Voice trigger detection is an important task, which enables activating a voice assistant when a target user speaks a keyword phrase. A detector is typically trained on speech data independent of speaker information and used for the voice trigger detection task. However, such a speaker independent voice trigger detector typically suffers from performance degradation on speech from underrepresented groups, such as accented speakers. In this work, we propose a novel voice trigger detector that can use a small number of utterances from a target speaker to improve detection accuracy. Our proposed model employs an encoder-decoder architecture. While the encoder performs speaker independent voice trigger detection, similar to the conventional detector, the decoder predicts a personalized embedding for each utterance. A personalized voice trigger score is then obtained as a similarity score between the embeddings of enrollment utterances and a test utterance. The personalized embedding allows adapting to target speaker's speech when computing the voice trigger score, hence improving voice trigger detection accuracy. Experimental results show that the proposed approach achieves a 38% relative reduction in a false rejection rate (FRR) compared to a baseline speaker independent voice trigger model.
Trigger-word detection plays an important role as the entry point of user's communication with voice assistants. But supporting a particular word as a trigger-word involves huge amount of data collection, augmentation and labelling for that word. This makes supporting new trigger-words a tedious and time consuming process. To combat this, we explore the use of contrastive learning as a pre-training task that helps the detection model to generalize to different words and noise conditions. We explore supervised contrastive techniques and also propose a novel self-supervised training technique us…
This paper describes the system developed by the NPU team for the 2020 personalized voice trigger challenge. Our submitted system consists of two independently trained subsystems: a small footprint keyword spotting (KWS) system and a speaker verification (SV) system. For the KWS system, a multi-scale dilated temporal convolutional (MDTC) network is proposed to detect wake-up word (WuW). For SV system, Write something here. The KWS predicts posterior probabilities of whether an audio utterance contains WuW and estimates the location of WuW at the same time. When the posterior probability ofWuW …
We present an architecture for voice trigger detection for virtual assistants. The main idea in this work is to exploit information in words that immediately follow the trigger phrase. We first demonstrate that by including more audio context after a detected trigger phrase, we can indeed get a more accurate decision. However, waiting to listen to more audio each time incurs a latency increase. Progressive Voice Trigger Detection allows us to trade-off latency and accuracy by accepting clear trigger candidates quickly, but waiting for more context to decide whether to accept more marginal exam…
We present a unified and hardware efficient architecture for two stage voice trigger detection (VTD) and false trigger mitigation (FTM) tasks. Two stage VTD systems of voice assistants can get falsely activated to audio segments acoustically similar to the trigger phrase of interest. FTM systems cancel such activations by using post trigger audio context. Traditional FTM systems rely on automatic speech recognition lattices which are computationally expensive to obtain on device. We propose a streaming transformer (TF) encoder architecture, which progressively processes incoming audio chunks a…
We propose a stacked 1D convolutional neural network (S1DCNN) for end-to-end small footprint voice trigger detection in a streaming scenario. Voice trigger detection is an important speech application, with which users can activate their devices by simply saying a keyword or phrase. Due to privacy and latency reasons, a voice trigger detection system should run on an always-on processor on device. Therefore, having small memory and compute cost is crucial for a voice trigger detection system. Recently, singular value decomposition filters (SVDFs) has been used for end-to-end voice trigger dete…
Huawei Technologies Research \& Development (UK) Ltd
End-to-end models have gradually become the main technical stream for voice trigger, aiming to achieve an utmost prediction accuracy but with a small footprint. In present paper, we propose an end-to-end voice trigger framework, namely WakeupNet, which is basically structured on a Transformer encoder. The purpose of this framework is to explore the context-capturing capability of Transformer, as sequential information is vital for wakeup-word detection. However, the conventional Transformer encoder is too large to fit our task. To address this issue, we introduce different model compression ap…
