Outdoor acoustic events detection is an exciting research field but challenged by the need for complex algorithms and deep learning techniques, typically requiring many computational, memory, and energy resources. This challenge discourages IoT implementation, where an efficient use of resources is required. However, current embedded technologies and microcontrollers have increased their capabilities without penalizing energy efficiency. This paper addresses the application of sound event detection at the edge, by optimizing deep learning techniques on resource-constrained embedded platforms for the IoT. The contribution is two-fold: firstly, a two-stage student-teacher approach is presented to make state-of-the-art neural networks for sound event detection fit on current microcontrollers; secondly, we test our approach on an ARM Cortex M4, particularly focusing on issues related to 8-bits quantization. Our embedded implementation can achieve 68% accuracy in recognition on Urbansound8k, not far from state-of-the-art performance, with an inference time of 125 ms for each second of the audio stream, and power consumption of 5.5 mW in just 34.3 kB of RAM.
Sound event detection (SED) and acoustic scene classification (ASC) are important research topics in environmental sound analysis. Many research groups have addressed SED and ASC using neural-network-based methods, such as the convolutional neural network (CNN), recurrent neural network (RNN), and convolutional recurrent neural network (CRNN). The conventional methods address SED and ASC separately even though sound events and acoustic scenes are closely related to each other. For example, in the acoustic scene "office," the sound events "mouse clicking" and "keyboard typing" are likely to occ…
This paper proposes acoustic event detection (AED) with classifier chains, a new classifier based on the probabilistic chain rule. The proposed AED with classifier chains consists of a gated recurrent unit and performs iterative binary detection of each event one by one. In each iteration, the event's activity is estimated and used to condition the next output based on the probabilistic chain rule to form classifier chains. Therefore, the proposed method can handle the interdependence among events upon classification, while the conventional AED methods with multiple binary classifiers with a l…
Amazon.com Inc.（亚马逊公司）；Toyota Technological Institute at Chicago（芝加哥丰田技术研究院）
This paper proposes a network architecture mainly designed for audio tagging, which can also be used for weakly supervised acoustic event detection (AED). The proposed network consists of a modified DenseNet as the feature extractor, and a global average pooling (GAP) layer to predict frame-level labels at inference time. This architecture is inspired by the work proposed by Zhou et al., a well-known framework using GAP to localize visual objects given image-level labels. While most of the previous works on weakly supervised AED used recurrent layers with attention-based mechanism to localize …
Acoustic event detection and scene classification are major research tasks in environmental sound analysis, and many methods based on neural networks have been proposed. Conventional methods have addressed these tasks separately; however, acoustic events and scenes are closely related to each other. For example, in the acoustic scene `office', the acoustic events `mouse clicking' and `keyboard typing' are likely to occur. In this paper, we propose multitask learning for joint analysis of acoustic events and scenes, which shares the parts of the networks holding information on acoustic events a…
University of Kent（肯特大学）；University of Oxford（牛津大学）
Acoustic scenes are rich and redundant in their content. In this work, we present a spatio-temporal attention pooling layer coupled with a convolutional recurrent neural network to learn from patterns that are discriminative while suppressing those that are irrelevant for acoustic scene classification. The convolutional layers in this network learn invariant features from time-frequency input. The bidirectional recurrent layers are then able to encode the temporal dynamics of the resulting convolutional features. Afterwards, a two-dimensional attention mask is formed via the outer product of t…
IMT Atlantique（大西洋国立高等工业技术与矿业学校）；Dalhousie University（达尔豪斯大学）；Polish Academy of Sciences（波兰科学院）
In this paper, we adapt Recurrent Neural Networks with Stochastic Layers, which are the state-of-the-art for generating text, music and speech, to the problem of acoustic novelty detection. By integrating uncertainty into the hidden states, this type of network is able to learn the distribution of complex sequences. Because the learned distribution can be calculated explicitly in terms of probability, we can evaluate how likely an observation is then detect low-probability events as novel. The model is robust, highly unsupervised, end-to-end and requires minimum preprocessing, feature engineer…
