Training acoustic models with sequentially incoming data -- while both leveraging new data and avoiding the forgetting effect-- is an essential obstacle to achieving human intelligence level in speech recognition. An obvious approach to leverage data from a new domain (e.g., new accented speech) is to first generate a comprehensive dataset of all domains, by combining all available data, and then use this dataset to retrain the acoustic models. However, as the amount of training data grows, storing and retraining on such a large-scale dataset becomes practically impossible. To deal with this problem, in this study, we study several domain expansion techniques which exploit only the data of the new domain to build a stronger model for all domains. These techniques are aimed at learning the new domain with a minimal forgetting effect (i.e., they maintain original model performance). These techniques modify the adaptation procedure by imposing new constraints including (1) weight constraint adaptation (WCA): keeping the model parameters close to the original model parameters; (2) elastic weight consolidation (EWC): slowing down training for parameters that are important for previously established domains; (3) soft KL-divergence (SKLD): restricting the KL-divergence between the original and the adapted model output distributions; and (4) hybrid SKLD-EWC: incorporating both SKLD and EWC constraints. We evaluate these techniques in an accent adaptation task in which we adapt a deep neural network (DNN) acoustic model trained with native English to three different English accents: Australian, Hispanic, and Indian. The experimental results show that SKLD significantly outperforms EWC, and EWC works better than WCA. The hybrid SKLD-EWC technique results in the best overall performance.
Conversational context information, higher-level knowledge that spans across sentences, can help to recognize a long conversation. However, existing speech recognition models are typically built at a sentence level, and thus it may not capture important conversational context information. The recent progress in end-to-end speech recognition enables integrating context with other available information (e.g., acoustic, linguistic resources) and directly recognizing words from speech. In this work, we present a direct acoustic-to-word, end-to-end speech recognition model capable of utilizing the …
KAIST（韩国科学技术院）；Mokwon University（木原大学）；KAIST Institute for Artificial Intelligence（韩国科学技术院人工智能研究所）
Many speech enhancement methods try to learn the relationship between noisy and clean speech, obtained using an acoustic room simulator. We point out several limitations of enhancement methods relying on clean speech targets; the goal of this work is proposing an alternative learning algorithm, called acoustic and adversarial supervision (AAS). AAS makes the enhanced output both maximizing the likelihood of transcription on the pre-trained acoustic model and having general characteristics of clean speech, which improve generalization on unseen noisy speeches. We employ the connectionist tempor…
Carl von Ossietzky Universität Oldenburg（卡尔·冯·奥西茨基奥尔登堡大学）
This paper presents a speech intelligibility model based on automatic speech recognition (ASR), combining phoneme probabilities from deep neural networks (DNN) and a performance measure that estimates the word error rate from these probabilities. This model does not require the clean speech reference nor the word labels during testing as the ASR decoding step, which finds the most likely sequence of words given phoneme posterior probabilities, is omitted. The model is evaluated via the root-mean-squared error between the predicted and observed speech reception thresholds from eight normal-hear…
Sun Yat-sen University（中山大学）；Dark Matter AI Research（暗物质人工智能研究院）；Sea AI Lab（冬海人工智能实验室）
Unifying acoustic and linguistic representation learning has become increasingly crucial to transfer the knowledge learned on the abundance of high-resource language data for low-resource speech recognition. Existing approaches simply cascade pre-trained acoustic and language models to learn the transfer from speech to text. However, how to solve the representation discrepancy of speech and text is unexplored, which hinders the utilization of acoustic and linguistic information. Moreover, previous works simply replace the embedding layer of the pre-trained language model with the acoustic feat…
University of Waterloo（滑铁卢大学）；Baidu Research USA（百度美国研究院）；Baidu Research（百度研究院）；Oregon State University（俄勒冈州立大学）
Recently, speech representation learning has improved many speech-related tasks such as speech recognition, speech classification, and speech-to-text translation. However, all the above tasks are in the direction of speech understanding, but for the inverse direction, speech synthesis, the potential of representation learning is yet to be realized, due to the challenging nature of generating high-quality speech. To address this problem, we propose our framework, Alignment-Aware Acoustic-Text Pretraining (A$^3$T), which reconstructs masked acoustic signals with text input and acoustic-text alig…