Budapest University of Technology and Economics（布达佩斯技术与经济大学）；Department of Telecommunications and Media Informatics（电信与媒体信息学系）；Faculty of Electrical Engineering and Informatics（电气工程与信息学院）；Department of Telecommunications（电信系）；Media Informatics Faculty of Electrical Engineering（电气工程媒体信息学院）；Informatics Budapest University of Technology（布达佩斯技术大学信息学院）
MOS (Mean Opinion Score) is a subjective method used for the evaluation of a system's quality. Telecommunications (for voice and video), and speech synthesis systems (for generated speech) are a few of the many applications of the method. While MOS tests are widely accepted, they are time-consuming and costly since human input is required. In addition, since the systems and subjects of the tests differ, the results are not really comparable. On the other hand, a large number of previous tests allow us to train machine learning models that are capable of predicting MOS value. By automatically p…
Voice-triggered smart assistants often rely on detection of a trigger-phrase before they start listening for the user request. Mitigation of false triggers is an important aspect of building a privacy-centric non-intrusive smart assistant. In this paper, we address the task of false trigger mitigation (FTM) using a novel approach based on analyzing automatic speech recognition (ASR) lattices using graph neural networks (GNN). The proposed approach uses the fact that decoding lattice of a falsely triggered audio exhibits uncertainties in terms of many alternative paths and unexpected words on t…
In this paper, we present the XMUSPEECH system for Task 1 of 2020 Personalized Voice Trigger Challenge (PVTC2020). Task 1 is a joint wake-up word detection with speaker verification on close talking data. The whole system consists of a keyword spotting (KWS) sub-system and a speaker verification (SV) sub-system. For the KWS system, we applied a Temporal Depthwise Separable Convolution Residual Network (TDSC-ResNet) to improve the system's performance. For the SV system, we proposed a multi-task learning network, where phonetic branch is trained with the character label of the utterance, and sp…
Fake the Real: Backdoor Attack on Deep Speech Classification via Voice Conversion
Ningbo University（宁波大学）；Zhejiang Key Laboratory of Mobile Network Application Technology（浙江省移动网络应用技术重点实验室）；Ningbo City College of Vocational Technology（宁波城市职业技术学院）
We propose a method to reduce false voice triggers of a speech-enabled personal assistant by post-processing the hypothesis lattice of a server-side large-vocabulary continuous speech recognizer (LVCSR) via a neural network. We first discuss how an estimate of the posterior probability of the trigger phrase can be obtained from the hypothesis lattice using known techniques to perform detection, then investigate a statistical model that processes the lattice in a more explicitly data-driven, discriminative manner. We propose using a Bidirectional Lattice Recurrent Neural Network (LatticeRNN) fo…
Sony Corporation（索尼公司）；University of Tsukuba（筑波大学）；Indian Institute of Technology Bombay（印度理工学院孟买分校）；Indian Institute of Science（印度科学学院）；Sony India Software Centre（索尼印度软件中心）
Despite recent advances in voice separation methods, many challenges remain in realistic scenarios such as noisy recording and the limits of available data. In this work, we propose to explicitly incorporate the phonetic and linguistic nature of speech by taking a transfer learning approach using an end-to-end automatic speech recognition (E2EASR) system. The voice separation is conditioned on deep features extracted from E2EASR to cover the long-term dependence of phonetic aspects. Experimental results on speech separation and enhancement task on the AVSpeech dataset show that the proposed me…
We describe the design of a voice trigger detection system for smart speakers. In this study, we address two major challenges. The first is that the detectors are deployed in complex acoustic environments with external noise and loud playback by the device itself. Secondly, collecting training examples for a specific keyword or trigger phrase is challenging resulting in a scarcity of trigger phrase specific training data. We describe a two-stage cascaded architecture where a low-power detector is always running and listening for the trigger phrase. If a detection is made at this stage, the can…
Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker. Previous works have made progress on voice conversion with parallel training data and pre-known speakers. However, zero-shot voice style transfer, which learns from non-parallel data and generates voices for previously unseen speakers, remains a challenging problem. We propose a novel zero-shot voice transfer method via disentangled representation learning. The proposed method first encodes speaker-related style and voice content of each input …
Automatic speech transcription and speaker recognition are usually treated as separate tasks even though they are interdependent. In this study, we investigate training a single network to perform both tasks jointly. We train the network in a supervised multi-task learning setup, where the speech transcription branch of the network is trained to minimise a phonetic connectionist temporal classification (CTC) loss while the speaker recognition branch of the network is trained to label the input sequence with the correct label for the speaker. We present a large-scale empirical study where the m…
In recent years, deep learning has surpassed traditional approaches to the problem of singing voice separation. The Wave-U-Net is a recent deep network architecture that operates directly on the time domain. The standard Wave-U-Net is trained with data augmentation and early stopping to prevent overfitting. Minimum hyperspherical energy (MHE) regularization has recently proven to increase generalization in image classification problems by encouraging a diversified filter configuration. In this work, we apply MHE regularization to the 1D filters of the Wave-U-Net. We evaluated this approach for…
One-shot voice cloning aims to transform speaker voice and speaking style in speech synthesized from a text-to-speech (TTS) system, where only a shot recording from the target reference speech can be used. Out-of-domain transfer is still a challenging task, and one important aspect that impacts the accuracy and similarity of synthetic speech is the conditional representations carrying speaker or style cues extracted from the limited references. In this paper, we present a novel one-shot voice cloning algorithm called Unet-TTS that has good generalization ability for unseen speakers and styles.…
One-shot voice conversion has received significant attention since only one utterance from source speaker and target speaker respectively is required. Moreover, source speaker and target speaker do not need to be seen during training. However, available one-shot voice conversion approaches are not stable for unseen speakers as the speaker embedding extracted from one utterance of an unseen speaker is not reliable. In this paper, we propose a deep discriminative speaker encoder to extract speaker embedding from one utterance more effectively. Specifically, the speaker encoder first integrates r…
Towards Improving the Expressiveness of Singing Voice Synthesis with BERT Derived Semantic Information
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Huya Inc.（虎牙公司）；The Chinese University of Hong Kong（香港中文大学）；XVerse Inc.（XVerse公司）
Detecting singing-voice in polyphonic instrumental music is critical to music information retrieval. To train a robust vocal detector, a large dataset marked with vocal or non-vocal label at frame-level is essential. However, frame-level labeling is time-consuming and labor expensive, resulting there is little well-labeled dataset available for singing-voice detection (S-VD). Hence, we propose a data augmentation method for S-VD by transfer learning. In this study, clean speech clips with voice activity endpoints and separate instrumental music clips are artificially added together to simulate…
When interacting with smart devices such as mobile phones or wearables, the user typically invokes a virtual assistant (VA) by saying a keyword or by pressing a button on the device. However, in many cases, the VA can accidentally be invoked by the keyword-like speech or accidental button press, which may have implications on user experience and privacy. To this end, we propose an acoustic false-trigger-mitigation (FTM) approach for on-device device-directed speech detection that simultaneously handles the voice-trigger and touch-based invocation. To facilitate the model deployment on-device, …
EmoAttack: Utilizing Emotional Voice Conversion for Speech Backdoor Attacks on Deep Speech Classification Models
School of Cyberspace Science Xiangtan University Xiangtan, China；School of Cyberspace Science Xiangtan University Beijing, China；School of Software \& Microelectronics Peking University Beijing, China
State-of-the-art singing voice separation is based on deep learning making use of CNN structures with skip connections (like U-net model, Wave-U-Net model, or MSDENSELSTM). A key to the success of these models is the availability of a large amount of training data. In the following study, we are interested in singing voice separation for mono signals and will investigate into comparing the U-Net and the Wave-U-Net that are structurally similar, but work on different input representations. First, we report a few results on variations of the U-Net model. Second, we will discuss the potential of …