Acoustic environment characterization opens doors for sound reproduction innovations, smart EQing, speech enhancement, hearing aids, and forensics. Reverberation time, clarity, and direct-to-reverberant ratio are acoustic parameters that have been defined to describe reverberant environments. They are closely related to speech intelligibility and sound quality. As explained in the ISO3382 standard, they can be derived from a room measurement called the Room Impulse Response (RIR). However, measuring RIRs requires specific equipment and intrusive sound to be played. The recent audio combined wi…
RV College of Engineering（RV工程学院）；Wipro Limited（威普罗有限公司）
This paper elucidates a model for acoustic single and multi-tone classification in resource constrained edge devices. The proposed model is of State-of-the-art Fast Accurate Stable Tiny Gated Recurrent Neural Network. This model has resulted in improved performance metrics and lower size compared to previous hypothesized methods by using lesser parameters with higher efficiency and employment of a noise reduction algorithm. The model is implemented as an acoustic AI module, focused for the application of sound identification, localization, and deployment on AI systems like that of an autonomou…
In this paper we present an approach to polyphonic sound event detection in real life recordings based on bi-directional long short term memory (BLSTM) recurrent neural networks (RNNs). A single multilabel BLSTM RNN is trained to map acoustic features of a mixture signal consisting of sounds from multiple classes, to binary activity indicators of each event class. Our method is tested on a large database of real-life recordings, with 61 classes (e.g. music, car, speech) from 10 different everyday contexts. The proposed method outperforms previous approaches by a large margin, and the results a…
In acoustic signal processing, the target signals usually carry semantic information, which is encoded in a hierarchal structure of short and long-term contexts. However, the background noise distorts these structures in a nonuniform way. The existing deep acoustic signal enhancement (ASE) architectures ignore this kind of local and global effect. To address this problem, we propose to integrate a novel temporal attentive-pooling (TAP) mechanism into a conventional convolutional recurrent neural network, termed as TAP-CRNN. The proposed approach considers both global and local attention for AS…
The forensic investigation of a terrorist attack poses a significant challenge to the investigative authorities, as often several thousand hours of video footage must be viewed. Large scale Video Analytic Platforms (VAP) assist law enforcement agencies (LEA) in identifying suspects and securing evidence. Current platforms focus primarily on the integration of different computer vision methods and thus are restricted to a single modality. We present a video analytic platform that integrates visual and audio analytic modules and fuses information from surveillance cameras and video uploads from …
The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of such models (in terms of low distortion in the generated speech), their recursive structure tends to make them slow to train and to sample from. In this work, we try to overcome the limitations of recursive structure by using a module based on the transformer decoder network, designed without recurrent connections but emulating them with attention and positi…
Acoustic echo cancellation (AEC) plays an important role in the full-duplex speech communication as well as the front-end speech enhancement for recognition in the conditions when the loudspeaker plays back. In this paper, we present an all-deep-learning framework that implicitly estimates the second order statistics of echo/noise and target speech, and jointly solves echo and noise suppression through an attention based recurrent neural network. The proposed model outperforms the state-of-the-art joint echo cancellation and speech enhancement method F-T-LSTM in terms of objective speech quali…
Kwai（快手）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
The use of future contextual information is typically shown to be helpful for acoustic modeling. However, for the recurrent neural network (RNN), it's not so easy to model the future temporal context effectively, meanwhile keep lower model latency. In this paper, we attempt to design a RNN acoustic model that being capable of utilizing the future context effectively and directly, with the model latency and computation cost as low as possible. The proposed model is based on the minimal gated recurrent unit (mGRU) with an input projection layer inserted in it. Two context modules, temporal encod…
Acoustic Echo Cancellation (AEC) plays a key role in voice interaction. Due to the explicit mathematical principle and intelligent nature to accommodate conditions, adaptive filters with different types of implementations are always used for AEC, giving considerable performance. However, there would be some kinds of residual echo in the results, including linear residue introduced by mismatching between estimation and the reality and non-linear residue mostly caused by non-linear components on the audio devices. The linear residue can be reduced with elaborate structure and methods, leaving th…