Université de Lorraine（洛林大学）；Inria（法国国家信息与自动化研究所）；Loria（洛林信息学研究实验室）
The word error rate (WER) of an automatic speech recognition (ASR) system increases when a mismatch occurs between the training and the testing conditions due to the noise, etc. In this case, the acoustic information can be less reliable. This work aims to improve ASR by modeling long-term semantic relations to compensate for distorted acoustic features. We propose to perform this through rescoring of the ASR N-best hypotheses list. To achieve this, we train a deep neural network (DNN). Our DNN rescoring model is aimed at selecting hypotheses that have better semantic consistency and therefore…
Monaural speech enhancement has made dramatic advances since the introduction of deep learning a few years ago. Although enhanced speech has been demonstrated to have better intelligibility and quality for human listeners, feeding it directly to automatic speech recognition (ASR) systems trained with noisy speech has not produced expected improvements in ASR performance. The lack of an enhancement benefit on recognition, or the gap between monaural speech enhancement and recognition, is often attributed to speech distortions introduced in the enhancement process. In this study, we analyze the …
In automatic speech recognition, often little training data is available for specific challenging tasks, but training of state-of-the-art automatic speech recognition systems requires large amounts of annotated speech. To address this issue, we propose a two-staged approach to acoustic modeling that combines noise and reverberation data augmentation with transfer learning to robustly address challenges such as difficult acoustic recording conditions, spontaneous speech, and speech of elderly people. We evaluate our approach using the example of German oral history interviews, where a relative …
Children speech recognition is challenging mainly due to the inherent high variability in children's physical and articulatory characteristics and expressions. This variability manifests in both acoustic constructs and linguistic usage due to the rapidly changing developmental stage in children's life. Part of the challenge is due to the lack of large amounts of available children speech data for efficient modeling. This work attempts to address the key challenges using transfer learning from adult's models to children's models in a Deep Neural Network (DNN) framework for children's Automatic …
In this paper, a time delay neural network (TDNN) based acoustic model is proposed to implement a fast-converged acoustic modeling for Korean speech recognition. The TDNN has an advantage in fast-convergence where the amount of training data is limited, due to subsampling which excludes duplicated weights. The TDNN showed an absolute improvement of 2.12% in terms of character error rate compared to feed forward neural network (FFNN) based modelling for Korean speech corpora. The proposed model converged 1.67 times faster than a FFNN-based model did.
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；IBM Research AI（IBM研究院人工智能部门）；IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）
In automatic speech recognition (ASR), wideband (WB) and narrowband (NB) speech signals with different sampling rates typically use separate acoustic models. Therefore mixed-bandwidth (MB) acoustic modeling has important practical values for ASR system deployment. In this paper, we extensively investigate large-scale MB deep neural network acoustic modeling for ASR using 1,150 hours of WB data and 2,300 hours of NB data. We study various MB strategies including downsampling, upsampling and bandwidth extension for MB acoustic modeling and evaluate their performance on 8 diverse WB and NB test s…
University of Maryland（马里兰大学）；SRI International（斯坦福国际研究院）；Apple Inc.（苹果公司）
Unseen data can degrade performance of deep neural net acoustic models. To cope with unseen data, adaptation techniques are deployed. For unlabeled unseen data, one must generate some hypothesis given an existing model, which is used as the label for model adaptation. However, assessing the goodness of the hypothesis can be difficult, and an erroneous hypothesis can lead to poorly trained models. In such cases, a strategy to select data having reliable hypothesis can ensure better model adaptation. This work proposes a data-selection strategy for DNN model adaptation, where DNN output layer ac…
End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to integrate with downstream tasks such as spoken language understanding, because inference (search) is much simplified compared to phoneme, character or any other sort of sub-word units. In this paper, we describe methods to construct contextual acoustic word embeddings directly from a supervised sequence-to-sequence acoustic-to-word speech recognition model …
