recordings under several training scenarios: speaker-dependent, multi-speaker…
The University of Tokyo（东京大学）；Sony Computer Science Laboratories（索尼计算机科学实验室）
The availability of digital devices operated by voice is expanding rapidly. However, the applications of voice interfaces are still restricted. For example, speaking in public places becomes an annoyance to the surrounding people, and secret information should not be uttered. Environmental noise may reduce the accuracy of speech recognition. To address these limitations, a system to detect a user's unvoiced utterance is proposed. From internal information observed by an ultrasonic imaging sensor attached to the underside of the jaw, our proposed system recognizes the utterance contents without…
In this paper, we propose NEC (Neural Enhanced Cancellation), a defense mechanism, which prevents unauthorized microphones from capturing a target speaker's voice. Compared with the existing scrambling-based audio cancellation approaches, NEC can selectively remove a target speaker's voice from a mixed speech without causing interference to others. Specifically, for a target speaker, we design a Deep Neural Network (DNN) model to extract high-level speaker-specific but utterance-independent vocal features from his/her reference audios. When the microphone is recording, the DNN generates a shad…
Target speech separation is the process of filtering a certain speaker's voice out of speech mixtures according to the additional speaker identity information provided. Recent works have made considerable improvement by processing signals in the time domain directly. The majority of them take fully overlapped speech mixtures for training. However, since most real-life conversations occur randomly and are sparsely overlapped, we argue that training with different overlap ratio data benefits. To do so, an unavoidable problem is that the popularly used SI-SNR loss has no definition for silent sou…
University of Edinburgh（爱丁堡大学）；University of Science and Technology of China（中国科学技术大学）；Queen Margaret University（玛格丽特女王大学）；Articulate Instruments Ltd.（Articulate仪器有限公司）
We present the Tongue and Lips corpus (TaL), a multi-speaker corpus of audio, ultrasound tongue imaging, and lip videos. TaL consists of two parts: TaL1 is a set of six recording sessions of one professional voice talent, a male native speaker of English; TaL80 is a set of recording sessions of 81 native speakers of English without voice talent experience. Overall, the corpus contains 24 hours of parallel ultrasound, video, and audio data, of which approximately 13.5 hours are speech. This paper describes the corpus and presents benchmark results for the tasks of speech recognition, speech syn…
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）
Silent speech interfaces (SSI) has been an exciting area of recent interest. In this paper, we present a non-invasive silent speech interface that uses inaudible acoustic signals to capture people's lip movements when they speak. We exploit the speaker and microphone of the smartphone to emit signals and listen to their reflections, respectively. The extracted phase features of these reflections are fed into the deep learning networks to recognize speech. And we also propose an end-to-end recognition framework, which combines the CNN and attention-based encoder-decoder network. Evaluation resu…
The goal of this work is to reconstruct speech from a silent talking face video. Recent studies have shown impressive performance on synthesizing speech from silent talking face videos. However, they have not explicitly considered on varying identity characteristics of different speakers, which place a challenge in the video-to-speech synthesis, and this becomes more critical in unseen-speaker settings. Our approach is to separate the speech content and the visage-style from a given silent talking face video. By guiding the model to independently focus on modeling the two representations, we c…
Adobe Systems（奥多比系统公司）；Netaji Subhas Institute of Technology（内塔吉·苏巴斯理工学院）；National Institute of Informatics（国立信息学研究所）；National University of Singapore（新加坡国立大学）
Speechreading or lipreading is the technique of understanding and getting phonetic features from a speaker's visual features such as movement of lips, face, teeth and tongue. It has a wide range of multimedia applications such as in surveillance, Internet telephony, and as an aid to a person with hearing impairments. However, most of the work in speechreading has been limited to text generation from silent videos. Recently, research has started venturing into generating (audio) speech from silent video sequences but there have been no developments thus far in dealing with divergent views and p…
We investigate the automatic processing of child speech therapy sessions using ultrasound visual biofeedback, with a specific focus on complementing acoustic features with ultrasound images of the tongue for the tasks of speaker diarization and time-alignment of target words. For speaker diarization, we propose an ultrasound-based time-domain signal which we call estimated tongue activity. For word-alignment, we augment an acoustic model with low-dimensional representations of ultrasound images of the tongue, learned by a convolutional neural network. We conduct our experiments using the Ultra…
Budapest University of Technology and Economics（布达佩斯技术与经济大学）；MTA-ELTE Lendület Lingual Articulation Research Group（MTA-ELTE Lendület 舌部发音研究组）；University of Szeged（塞格德大学）；MTA-SZTE Research Group on Artificial Intelligence（MTA-SZTE 人工智能研究组）；Eötvös Loránd University（厄特沃什·罗兰大学）