This paper investigates the joint localization, detection, and tracking of sound events using a convolutional recurrent neural network (CRNN). We use a CRNN previously proposed for the localization and detection of stationary sources, and show that the recurrent layers enable the spatial tracking of moving sources when trained with dynamic scenes. The tracking performance of the CRNN is compared with a stand-alone tracking method that combines a multi-source (DOA) estimator and a particle filter. Their respective performance is evaluated in various acoustic conditions such as anechoic and reve…
Acoustic characterization of speech rhythm: going beyond metrics with recurrent neural networks
Purdue University（普渡大学）；Ghent University（根特大学）；Integrative Neuroscience and Cognition Center, CNRS & Université Paris Cité（整合神经科学与认知中心，法国国家科学研究中心与巴黎西岱大学）；University of Padua（帕多瓦大学）
Leipzig University of Applied Sciences（莱比锡应用科学大学）；University of Victoria（维多利亚大学）；Max Planck Institute for Evolutionary Anthropology（马克斯·普朗克进化人类学研究所）；German Centre for Integrative Biodiversity Research (iDiv) Halle-Jena-Leipzig（德国综合生物多样性研究中心（iDiv）哈雷-耶拿-莱比锡）
Automatic detection systems are important in passive acoustic monitoring (PAM) systems, as these record large amounts of audio data which are infeasible for humans to evaluate manually. In this paper we evaluated methods for compensating class imbalance for deep-learning based automatic detection of acoustic chimpanzee calls. The prevalence of chimpanzee calls in natural habitats is very rare, i.e. databases feature a heavy imbalance between background and target calls. Such imbalances can have negative effects on classifier performances. We employed a state-of-the-art detection approach based…
The use of future contextual information is typically shown to be helpful for acoustic modeling. Recently, we proposed a RNN model called minimal gated recurrent unit with input projection (mGRUIP), in which a context module namely temporal convolution, is specifically designed to model the future context. This model, mGRUIP with context module (mGRUIP-Ctx), has been shown to be able of utilizing the future context effectively, meanwhile with quite low model latency and computation cost. In this paper, we continue to improve mGRUIP-Ctx with two revisions: applying BN methods and enlarging mode…
Vanishing long-term gradients are a major issue in training standard recurrent neural networks (RNNs), which can be alleviated by long short-term memory (LSTM) models with memory cells. However, the extra parameters associated with the memory cells mean an LSTM layer has four times as many parameters as an RNN with the same hidden vector size. This paper addresses the vanishing gradient problem using a high order RNN (HORNN) which has additional connections from multiple previous time steps. Speech recognition experiments using British English multi-genre broadcast (MGB3) data showed that the …
In this paper we demonstrate predicting electroencephalograpgy (EEG) features from acoustic features using recurrent neural network (RNN) based regression model and generative adversarial network (GAN). We predict various types of EEG features from acoustic features. We compare our results with the previously studied problem on speech synthesis using EEG and our results demonstrate that EEG features can be generated from acoustic features with lower root mean square error (RMSE), normalized RMSE values compared to generating acoustic features from EEG features (ie: speech synthesis using EEG) …
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 …
In this article, we propose a novel technique for classification of the Murmurs in heart sound. We introduce a novel deep neural network architecture using parallel combination of the Recurrent Neural Network (RNN) based Bidirectional Long Short-Term Memory (BiLSTM) & Convolutional Neural Network (CNN) to learn visual and time-dependent characteristics of Murmur in PCG waveform. Set of acoustic features are presented to our proposed deep neural network to discriminate between Normal and Murmur class. The proposed method was evaluated on a large dataset using 5-fold cross-validation, resulting …
Chair of Complex & Intelligent Systems（复杂与智能系统教席）；Chair of Embedded Intelligence for Health Care & Wellbeing（健康护理与福祉嵌入式智能教席）；GLAM – Group on Language, Audio & Music（语言、音频与音乐研究组）；Universität Passau（帕绍大学）；Augsburg University（奥格斯堡大学）；Imperial College London（伦敦帝国理工学院）
auDeep is a Python toolkit for deep unsupervised representation learning from acoustic data. It is based on a recurrent sequence to sequence autoencoder approach which can learn representations of time series data by taking into account their temporal dynamics. We provide an extensive command line interface in addition to a Python API for users and developers, both of which are comprehensively documented and publicly available at https://github.com/auDeep/auDeep. Experimental results indicate that auDeep features are competitive with state-of-the art audio classification.