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）；University of Science and Technology of China（中国科学技术大学）；Aquinas International Academy（阿奎那国际学院）
Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Recently, AutoVC, a conditional autoencoder based method, achieved excellent conversion results by disentangling the speaker identity and the speech content using information-constraining bottlenecks. However, due to the pure autoencoder training method, it is difficult to evaluate the separation effect of content and speaker identity. In this paper, a novel voice conversion framework, named $\boldsymbol T$ext $\boldsymbol G$uided $\boldsymbol A$utoVC(TGAVC), is proposed to more effectivel…
University of Costa Rica（哥斯达黎加大学）；Metropolitan Autonomous University（大都会自治大学）
Recent developments in speech synthesis have produced systems capable of outcome intelligible speech, but now researchers strive to create models that more accurately mimic human voices. One such development is the incorporation of multiple linguistic styles in various languages and accents. HMM-based Speech Synthesis is of great interest to many researchers, due to its ability to produce sophisticated features with small footprint. Despite such progress, its quality has not yet reached the level of the predominant unit-selection approaches that choose and concatenate recordings of real speech…
The Chinese University of Hong Kong（香港中文大学）；Sogou Inc.（搜狗公司）；Tencent PCG AIBU（腾讯平台与内容事业群AI业务单元）
Adversarial waveform generation has been a popular approach as the backend of singing voice conversion (SVC) to generate high-quality singing audio. However, the instability of GAN also leads to other problems, such as pitch jitters and U/V errors. It affects the smoothness and continuity of harmonics, hence degrades the conversion quality seriously. This paper proposes to feed harmonic signals to the SVC model in advance to enhance audio generation. We extract the sine excitation from the pitch, and filter it with a linear time-varying (LTV) filter estimated by a neural network. Both these tw…
The performance of voice-based Parkinson's disease (PD) detection systems degrades when there is an acoustic mismatch between training and operating conditions caused mainly by degradation in test signals. In this paper, we address this mismatch by considering three types of degradation commonly encountered in remote voice analysis, namely background noise, reverberation and nonlinear distortion, and investigate how these degradations influence the performance of a PD detection system. Given that the specific degradation is known, we explore the effectiveness of a variety of enhancement algori…
iFLYTEK Research, iFLYTEK Co., Ltd., Hefei, P.R.China（科大讯飞股份有限公司讯飞研究院，中国合肥）；Anhui Science and Technology Research Institute, Hefei, P.R.China（安徽省科学技术研究院，中国合肥）
This paper presents methods of making using of text supervision to improve the performance of sequence-to-sequence (seq2seq) voice conversion. Compared with conventional frame-to-frame voice conversion approaches, the seq2seq acoustic modeling method proposed in our previous work achieved higher naturalness and similarity. In this paper, we further improve its performance by utilizing the text transcriptions of parallel training data. First, a multi-task learning structure is designed which adds auxiliary classifiers to the middle layers of the seq2seq model and predicts linguistic labels as a…
Recently, more and more zero-shot voice conversion algorithms have been proposed. As a fundamental part of zero-shot voice conversion, speaker embeddings are the key to improving the converted speech's speaker similarity. In this paper, we study the impact of speaker embeddings on zero-shot voice conversion performance. To better represent the characteristics of the target speaker and improve the speaker similarity in zero-shot voice conversion, we propose a novel speaker representation method in this paper. Our method combines the advantages of D-vector, global style token (GST) based speaker…
In this paper, we address the task of determining whether a given utterance is directed towards a voice-enabled smart-assistant device or not. An undirected utterance is termed as a "false trigger" and false trigger mitigation (FTM) is essential for designing a privacy-centric non-intrusive smart assistant. The directedness of an utterance can be identified by running automatic speech recognition (ASR) on it and determining the user intent by analyzing the ASR transcript. But in case of a false trigger, transcribing the audio using ASR itself is strongly undesirable. To alleviate this issue, w…