On-device speech recognition requires training models of different sizes for deploying on devices with various computational budgets. When building such different models, we can benefit from training them jointly to take advantage of the knowledge shared between them. Joint training is also efficient since it reduces the redundancy in the training procedure's data handling operations. We propose a method for collaboratively training acoustic encoders of different sizes for speech recognition. We use a sequence transducer setup where different acoustic encoders share a common predictor and join…
In spoken language understanding (SLU), what the user says is converted to his/her intent. Recent work on end-to-end SLU has shown that accuracy can be improved via pre-training approaches. We revisit ideas presented by Lugosch et al. using speech pre-training and three-module modeling; however, to ease construction of the end-to-end SLU model, we use as our phoneme module an open-source acoustic-phonetic model from a DNN-HMM hybrid automatic speech recognition (ASR) system instead of training one from scratch. Hence we fine-tune on speech only for the word module, and we apply multi-target le…
Radboud University（拉德堡德大学）；National University of Singapore（新加坡国立大学）
In this paper, we describe several techniques for improving the acoustic and language model of an automatic speech recognition (ASR) system operating on code-switching (CS) speech. We focus on the recognition of Frisian-Dutch radio broadcasts where one of the mixed languages, namely Frisian, is an under-resourced language. In previous work, we have proposed several automatic transcription strategies for CS speech to increase the amount of available training speech data. In this work, we explore how the acoustic modeling (AM) can benefit from monolingual speech data belonging to the high-resour…
TTI-Chicago（芝加哥丰田技术研究院）；IBM Research AI（IBM研究院人工智能部门）
Direct acoustics-to-word (A2W) systems for end-to-end automatic speech recognition are simpler to train, and more efficient to decode with, than sub-word systems. However, A2W systems can have difficulties at training time when data is limited, and at decoding time when recognizing words outside the training vocabulary. To address these shortcomings, we investigate the use of recently proposed acoustic and acoustically grounded word embedding techniques in A2W systems. The idea is based on treating the final pre-softmax weight matrix of an AWE recognizer as a matrix of word embedding vectors, …
Baidu Research（百度研究院）；Oregon State University（俄勒冈州立大学）
End-to-end Speech-to-text Translation (E2E-ST), which directly translates source language speech to target language text, is widely useful in practice, but traditional cascaded approaches (ASR+MT) often suffer from error propagation in the pipeline. On the other hand, existing end-to-end solutions heavily depend on the source language transcriptions for pre-training or multi-task training with Automatic Speech Recognition (ASR). We instead propose a simple technique to learn a robust speech encoder in a self-supervised fashion only on the speech side, which can utilize speech data without tran…
Estimating time-frequency domain masks for speech enhancement using deep learning approaches has recently become a popular field of research. In this paper, we propose a mask-based speech enhancement framework by using concatenated identical deep neural networks (CI-DNNs). The idea is that a single DNN is trained under multiple input and output signal-to-noise power ratio (SNR) conditions, using targets that provide a moderate SNR gain with respect to the input and therefore achieve a balance between speech component quality and noise suppression. We concatenate this single DNN several times w…
Single-channel speech enhancement with deep neural networks (DNNs) has shown promising performance and is thus intensively being studied. In this paper, instead of applying the mean squared error (MSE) as the loss function during DNN training for speech enhancement, we design a perceptual weighting filter loss motivated by the weighting filter as it is employed in analysis-by-synthesis speech coding, e.g., in code-excited linear prediction (CELP). The experimental results show that the proposed simple loss function improves the speech enhancement performance compared to a reference DNN with MS…
Deep neural network (DNN)-based speech enhancement ordinarily requires clean speech signals as the training target. However, collecting clean signals is very costly because they must be recorded in a studio. This requirement currently restricts the amount of training data for speech enhancement to less than 1/1000 of that of speech recognition which does not need clean signals. Increasing the amount of training data is important for improving the performance, and hence the requirement of clean signals should be relaxed. In this paper, we propose a training strategy that does not require clean …