University of Science and Technology of China（中国科学技术大学）
This paper presents a method of using autoregressive neural networks for the acoustic modeling of singing voice synthesis (SVS). Singing voice differs from speech and it contains more local dynamic movements of acoustic features, e.g., vibratos. Therefore, our method adopts deep autoregressive (DAR) models to predict the F0 and spectral features of singing voice in order to better describe the dependencies among the acoustic features of consecutive frames. For F0 modeling, discretized F0 values are used and the influences of the history length in DAR are analyzed by experiments. An F0 post-pro…
UT Austin（德克萨斯大学奥斯汀分校）；FAIR, Meta AI（元人工智能基础人工智能研究院）；Reality Labs at Meta（元现实实验室）；Georgia Tech（佐治亚理工学院）
We introduce SoundSpaces 2.0, a platform for on-the-fly geometry-based audio rendering for 3D environments. Given a 3D mesh of a real-world environment, SoundSpaces can generate highly realistic acoustics for arbitrary sounds captured from arbitrary microphone locations. Together with existing 3D visual assets, it supports an array of audio-visual research tasks, such as audio-visual navigation, mapping, source localization and separation, and acoustic matching. Compared to existing resources, SoundSpaces 2.0 has the advantages of allowing continuous spatial sampling, generalization to novel e…
End-to-end speech recognition generally uses hand-engineered acoustic features as input and excludes the feature extraction module from its joint optimization. To extract learnable and adaptive features and mitigate information loss, we propose a new encoder that adopts globally attentive locally recurrent (GALR) networks and directly takes raw waveform as input. We observe improved ASR performance and robustness by applying GALR on different window lengths to aggregate fine-grain temporal information into multi-scale acoustic features. Experiments are conducted on a benchmark dataset AISHELL-…
Speech audio quality is subject to degradation caused by an acoustic environment and isotropic ambient and point noises. The environment can lead to decreased speech intelligibility and loss of focus and attention by the listener. Basic acoustic parameters that characterize the environment well are (i) signal-to-noise ratio (SNR), (ii) speech transmission index, (iii) reverberation time, (iv) clarity, and (v) direct-to-reverberant ratio. Except for the SNR, these parameters are usually derived from the Room Impulse Response (RIR) measurements; however, such measurements are often not available…
Turing Robot co.ltd（图灵机器人有限公司）；Chinese University of Hongkong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data (SRIBD)（深圳大数据研究院）
Neural networks with Auto-regressive structures, such as Recurrent Neural Networks (RNNs), have become the most appealing structures for acoustic modeling of parametric text to speech synthesis (TTS) in ecent studies. Despite the prominent capacity to capture long-term dependency, these models consist of massive sequential computations that cannot be fully parallel. In this paper, we propose a U-shaped Fully-parallel Acoustic Neural Structure (UFANS), which is a deconvolutional alternative of RNNs for Statistical Parametric Speech Synthesis (SPSS). The experiments verify that our proposed mode…
This article presents new numerical simulation tools, respectively developed in Matlab and Blender softwares. Available in open-source under the GPL 3.0 license, it uses a ray-tracing/image-sources hybrid method to calculate the room acoustics for large meshes. Performances are optimized to solve problems of significant size (typically more than 100,000 surface elements and about a million of rays). For this purpose, a Divide and Conquer approach with a recursive binary tree structure has been implemented to reduce the quadratic complexity of the ray/element interactions to near-linear. Thus, …
Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔国立理工学院）；GIPSA-lab（格勒诺布尔图像语音信号自动化实验室）；Univ. Savoie Mont Blanc（萨瓦勃朗峰大学）；LPNC（认知神经科学实验室）
We propose a computational model of speech production combining a pre-trained neural articulatory synthesizer able to reproduce complex speech stimuli from a limited set of interpretable articulatory parameters, a DNN-based internal forward model predicting the sensory consequences of articulatory commands, and an internal inverse model based on a recurrent neural network recovering articulatory commands from the acoustic speech input. Both forward and inverse models are jointly trained in a self-supervised way from raw acoustic-only speech data from different speakers. The imitation simulatio…
Multilingual training has been shown to improve acoustic modeling performance by sharing and transferring knowledge in modeling different languages. Knowledge sharing is usually achieved by using common lower-level layers for different languages in a deep neural network. Recently, the domain adversarial network was proposed to reduce domain mismatch of training data and learn domain-invariant features. It is thus worth exploring whether adversarial training can further promote knowledge sharing in multilingual models. In this work, we apply the domain adversarial network to encourage the share…