Articulatory information has been shown to be effective in improving the performance of HMM-based and DNN-based text-to-speech synthesis. Speech synthesis research focuses traditionally on text-to-speech conversion, when the input is text or an estimated linguistic representation, and the target is synthesized speech. However, a research field that has risen in the last decade is articulation-to-speech synthesis (with a target application of a Silent Speech Interface, SSI), when the goal is to synthesize speech from some representation of the movement of the articulatory organs. In this paper,…
Zhejiang University（浙江大学）；Royal Holloway, University of London（伦敦大学皇家霍洛威学院）
Silent Speech Decoding (SSD), based on articulatory neuromuscular activities, has become a prevalent task of Brain-Computer Interface (BCI) in recent years. Many works have been devoted to decoding surface electromyography (sEMG) from articulatory neuromuscular activities. However, restoring silent speech in tonal languages such as Mandarin Chinese is still difficult. This paper proposes an optimized Sequence-to-Sequence (Seq2Seq) approach to synthesize voice from the sEMG-based silent speech. We extract duration information to regulate the sEMG-based silent speech using the audio length. Then…
The University of Tokyo（东京大学）；CyberAgent, Inc.（赛博艾坚特公司）
Pause insertion, also known as phrase break prediction and phrasing, is an essential part of TTS systems because proper pauses with natural duration significantly enhance the rhythm and intelligibility of synthetic speech. However, conventional phrasing models ignore various speakers' different styles of inserting silent pauses, which can degrade the performance of the model trained on a multi-speaker speech corpus. To this end, we propose more powerful pause insertion frameworks based on a pre-trained language model. Our approach uses bidirectional encoder representations from transformers (B…
Though significant progress has been made for speaker-dependent Video-to-Speech (VTS) synthesis, little attention is devoted to multi-speaker VTS that can map silent video to speech, while allowing flexible control of speaker identity, all in a single system. This paper proposes a novel multi-speaker VTS system based on cross-modal knowledge transfer from voice conversion (VC), where vector quantization with contrastive predictive coding (VQCPC) is used for the content encoder of VC to derive discrete phoneme-like acoustic units, which are transferred to a Lip-to-Index (Lip2Ind) network to inf…
Speechreading is the task of inferring phonetic information from visually observed articulatory facial movements, and is a notoriously difficult task for humans to perform. In this paper we present an end-to-end model based on a convolutional neural network (CNN) for generating an intelligible and natural-sounding acoustic speech signal from silent video frames of a speaking person. We train our model on speakers from the GRID and TCD-TIMIT datasets, and evaluate the quality and intelligibility of reconstructed speech using common objective measurements. We show that speech predictions from th…
Budapest University of Technology and Economics（布达佩斯技术与经济大学）；University of Szeged, Institute of Informatics（塞格德大学信息学院）；HUN-REN–SZTE Research Group on Artificial Intelligence（HUN-REN–SZTE人工智能研究组）
Budapest University of Technology and Economics（布达佩斯技术与经济大学）；MTA-ELTE Lendület Lingual Articulation Research Group（MTA-ELTE Lendület 舌部发音研究组）
In this paper, we present our first experiments in text-to-articulation prediction, using ultrasound tongue image targets. We extend a traditional (vocoder-based) DNN-TTS framework with predicting PCA-compressed ultrasound images, of which the continuous tongue motion can be reconstructed in synchrony with synthesized speech. We use the data of eight speakers, train fully connected and recurrent neural networks, and show that FC-DNNs are more suitable for the prediction of sequential data than LSTMs, in case of limited training data. Objective experiments and visualized predictions show that t…
Budapest University of Technology and Economics（布达佩斯科技经济大学）；University of Szeged（塞格德大学）；MTA-SZTE Research Group on Artificial Intelligence（匈牙利科学院-塞格德大学人工智能研究组）；Eötvös Loránd University（厄特沃什·罗兰大学）；MTA-ELTE Lendület Lingual Articulation Research Group（匈牙利科学院-厄特沃什·罗兰大学林杜莱特舌部发音研究组）
For articulatory-to-acoustic mapping, typically only limited parallel training data is available, making it impossible to apply fully end-to-end solutions like Tacotron2. In this paper, we experimented with transfer learning and adaptation of a Tacotron2 text-to-speech model to improve the final synthesis quality of ultrasound-based articulatory-to-acoustic mapping with a limited database. We use a multi-speaker pre-trained Tacotron2 TTS model and a pre-trained WaveGlow neural vocoder. The articulatory-to-acoustic conversion contains three steps: 1) from a sequence of ultrasound tongue image r…
Voice activity detection (VAD) is an essential pre-processing step for tasks such as automatic speech recognition (ASR) and speaker recognition. A basic goal is to remove silent segments within an audio, while a more general VAD system could remove all the irrelevant segments such as noise and even unwanted speech from non-target speakers. We define the task, which only detects the speech from the target speaker, as speaker-dependent voice activity detection (SDVAD). This task is quite common in real applications and usually implemented by performing speaker verification (SV) on audio segments…
University of Oxford（牛津大学）；University of Bath（巴斯大学）
In this work, we address the problem of generating speech from silent lip videos for any speaker in the wild. In stark contrast to previous works, our method (i) is not restricted to a fixed number of speakers, (ii) does not explicitly impose constraints on the domain or the vocabulary and (iii) deals with videos that are recorded in the wild as opposed to within laboratory settings. The task presents a host of challenges, with the key one being that many features of the desired target speech, like voice, pitch and linguistic content, cannot be entirely inferred from the silent face video. In …