Yuan Ze University（元智大学）；National Chi Nan University（国立暨南国际大学）
Speech-related applications deliver inferior performance in complex noise environments. Therefore, this study primarily addresses this problem by introducing speech-enhancement (SE) systems based on deep neural networks (DNNs) applied to a distributed microphone architecture, and then investigates the effectiveness of three different DNN-model structures. The first system constructs a DNN model for each microphone to enhance the recorded noisy speech signal, and the second system combines all the noisy recordings into a large feature structure that is then enhanced through a DNN model. As for …
In this work, we propose the use of dropouts as a Bayesian estimator for increasing the generalizability of a deep neural network (DNN) for speech enhancement. By using Monte Carlo (MC) dropout, we show that the DNN performs better enhancement in unseen noise and SNR conditions. The DNN is trained on speech corrupted with Factory2, M109, Babble, Leopard and Volvo noises at SNRs of 0, 5 and 10 dB and tested on speech with white, pink and factory1 noises. Speech samples are obtained from the TIMIT database and noises from NOISEX-92. In another experiment, we train five DNN models separately on s…
An accurate objective speech intelligibility prediction algorithms is of great interest for many applications such as speech enhancement for hearing aids. Most algorithms measures the signal-to-noise ratios or correlations between the acoustic features of clean reference signals and degraded signals. However, these hand-picked acoustic features are usually not explicitly correlated with recognition. Meanwhile, deep neural network (DNN) based automatic speech recogniser (ASR) is approaching human performance in some speech recognition tasks. This work leverages the hidden representations from D…
Deep neural network (DNN)-based speech enhancement usually uses a clean speech as a training target. However, it is hard to collect large amounts of clean speech because the recording is very costly. In other words, the performance of current speech enhancement has been limited by the amount of training data. To relax this limitation, Noisy-target Training (NyTT) that utilizes noisy speech as a training target has been proposed. Although it has been experimentally shown that NyTT can train a DNN without clean speech, a detailed analysis has not been conducted and its behavior has not been unde…
Deep neural networks (DNN) are able to successfully process and classify speech utterances. However, understanding the reason behind a classification by DNN is difficult. One such debugging method used with image classification DNNs is activation maximization, which generates example-images that are classified as one of the classes. In this work, we evaluate applicability of this method to speech utterance classifiers as the means to understanding what DNN "listens to". We trained a classifier using the speech command corpus and then use activation maximization to pull samples from the trained…
Institute for Systems Research, University of Maryland（系统研究所以及马里兰大学）；Google Inc（谷歌公司）
Recent advancements in deep learning have led to drastic improvements in speech segregation models. Despite their success and growing applicability, few efforts have been made to analyze the underlying principles that these networks learn to perform segregation. Here we analyze the role of harmonicity on two state-of-the-art Deep Neural Networks (DNN)-based models- Conv-TasNet and DPT-Net. We evaluate their performance with mixtures of natural speech versus slightly manipulated inharmonic speech, where harmonics are slightly frequency jittered. We find that performance deteriorates significant…
Georgia Institute of Technology（佐治亚理工学院）；IBM Research（IBM研究院）；Universidad San Pablo-CEU, CEU Universities（CEU大学圣巴勃罗校区）
This work focuses on designing low complexity hybrid tensor networks by considering trade-offs between the model complexity and practical performance. Firstly, we exploit a low-rank tensor-train deep neural network (TT-DNN) to build an end-to-end deep learning pipeline, namely LR-TT-DNN. Secondly, a hybrid model combining LR-TT-DNN with a convolutional neural network (CNN), which is denoted as CNN+(LR-TT-DNN), is set up to boost the performance. Instead of randomly assigning large TT-ranks for TT-DNN, we leverage Riemannian gradient descent to determine a TT-DNN associated with small TT-ranks.…
Speaker adaptation aims to estimate a speaker specific acoustic model from a speaker independent one to minimize the mismatch between the training and testing conditions arisen from speaker variabilities. A variety of neural network adaptation methods have been proposed since deep learning models have become the main stream. But there still lacks an experimental comparison between different methods, especially when DNN-based acoustic models have been advanced greatly. In this paper, we aim to close this gap by providing an empirical evaluation of three typical speaker adaptation methods: LIN, …