Discrete-time modeling of acoustic, mechanical and electrical systems is a prominent topic in the musical signal processing literature. Such models are mostly derived by discretizing a mathematical model, given in terms of ordinary or partial differential equations, using established techniques. Recent work has applied the techniques of machine-learning to construct such models automatically from data for the case of systems which have lumped states described by scalar values, such as electrical circuits. In this work, we examine how similar techniques are able to construct models of systems w…
Waseda University（早稻田大学）；NTT Media Intelligence Laboratories（NTT媒体智能实验室）
Phase reconstruction, which estimates phase from a given amplitude spectrogram, is an active research field in acoustical signal processing with many applications including audio synthesis. To take advantage of rich knowledge from data, several studies presented deep neural network (DNN)--based phase reconstruction methods. However, the training of a DNN for phase reconstruction is not an easy task because phase is sensitive to the shift of a waveform. To overcome this problem, we propose a DNN-based two-stage phase reconstruction method. In the proposed method, DNNs estimate phase derivatives…
Unitary Evolution Recurrent Neural Networks (uRNNs) have three attractive properties: (a) the unitary property, (b) the complex-valued nature, and (c) their efficient linear operators. The literature so far does not address -- how critical is the unitary property of the model? Furthermore, uRNNs have not been evaluated on large tasks. To study these shortcomings, we propose the complex evolution Recurrent Neural Networks (ceRNNs), which is similar to uRNNs but drops the unitary property selectively. On a simple multivariate linear regression task, we illustrate that dropping the constraints im…
This study addresses robust automatic speech recognition (ASR) by introducing a Conformer-based acoustic model. The proposed model builds on the wide residual bi-directional long short-term memory network (WRBN) with utterance-wise dropout and iterative speaker adaptation, but employs a Conformer encoder instead of the recurrent network. The Conformer encoder uses a convolution-augmented attention mechanism for acoustic modeling. The proposed system is evaluated on the monaural ASR task of the CHiME-4 corpus. Coupled with utterance-wise normalization and speaker adaptation, our model achieves …
Tencent AI Lab（腾讯人工智能实验室）；Microsoft AI and Research（微软人工智能与研究事业部）
In this paper, we summarize recent progresses made in deep learning based acoustic models and the motivation and insights behind the surveyed techniques. We first discuss acoustic models that can effectively exploit variable-length contextual information, such as recurrent neural networks (RNNs), convolutional neural networks (CNNs), and their various combination with other models. We then describe acoustic models that are optimized end-to-end with emphasis on feature representations learned jointly with rest of the system, the connectionist temporal classification (CTC) criterion, and the att…
This paper presents ByteSing, a Chinese singing voice synthesis (SVS) system based on duration allocated Tacotron-like acoustic models and WaveRNN neural vocoders. Different from the conventional SVS models, the proposed ByteSing employs Tacotron-like encoder-decoder structures as the acoustic models, in which the CBHG models and recurrent neural networks (RNNs) are explored as encoders and decoders respectively. Meanwhile an auxiliary phoneme duration prediction model is utilized to expand the input sequence, which can enhance the model controllable capacity, model stability and tempo predict…
National Institute of Informatics（国立信息学研究所）；Aalto University（阿尔托大学）
Recent advances in speech synthesis suggest that limitations such as the lossy nature of the amplitude spectrum with minimum phase approximation and the over-smoothing effect in acoustic modeling can be overcome by using advanced machine learning approaches. In this paper, we build a framework in which we can fairly compare new vocoding and acoustic modeling techniques with conventional approaches by means of a large scale crowdsourced evaluation. Results on acoustic models showed that generative adversarial networks and an autoregressive (AR) model performed better than a normal recurrent net…
Technische Universität Braunschweig（布伦瑞克工业大学）；GN Audio A/S（GN音频公司）
Although today's speech communication systems support various bandwidths from narrowband to super-wideband and beyond, state-of-the art DNN methods for acoustic echo cancellation (AEC) are lacking modularity and bandwidth scalability. Our proposed DNN model builds upon a fully convolutional recurrent network (FCRN) and introduces scalability over various bandwidths up to a fullband (FB) system (48 kHz sampling rate). This modular approach allows joint wideband (WB) pre-training of mask-based AEC and postfilter stages with dedicated losses, followed by a separate training of them on FB data. A …