Many-to-many voice conversion with non-parallel training data has seen significant progress in recent years. StarGAN-based models have been interests of voice conversion. However, most of the StarGAN-based methods only focused on voice conversion experiments for the situations where the number of speakers was small, and the amount of training data was large. In this work, we aim at improving the data efficiency of the model and achieving a many-to-many non-parallel StarGAN-based voice conversion for a relatively large number of speakers with limited training samples. In order to improve data e…
In this paper, we focus on improving the performance of the text-dependent speaker verification system in the scenario of limited training data. The speaker verification system deep learning based text-dependent generally needs a large scale text-dependent training data set which could be labor and cost expensive, especially for customized new wake-up words. In recent studies, voice conversion systems that can generate high quality synthesized speech of seen and unseen speakers have been proposed. Inspired by those works, we adopt two different voice conversion methods as well as the very simp…
A Concept-based approach to Voice Disorder Detection
Politecnico di Torino；CENTAI Institute（CENTAI研究院）；San Feliciano Hospital（San Feliciano医院）；SCDU Otorinolaringoiatria, Head Neck Cancer Unit, Ospedale San Giovanni Bosco（SCDU耳鼻喉科，头颈癌症单元，San Giovanni Bosco医院）；Dipartimento di Oncologia, Università degli Studi di Torino（肿瘤学系，托里尼大学）
NTT Communication Science Laboratories, NTT Corporation（日本电信电话株式会社NTT通信科学实验室）；Brno University of Technology（布尔诺理工大学）
Target speech extraction, which extracts a single target source in a mixture given clues about the target speaker, has attracted increasing attention. We have recently proposed SpeakerBeam, which exploits an adaptation utterance of the target speaker to extract his/her voice characteristics that are then used to guide a neural network towards extracting speech of that speaker. SpeakerBeam presents a practical alternative to speech separation as it enables tracking speech of a target speaker across utterances, and achieves promising speech extraction performance. However, it sometimes fails whe…
Faculty of Engineering and Technology（工程与技术学院）；Faculty of Audiology and Speech Language Pathology（听觉与语言病理学学院）；Sri Ramachandra Institute of Higher Education and Research（Sri Ramachandra 高等教育与研究学院）
Stress during public speaking is common and adversely affects performance and self-confidence. Extensive research has been carried out to develop various models to recognize emotional states. However, minimal research has been conducted to detect stress during public speaking in real time using voice analysis. In this context, the current review showed that the application of algorithms was not properly explored and helped identify the main obstacles in creating a suitable testing environment while accounting for current complexities and limitations. In this paper, we present our main idea and…
We present in this paper an ultra-low power (ULP) Recurrent Neural Network (RNN) based classifier for an always-on voice Wake-Up Sensor (WUS) with performances suitable for real-world applications. The purpose of our sensor is to bring down by at least a factor 100 the power consumption in background noise of always-on speech processing algorithms such as Automatic Speech Recognition, Keyword Spotting, Speaker Verification, etc. Unlike the other published approaches, we designed our wake-up sensor to be robust to unseen real-world noises for realistic levels of speech and noise by carefully de…
Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions
Interdisciplinary Program in Artificial Intelligence, Seoul National University（首尔国立大学人工智能跨学科项目）；Department of EE, Yonsei University（延世大学电子工程系）；Department of ECE, SNU（首尔国立大学电子与计算机工程系）；Department of AI, University of Seoul（首尔大学人工智能系）；AIIS, ASRI, INMC, and ISRC, SNU（首尔国立大学人工智能研究所、亚洲研究机构、智能网络研究中心和智能系统研究所以及首尔国立大学）
In this paper, we present a method for fine-tuning models trained on the Deep Noise Suppression (DNS) 2020 Challenge to improve their performance on Voice over Internet Protocol (VoIP) applications. Our approach involves adapting the DNS 2020 models to the specific acoustic characteristics of VoIP communications, which includes distortion and artifacts caused by compression, transmission, and platform-specific processing. To this end, we propose a multi-task learning framework for VoIP-DNS that jointly optimizes noise suppression and VoIP-specific acoustics for speech enhancement. We evaluate …