This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker embedding such as a $d$-vector can be applied to multi-speaker modeling in speech synthesis, it does not correlate with the subjective inter-speaker similarity and is not necessarily appropriate speaker representation for open speakers whose speech utterances are not included in the training data. We propose two training algorithms for DNN-based speaker embedding model using an inter-speaker similarity matrix obtained…
This paper proposes architectures that facilitate the extrapolation of emotional expressions in deep neural network (DNN)-based text-to-speech (TTS). In this study, the meaning of "extrapolate emotional expressions" is to borrow emotional expressions from others, and the collection of emotional speech uttered by target speakers is unnecessary. Although a DNN has potential power to construct DNN-based TTS with emotional expressions and some DNN-based TTS systems have demonstrated satisfactory performances in the expression of the diversity of human speech, it is necessary and troublesome to col…
Waseda University（早稻田大学）；NTT Media Intelligence Laboratories（NTT媒体智能实验室）
We propose an end-to-end speech enhancement method with trainable time-frequency~(T-F) transform based on invertible deep neural network~(DNN). The resent development of speech enhancement is brought by using DNN. The ordinary DNN-based speech enhancement employs T-F transform, typically the short-time Fourier transform~(STFT), and estimates a T-F mask using DNN. On the other hand, some methods have considered end-to-end networks which directly estimate the enhanced signals without T-F transform. While end-to-end methods have shown promising results, they are black boxes and hard to understand…
Employing deep neural networks (DNNs) to directly learn filters for multi-channel speech enhancement has potentially two key advantages over a traditional approach combining a linear spatial filter with an independent tempo-spectral post-filter: 1) non-linear spatial filtering allows to overcome potential restrictions originating from a linear processing model and 2) joint processing of spatial and tempo-spectral information allows to exploit interdependencies between different sources of information. A variety of DNN-based non-linear filters have been proposed recently, for which good enhance…
National Institute of Technology, Tokuyama College（国立技术院德山高专）；NTT Media Intelligence Laboratories（NTT媒体智能实验室）；Waseda University（早稻田大学）
Improving subjective sound quality of enhanced signals is one of the most important missions in speech enhancement. For evaluating the subjective quality, several methods related to perceptually-motivated objective sound quality assessment (OSQA) have been proposed such as PESQ (perceptual evaluation of speech quality). However, direct use of such measures for training deep neural network (DNN) is not allowed in most cases because popular OSQAs are non-differentiable with respect to DNN parameters. Therefore, the previous study has proposed to approximate the score of OSQAs by an auxiliary DNN…
Carnegie Mellon University（卡内基梅隆大学）；Sony Corporation（索尼公司）；Sony Europe B.V.（索尼欧洲有限公司）
Recently, deep neural networks (DNNs) have been successfully used for speech enhancement, and DNN-based speech enhancement is becoming an attractive research area. While time-frequency masking based on the short-time Fourier transform (STFT) has been widely used for DNN-based speech enhancement over the last years, time domain methods such as the time-domain audio separation network (TasNet) have also been proposed. The most suitable method depends on the scale of the dataset and the type of task. In this paper, we explore the best speech enhancement algorithm on two different datasets. We pro…
Multi-frame approaches for single-microphone speech enhancement, e.g., the multi-frame minimum-power-distortionless-response (MFMPDR) filter, are able to exploit speech correlations across neighboring time frames. In contrast to single-frame approaches such as the Wiener gain, it has been shown that multi-frame approaches achieve a substantial noise reduction with hardly any speech distortion, provided that an accurate estimate of the correlation matrices and especially the speech interframe correlation (IFC) vector is available. Typical estimation procedures of the IFC vector require an estim…
A deep neural network (DNN)-based speech enhancement (SE) aiming to maximize the performance of an automatic speech recognition (ASR) system is proposed in this paper. In order to optimize the DNN-based SE model in terms of the character error rate (CER), which is one of the metric to evaluate the ASR system and generally non-differentiable, our method uses two DNNs: one for speech processing and one for mimicking the output CERs derived through an acoustic model (AM). Then both of DNNs are alternately optimized in the training phase. Even if the AM is a black-box, e.g., like one provided by a…
