With deep learning approaches becoming state-of-the-art in many speech (as well as non-speech) related machine learning tasks, efforts are being taken to delve into the neural networks which are often considered as a black box. In this paper it is analyzed how recurrent neural network (RNNs) cope with temporal dependencies by determining the relevant memory time span in a long short-term memory (LSTM) cell. This is done by leaking the state variable with a controlled lifetime and evaluating the task performance. This technique can be used for any task to estimate the time span the LSTM exploits in that specific scenario. The focus in this paper is on the task of separating speakers from overlapping speech. We discern two effects: A long term effect, probably due to speaker characterization and a short term effect, probably exploiting phone-size formant tracks.
In recent years there have been many deep learning approaches towards the multi-speaker source separation problem. Most use Long Short-Term Memory - Recurrent Neural Networks (LSTM-RNN) or Convolutional Neural Networks (CNN) to model the sequential behavior of speech. In this paper we propose a novel network for source separation using an encoder-decoder CNN and LSTM in parallel. Hyper parameters have to be chosen for both parts of the network and they are potentially mutually dependent. Since hyper parameter grid search has a high computational burden, random search is often preferred. Howeve…
Binghamton University（宾汉姆顿大学）；Sony Interactive Entertainment Inc（索尼互动娱乐公司）
In this paper, we present a reverberation removal approach for speaker verification, utilizing dual-label deep neural networks (DNNs). The networks perform feature mapping between the spectral features of reverberant and clean speech. Long short term memory recurrent neural networks (LSTMs) are trained to map corrupted Mel filterbank (MFB) features to two sets of labels: i) the clean MFB features, and ii) either estimated pitch tracks or the fast Fourier transform (FFT) spectrogram of clean speech. The performance of reverberation removal is evaluated by equal error rates (EERs) of speaker ver…
Google Inc.（谷歌公司）；Carnegie Mellon University（卡内基梅隆大学）
For many years, i-vector based audio embedding techniques were the dominant approach for speaker verification and speaker diarization applications. However, mirroring the rise of deep learning in various domains, neural network based audio embeddings, also known as d-vectors, have consistently demonstrated superior speaker verification performance. In this paper, we build on the success of d-vector based speaker verification systems to develop a new d-vector based approach to speaker diarization. Specifically, we combine LSTM-based d-vector audio embeddings with recent work in non-parametric c…
Duke Kunshan University（昆山杜克大学）；Sun Yat-sen University（中山大学）；LIMSI（法国计算机科学与自动化研究所）；CNRS（法国国家科学研究中心）；Univ. Paris-Sud（巴黎第十一大学）
More and more neural network approaches have achieved considerable improvement upon submodules of speaker diarization system, including speaker change detection and segment-wise speaker embedding extraction. Still, in the clustering stage, traditional algorithms like probabilistic linear discriminant analysis (PLDA) are widely used for scoring the similarity between two speech segments. In this paper, we propose a supervised method to measure the similarity matrix between all segments of an audio recording with sequential bidirectional long short-term memory networks (Bi-LSTM). Spectral cluste…
SenseTime Group Limited（商汤集团有限公司）；The University of Hong Kong（香港大学）
Speaker identification refers to the task of localizing the face of a person who has the same identity as the ongoing voice in a video. This task not only requires collective perception over both visual and auditory signals, the robustness to handle severe quality degradations and unconstrained content variations are also indispensable. In this paper, we describe a novel multimodal Long Short-Term Memory (LSTM) architecture which seamlessly unifies both visual and auditory modalities from the beginning of each sequence input. The key idea is to extend the conventional LSTM by not only sharing …
Human brain performs remarkably well in segregating a particular speaker from interfering ones in a multi-speaker scenario. It has been recently shown that we can quantitatively evaluate the segregation capability by modelling the relationship between the speech signals present in an auditory scene and the cortical signals of the listener measured using electroencephalography (EEG). This has opened up avenues to integrate neuro-feedback into hearing aids whereby the device can infer user's attention and enhance the attended speaker. Commonly used algorithms to infer the auditory attention are …
Aston University（阿斯顿大学）；University of Coimbra（科英布拉大学）；State University of Londrina（隆德里纳州立大学）
In speech recognition problems, data scarcity often poses an issue due to the willingness of humans to provide large amounts of data for learning and classification. In this work, we take a set of 5 spoken Harvard sentences from 7 subjects and consider their MFCC attributes. Using character level LSTMs (supervised learning) and OpenAI's attention-based GPT-2 models, synthetic MFCCs are generated by learning from the data provided on a per-subject basis. A neural network is trained to classify the data against a large dataset of Flickr8k speakers and is then compared to a transfer learning netw…
Automatic height and age estimation of speakers using acoustic features is widely used for the purpose of human-computer interaction, forensics, etc. In this work, we propose a novel approach of using attention mechanism to build an end-to-end architecture for height and age estimation. The attention mechanism is combined with Long Short-Term Memory(LSTM) encoder which is able to capture long-term dependencies in the input acoustic features. We modify the conventionally used Attention -- which calculates context vectors the sum of attention only across timeframes -- by introducing a modified c…
