Recently, attention-based transformers have become a de facto standard in many deep learning applications including natural language processing, computer vision, signal processing, etc.. In this paper, we propose a transformer-based end-to-end model to extract a target speaker's speech from a monaural multi-speaker mixed audio signal. Unlike existing speaker extraction methods, we introduce two additional objectives to impose speaker embedding consistency and waveform encoder invertibility and jointly train both speaker encoder and speech separator to better capture the speaker conditional embedding. Furthermore, we leverage a multi-scale discriminator to refine the perceptual quality of the extracted speech. Our experiments show that the use of a dual path transformer in the separator backbone along with proposed training paradigm improves the CNN baseline by $3.12$ dB points. Finally, we compare our approach with recent state-of-the-arts and show that our model outperforms existing methods by $4.1$ dB points on an average without creating additional data dependency.
Deep speaker embedding models have been commonly used as a building block for speaker diarization systems; however, the speaker embedding model is usually trained according to a global loss defined on the training data, which could be sub-optimal for distinguishing speakers locally in a specific meeting session. In this work we present the first use of graph neural networks (GNNs) for the speaker diarization problem, utilizing a GNN to refine speaker embeddings locally using the structural information between speech segments inside each session. The speaker embeddings extracted by a pre-traine…
This paper describes our submission to the Second Clarity Enhancement Challenge (CEC2), which consists of target speech enhancement for hearing-aid (HA) devices in noisy-reverberant environments with multiple interferers such as music and competing speakers. Our approach builds upon the powerful iterative neural/beamforming enhancement (iNeuBe) framework introduced in our recent work, and this paper extends it for target speaker extraction. We therefore name the proposed approach as iNeuBe-X, where the X stands for extraction. To address the challenges encountered in the CEC2 setting, we intro…
This report describes our submission to the track 1 and track 2 of the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC 2021). Both track 1 and track 2 share the same speaker verification system, which only uses VoxCeleb2-dev as our training set. This report explores several parts, including data augmentation, network structures, domain-based large margin fine-tuning, and back-end refinement. Our system is a fusion of 9 models and achieves first place in these two tracks of VoxSRC 2021. The minDCF of our submission is 0.1034, and the corresponding EER is 1.8460%.
Training-Free Multi-Step Inference for Target Speaker Extraction
Beijing University of Posts and Telecommunications, China（北京邮电大学，中国）；Center for Speech and Language Technologies, BNRist, Tsinghua University, China（语音与语言技术中心，北京理工大学，中国）
Department of Electrical and Computer Engineering National University of Singapore（新加坡国立大学电气与计算机工程系）
This work describes the speaker verification system developed by Human Language Technology Laboratory, National University of Singapore (HLT-NUS) for 2019 NIST Multimedia Speaker Recognition Evaluation (SRE). The multimedia research has gained attention to a wide range of applications and speaker recognition is no exception to it. In contrast to the previous NIST SREs, the latest edition focuses on a multimedia track to recognize speakers with both audio and visual information. We developed separate systems for audio and visual inputs followed by a score level fusion of the systems from the tw…
Cross-attention and Self-attention for Audio-visual Speaker Diarization in MISP-Meeting Challenge
Xiamen University（厦门大学）；Beijing Jiaotong University（北京交通大学）；School of Electronic Science and Engineering（电子科学与技术学院）；School of Electronic Information（电子信息学院）；School of Informatics（信息学院）
Fujitsu Research and Development Center（富士通研发中心）；Harbin Institute of Technology（哈尔滨工业大学）
Deep neural network with dual-path bi-directional long short-term memory (BiLSTM) block has been proved to be very effective in sequence modeling, especially in speech separation. This work investigates how to extend dual-path BiLSTM to result in a new state-of-the-art approach, called TasTas, for multi-talker monaural speech separation (a.k.a cocktail party problem). TasTas introduces two simple but effective improvements, one is an iterative multi-stage refinement scheme, and the other is to correct the speech with imperfect separation through a loss of speaker identity consistency between t…
See the Speaker: Crafting High-Resolution Talking Faces from Speech with Prior Guidance and Region Refinement
Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Speech and Acoustic Laboratory, Joy Future Academy, Jingdong Corporation（语音与声学实验室、Joy Future Academy、京东公司）；Aarhus University（阿arhus大学）
Confidence Score Guided Incremental and Speaker Adaptive Pseudo-Labeling for Semi-Supervised Elderly Speech Recognition
The Chinese University of Hong Kong, Hong Kong SAR, China（香港中文大学）；Institute of Software, Chinese Academy of Sciences, China（中国科学院软件研究所）；National Research Council Canada, Canada（加拿大国家研究理事会）
ASRRL-TTS: Agile Speaker Representation Reinforcement Learning for Text-to-Speech Speaker Adaptation
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Department of Automation, Tsinghua University（清华大学自动化系）；Beijing National Research Center for Information Science and Technology, Tsinghua University（北京信息科学与技术国家研究中心）；Kuaishou Technology Co., Ltd.（快手科技有限公司）；Tianjin University（天津大学）；Shanghai Polytechnic University（上海第二工业大学）
Cross-speaker style transfer (CSST) in text-to-speech (TTS) synthesis aims at transferring a speaking style to the synthesised speech in a target speaker's voice. Most previous CSST approaches rely on expensive high-quality data carrying desired speaking style during training and require a reference utterance to obtain speaking style descriptors as conditioning on the generation of a new sentence. This work presents Referee, a robust reference-free CSST approach for expressive TTS, which fully leverages low-quality data to learn speaking styles from text. Referee is built by cascading a text-t…
Personalized speech enhancement has been a field of active research for suppression of speechlike interferers such as competing speakers or TV dialogues. Compared with single channel approaches, multichannel PSE systems can be more effective in adverse acoustic conditions by leveraging the spatial information in microphone signals. However, the implementation of multichannel PSEs to accommodate a wide range of array topology in household applications can be challenging. To develop an array configuration agnostic PSE system, we define a spatial feature termed the long short term spatial coheren…