Lipreading has a lot of potential applications such as in the domain of surveillance and video conferencing. Despite this, most of the work in building lipreading systems has been limited to classifying silent videos into classes representing text phrases. However, there are multiple problems associated with making lipreading a text-based classification task like its dependence on a particular language and vocabulary mapping. Thus, in this paper we propose a multi-view lipreading to audio system, namely Lipper, which models it as a regression task. The model takes silent videos as input and pr…
CSTR, School of Informatics, University of Edinburgh, UK（英国爱丁堡大学信息学院语音技术研究中心）
Audiovisual synchronisation is the task of determining the time offset between speech audio and a video recording of the articulators. In child speech therapy, audio and ultrasound videos of the tongue are captured using instruments which rely on hardware to synchronise the two modalities at recording time. Hardware synchronisation can fail in practice, and no mechanism exists to synchronise the signals post hoc. To address this problem, we employ a two-stream neural network which exploits the correlation between the two modalities to find the offset. We train our model on recordings from 69 s…
University of British Columbia（不列颠哥伦比亚大学）；Haskins Laboratories（哈斯金斯实验室）
Thousands of individuals need surgical removal of their larynx due to critical diseases every year and therefore, require an alternative form of communication to articulate speech sounds after the loss of their voice box. This work addresses the articulatory-to-acoustic mapping problem based on ultrasound (US) tongue images for the development of a silent-speech interface (SSI) that can provide them with an assistance in their daily interactions. Our approach targets automatically extracting tongue movement information by selecting an optimal feature set from US images and mapping these featur…
Cross-Modal Masking for Robust Silent Speech Synthesis Using sEMG and Lipreading
Aholab research group within the HiTZ Center at University of the Basque Country (UPV/EHU)（巴斯克大学HiTZ中心内Aholab研究组）；PRHLT research center, Universitat Politècnica de València (UPV)（瓦伦西亚理工大学PRHLT研究中心）
Budapest University of Technology and Economics（布达佩斯技术与经济大学）；MTA-ELTE Lendület Lingual Articulation Research Group（MTA-ELTE伦杜莱特语言发音研究组）
Articulatory-to-acoustic (forward) mapping is a technique to predict speech using various articulatory acquisition techniques (e.g. ultrasound tongue imaging, lip video). Real-time MRI (rtMRI) of the vocal tract has not been used before for this purpose. The advantage of MRI is that it has a high `relative' spatial resolution: it can capture not only lingual, labial and jaw motion, but also the velum and the pharyngeal region, which is typically not possible with other techniques. In the current paper, we train various DNNs (fully connected, convolutional and recurrent neural networks) for art…
Incorporating Ultrasound Tongue Images for Audio-Visual Speech Enhancement
National Engineering Research Center of Speech and Language Information Processing（国家语言信息处理工程研究中心）；University of Science and Technology of China（中国科学技术大学）
Imperial College London（帝国理工学院）；Samsung AI Centre（三星人工智能中心）
Speech is a means of communication which relies on both audio and visual information. The absence of one modality can often lead to confusion or misinterpretation of information. In this paper we present an end-to-end temporal model capable of directly synthesising audio from silent video, without needing to transform to-and-from intermediate features. Our proposed approach, based on GANs is capable of producing natural sounding, intelligible speech which is synchronised with the video. The performance of our model is evaluated on the GRID dataset for both speaker dependent and speaker indepen…
Personalized speech enhancement (PSE) models achieve promising results compared with unconditional speech enhancement models due to their ability to remove interfering speech in addition to background noise. Unlike unconditional speech enhancement, causal PSE models may occasionally remove the target speech by mistake. The PSE models also tend to leak interfering speech when the target speaker is silent for an extended period. We show that existing PSE methods suffer from a trade-off between speech over-suppression and interference leakage by addressing one problem at the expense of the other.…
University of Edinburgh（爱丁堡大学）；University of Strathclyde（思克莱德大学）
Ultrasound tongue imaging is used to visualise the intra-oral articulators during speech production. It is utilised in a range of applications, including speech and language therapy and phonetics research. Ultrasound and speech audio are recorded simultaneously, and in order to correctly use this data, the two modalities should be correctly synchronised. Synchronisation is achieved using specialised hardware at recording time, but this approach can fail in practice resulting in data of limited usability. In this paper, we address the problem of automatically synchronising ultrasound and audio …
Articulatory strategy as a source of variation in acoustic vowel dynamics
Linguistics and English Language, University of Manchester, United Kingdom（曼彻斯特大学语言学与英语语言系，英国）；Linguistics and English Language, Lancaster University, United Kingdom（兰卡斯特大学语言学与英语语言系，英国）
Hierarchical Codec Diffusion for Video-to-Speech Generation
Fudan University（复旦大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