Columbia University（哥伦比亚大学）；Recognition Technologies, Inc.（识别技术公司）
Majority of speech signals across different scenarios are never available with well-defined audio segments containing only a single speaker. A typical conversation between two speakers consists of segments where their voices overlap, interrupt each other or halt their speech in between multiple sentences. Recent advancements in diarization technology leverage neural network-based approaches to improvise multiple subsystems of speaker diarization system comprising of extracting segment-wise embedding features and detecting changes in the speaker during conversation. However, to identify speaker…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
LSTM-based speaker verification usually uses a fixed-length local segment randomly truncated from an utterance to learn the utterance-level speaker embedding, while using the average embedding of all segments of a test utterance to verify the speaker, which results in a critical mismatch between testing and training. This mismatch degrades the performance of speaker verification, especially when the durations of training and testing utterances are very different. To alleviate this issue, we propose the deep segment attentive embedding method to learn the unified speaker embeddings for utteranc…
University of Stirling（斯特林大学）；Aix Marseille Univ（艾克斯-马赛大学）；CNRS（法国国家科学研究中心）；University of Sheffield（谢菲尔德大学）
Human auditory cortex excels at selectively suppressing background noise to focus on a target speaker. The process of selective attention in the brain is known to contextually exploit the available audio and visual cues to better focus on target speaker while filtering out other noises. In this study, we propose a novel deep neural network (DNN) based audiovisual (AV) mask estimation model. The proposed AV mask estimation model contextually integrates the temporal dynamics of both audio and noise-immune visual features for improved mask estimation and speech separation. For optimal AV features…
Fundamental frequency is one of the most important parameters of human speech, of importance for the classification of accent, gender, speaking styles, speaker identification, age, among others. The proper detection of this parameter remains as an important challenge for severely degraded signals. In previous references for detecting fundamental frequency in noisy speech using deep learning, the networks, such as Long Short-term Memory (LSTM) has been initialized with random weights, and then trained following a back-propagation through time algorithm. In this work, a proposal for a more effic…
Computational models for sarcasm detection have often relied on the content of utterances in isolation. However, speaker's sarcastic intent is not always obvious without additional context. Focusing on social media discussions, we investigate two issues: (1) does modeling of conversation context help in sarcasm detection and (2) can we understand what part of conversation context triggered the sarcastic reply. To address the first issue, we investigate several types of Long Short-Term Memory (LSTM) networks that can model both the conversation context and the sarcastic response. We show that t…
We propose an end to end deep learning approach for generating real-time facial animation from just audio. Specifically, our deep architecture employs deep bidirectional long short-term memory network and attention mechanism to discover the latent representations of time-varying contextual information within the speech and recognize the significance of different information contributed to certain face status. Therefore, our model is able to drive different levels of facial movements at inference and automatically keep up with the corresponding pitch and latent speaking style in the input audio…
Modular Deep Learning Framework for Assistive Perception: Gaze, Affect, and Speaker Identification
School of Computer Science and Engineering (SCOPE)（计算机科学与工程学院）；Vellore Institute of Technology (VIT)（韦洛雷理工学院）；School of Electronics Engineering (SENSE)（电子工程学院）
University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）；Istituto Italiano di Tecnologia（意大利理工学院）
In this paper, we address the problem of enhancing the speech of a speaker of interest in a cocktail party scenario when visual information of the speaker of interest is available. Contrary to most previous studies, we do not learn visual features on the typically small audio-visual datasets, but use an already available face landmark detector (trained on a separate image dataset). The landmarks are used by LSTM-based models to generate time-frequency masks which are applied to the acoustic mixed-speech spectrogram. Results show that: (i) landmark motion features are very effective features fo…
Tsinghua University（清华大学）；University of Science and Technology of China（中国科学技术大学）；University of Michigan（密歇根大学）；Columbia University in the City of New York（纽约哥伦比亚大学）；National University of Defense Technology（国防科技大学）
A challenge in speech production research is to predict future tongue movements based on a short period of past tongue movements. This study tackles speaker-dependent tongue motion prediction problem in unlabeled ultrasound videos with convolutional long short-term memory (ConvLSTM) networks. The model has been tested on two different ultrasound corpora. ConvLSTM outperforms 3-dimensional convolutional neural network (3DCNN) in predicting the 9\textsuperscript{th} frames based on 8 preceding frames, and also demonstrates good capacity to predict only the tongue contours in future frames. Furth…
Istituto Italiano di Tecnologia（意大利技术研究院）；University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）
We propose a method to address audio-visual target speaker enhancement in multi-talker environments using event-driven cameras. State of the art audio-visual speech separation methods shows that crucial information is the movement of the facial landmarks related to speech production. However, all approaches proposed so far work offline, using frame-based video input, making it difficult to process an audio-visual signal with low latency, for online applications. In order to overcome this limitation, we propose the use of event-driven cameras and exploit compression, high temporal resolution an…