Building on the deep learning based acoustic echo cancellation (AEC) in the single-loudspeaker (single-channel) and single-microphone setup, this paper investigates multi-channel AEC (MCAEC) and multi-microphone AEC (MMAEC). We train a deep neural network (DNN) to predict the near-end speech from microphone signals with far-end signals used as additional information. We find that the deep learning approach avoids the non-uniqueness problem in traditional MCAEC algorithms. For the AEC setup with multiple microphones, rather than employing AEC for each microphone, a single DNN is trained to achi…
The goal of acoustic (or sound) events detection (AED or SED) is to predict the temporal position of target events in given audio segments. This task plays a significant role in safety monitoring, acoustic early warning and other scenarios. However, the deficiency of data and diversity of acoustic event sources make the AED task a tough issue, especially for prevalent data-driven methods. In this paper, we start by analyzing acoustic events according to their time-frequency domain properties, showing that different acoustic events have different time-frequency scale characteristics. Inspired b…
Training convolutional recurrent neural networks on first-order Ambisonics signals is a well-known approach when estimating the direction of arrival for speech/sound signals. In this work, we investigate whether increasing the order of Ambisonics up to the fourth order further improves the estimation performance of convolutional recurrent neural networks. While our results on data based on simulated spatial room impulse responses show that the use of higher Ambisonics orders does have the potential to provide better localization results, no further improvement was shown on data based on real s…
Recently, recurrent neural networks have become state-of-the-art in acoustic modeling for automatic speech recognition. The long short-term memory (LSTM) units are the most popular ones. However, alternative units like gated recurrent unit (GRU) and its modifications outperformed LSTM in some publications. In this paper, we compared five neural network (NN) architectures with various adaptation and feature normalization techniques. We have evaluated feature-space maximum likelihood linear regression, five variants of i-vector adaptation and two variants of cepstral mean normalization. The most…
Université Paris-Est（巴黎东部大学）；INSAT Institut National des Sciences Appliquées et de Technologie（突尼斯应用科学与技术学院）；Yobitrust（优比特信托公司）；University of Sciences and Arts in Lebanon（黎巴嫩科学与艺术大学）；Université de Bourgogne Franche Comté（勃艮第-弗朗什-孔泰大学）
Clinical depression or Major Depressive Disorder (MDD) is a common and serious medical illness. In this paper, a deep recurrent neural network-based framework is presented to detect depression and to predict its severity level from speech. Low-level and high-level audio features are extracted from audio recordings to predict the 24 scores of the Patient Health Questionnaire and the binary class of depression diagnosis. To overcome the problem of the small size of Speech Depression Recognition (SDR) datasets, expanding training labels and transferred features are considered. The proposed approa…
The recurrent neural network transducer (RNN-T) has recently become the mainstream end-to-end approach for streaming automatic speech recognition (ASR). To estimate the output distributions over subword units, RNN-T uses a fully connected layer as the joint network to fuse the acoustic representations extracted using the acoustic encoder with the text representations obtained using the prediction network based on the previous subword units. In this paper, we propose to use gating, bilinear pooling, and a combination of them in the joint network to produce more expressive representations to fee…
We investigate training end-to-end speech recognition models with the recurrent neural network transducer (RNN-T): a streaming, all-neural, sequence-to-sequence architecture which jointly learns acoustic and language model components from transcribed acoustic data. We explore various model architectures and demonstrate how the model can be improved further if additional text or pronunciation data are available. The model consists of an `encoder', which is initialized from a connectionist temporal classification-based (CTC) acoustic model, and a `decoder' which is partially initialized from a r…
IBM Research AI（IBM研究院人工智能部）；IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）；IBM Research Tokyo（IBM东京研究院）
We introduce two techniques, length perturbation and n-best based label smoothing, to improve generalization of deep neural network (DNN) acoustic models for automatic speech recognition (ASR). Length perturbation is a data augmentation algorithm that randomly drops and inserts frames of an utterance to alter the length of the speech feature sequence. N-best based label smoothing randomly injects noise to ground truth labels during training in order to avoid overfitting, where the noisy labels are generated from n-best hypotheses. We evaluate these two techniques extensively on the 300-hour Sw…