VoxKnesset: A Large-Scale Longitudinal Hebrew Speech Dataset for Aging Speaker Modeling
Department of Computer Science and Applied Mathematics, Department of Molecular Cell Biology, Weizmann Institute of Science（计算机科学与应用数学系、分子细胞生物学系、魏茨曼科学研究所）
Deep convolutional neural networks (CNNs) have brought breakthroughs in processing clinical electrocardiograms (ECGs), speaker-independent speech and complex images. However, typical CNNs require a fixed input size while it is common to process variable-size data in practical use. Recurrent networks such as long short-term memory (LSTM) are capable of eliminating the restriction, but suffer from high computational complexity. In this paper, we propose local pattern aggregation-based deep-learning models to effectively deal with both problems. The novel network structure, called LPANet, has cro…
We present an end-to-end speech recognition model that learns interaction between two speakers based on the turn-changing information. Unlike conventional speech recognition models, our model exploits two speakers' history of conversational-context information that spans across multiple turns within an end-to-end framework. Specifically, we propose a speaker-specific cross-attention mechanism that can look at the output of the other speaker side as well as the one of the current speaker for better at recognizing long conversations. We evaluated the models on the Switchboard conversational spee…
MILA（米拉研究所）；Université de Montréal（蒙特利尔大学）；Samsung Advanced Institute of Technology（三星先进技术研究院）
Layer normalization is a recently introduced technique for normalizing the activities of neurons in deep neural networks to improve the training speed and stability. In this paper, we introduce a new layer normalization technique called Dynamic Layer Normalization (DLN) for adaptive neural acoustic modeling in speech recognition. By dynamically generating the scaling and shifting parameters in layer normalization, DLN adapts neural acoustic models to the acoustic variability arising from various factors such as speakers, channel noises, and environments. Unlike other adaptive acoustic models, …
Tsinghua University（清华大学）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Acoustics, Chinese Academy of Sciences（中国科学院声学研究所）；North China Power Engineering CO., LTD. of China Power Engineering Consulting Group（中国电力工程顾问集团华北电力设计院有限公司）
Utterance-level permutation invariant training (uPIT) has achieved promising progress on single-channel multi-talker speech separation task. Long short-term memory (LSTM) and bidirectional LSTM (BLSTM) are widely used as the separation networks of uPIT, i.e. uPIT-LSTM and uPIT-BLSTM. uPIT-LSTM has lower latency but worse performance, while uPIT-BLSTM has better performance but higher latency. In this paper, we propose using latency-controlled BLSTM (LC-BLSTM) during inference to fulfill low-latency and good-performance speech separation. To find a better training strategy for BLSTM-based separ…
University of Sheffield（谢菲尔德大学）；NIHR Biomedical Research Centre（NIHR生物医学研究中心）；King’s College London（伦敦国王学院）
In the sentence classification task, context formed from sentences adjacent to the sentence being classified can provide important information for classification. This context is, however, often ignored. Where methods do make use of context, only small amounts are considered, making it difficult to scale. We present a new method for sentence classification, Context-LSTM-CNN, that makes use of potentially large contexts. The method also utilizes long-range dependencies within the sentence being classified, using an LSTM, and short-span features, using a stacked CNN. Our experiments demonstrate …
We introduce BERTphone, a Transformer encoder trained on large speech corpora that outputs phonetically-aware contextual representation vectors that can be used for both speaker and language recognition. This is accomplished by training on two objectives: the first, inspired by adapting BERT to the continuous domain, involves masking spans of input frames and reconstructing the whole sequence for acoustic representation learning; the second, inspired by the success of bottleneck features from ASR, is a sequence-level CTC loss applied to phoneme labels for phonetic representation learning. We p…
Energy consumed in buildings takes significant portions of the total global energy usage. A large amount of building energy is used for heating, cooling, ventilation, and air-conditioning (HVAC). However, compared to its importance, building energy management systems nowadays are limited in controlling HVAC based on simple rule-based control (RBC) technologies. The ability to design systems that can efficiently manage HVAC can reduce energy usage and greenhouse gas emissions, and, all in all, it can help us to mitigate climate change. This paper proposes predictive time-series models of occupa…
Indian Association for the Cultivation of Science（印度科学培育协会）
Development of new drugs is an expensive and time-consuming process. Due to the world-wide SARS-CoV-2 outbreak, it is essential that new drugs for SARS-CoV-2 are developed as soon as possible. Drug repurposing techniques can reduce the time span needed to develop new drugs by probing the list of existing FDA-approved drugs and their properties to reuse them for combating the new disease. We propose a novel architecture DeepGLSTM, which is a Graph Convolutional network and LSTM based method that predicts binding affinity values between the FDA-approved drugs and the viral proteins of SARS-CoV-2…
Deep Learning for Financial Time Series: A Large-Scale Benchmark of Risk-Adjusted Performance
Machine Learning Research Group, Department of Engineering Science, University of Oxford（牛津大学工程科学系机器学习研究组）；Oxford-Man Institute of Quantitative Finance, University of Oxford（牛津大学量化金融研究所）
