We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients). The augmentation policy consists of warping the features, masking blocks of frequency channels, and masking blocks of time steps. We apply SpecAugment on Listen, Attend and Spell networks for end-to-end speech recognition tasks. We achieve state-of-the-art performance on the LibriSpeech 960h and Swichboard 300h tasks, outperforming all prior work. On LibriSpeech, we achieve 6.8% WER on test-other without the use of a language model, and 5.8% WER with shallow fusion with a language model. This compares to the previous state-of-the-art hybrid system of 7.5% WER. For Switchboard, we achieve 7.2%/14.6% on the Switchboard/CallHome portion of the Hub5'00 test set without the use of a language model, and 6.8%/14.1% with shallow fusion, which compares to the previous state-of-the-art hybrid system at 8.3%/17.3% WER.

SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

Data augmentation is a common strategy adopted to increase the quantity of training data, avoid overfitting and improve robustness of the models. In this paper, we investigate audio-level speech augmentation methods which directly process the raw signal. The method we particularly recommend is to change the speed of the audio signal, producing 3 versions of the original signal with speed factors of 0.9, 1.0 and 1.1. The proposed technique has a low implementation cost, making it easy to adopt. We present results on 4 different LVCSR tasks with training data ranging from 100 hours to 1000 hours, to examine the effectiveness of audio augmentation in a variety of data scenarios. An average relative improvement of 4.3% was observed across the 4 tasks.

/pdf/audio-augmentation-for-speech-recognition-4yne0qzz10.pdf

Audio augmentation for speech recognition.

Over the past decades, a tremendous amount of research has been done on the use of machine learning for speech processing applications, especially speech recognition. However, in the past few years, research has focused on utilizing deep learning for speech-related applications. This new area of machine learning has yielded far better results when compared to others in a variety of applications including speech, and thus became a very attractive area of research. This paper provides a thorough examination of the different studies that have been conducted since 2006, when deep learning first arose as a new area of machine learning, for speech applications. A thorough statistical analysis is provided in this review which was conducted by extracting specific information from 174 papers published between the years 2006 and 2018. The results provided in this paper shed light on the trends of research in this area as well as bring focus to new research topics.

/pdf/speech-recognition-using-deep-neural-networks-a-systematic-kp43ilkz5h.pdf

Speech Recognition Using Deep Neural Networks: A Systematic Review

The Common Voice corpus is a massively-multilingual collection of transcribed speech intended for speech technology research and development. Common Voice is designed for Automatic Speech Recognition purposes but can be useful in other domains (e.g. language identification). To achieve scale and sustainability, the Common Voice project employs crowdsourcing for both data collection and data validation. The most recent release includes 29 languages, and as of November 2019 there are a total of 38 languages collecting data. Over 50,000 individuals have participated so far, resulting in 2,500 hours of collected audio. To our knowledge this is the largest audio corpus in the public domain for speech recognition, both in terms of number of hours and number of languages. As an example use case for Common Voice, we present speech recognition experiments using Mozilla’s DeepSpeech Speech-to-Text toolkit. By applying transfer learning from a source English model, we find an average Character Error Rate improvement of 5.99 ± 5.48 for twelve target languages (German, French, Italian, Turkish, Catalan, Slovenian, Welsh, Irish, Breton, Tatar, Chuvash, and Kabyle). For most of these languages, these are the first ever published results on end-to-end Automatic Speech Recognition.

Common Voice: A Massively-Multilingual Speech Corpus

This paper presents a new feature extraction algorithm called power normalized Cepstral coefficients (PNCC) that is motivated by auditory processing. Major new features of PNCC processing include the use of a power-law nonlinearity that replaces the traditional log nonlinearity used in MFCC coefficients, a noise-suppression algorithm based on asymmetric filtering that suppresses background excitation, and a module that accomplishes temporal masking. We also propose the use of medium-time power analysis in which environmental parameters are estimated over a longer duration than is commonly used for speech, as well as frequency smoothing. Experimental results demonstrate that PNCC processing provides substantial improvements in recognition accuracy compared to MFCC and PLP processing for speech in the presence of various types of additive noise and in reverberant environments, with only slightly greater computational cost than conventional MFCC processing, and without degrading the recognition accuracy that is observed while training and testing using clean speech. PNCC processing also provides better recognition accuracy in noisy environments than techniques such as vector Taylor series (VTS) and the ETSI advanced front end (AFE) while requiring much less computation. We describe an implementation of PNCC using "online processing" that does not require future knowledge of the input.

/pdf/power-normalized-cepstral-coefficients-pncc-for-robust-4hlic3rj7n.pdf

Power-normalized cepstral coefficients (PNCC) for robust speech recognition

In this paper, we investigate alternative ways of processing MFCC-based features to use as the input to Deep Neural Networks (DNNs). Our baseline is a conventional feature pipeline that involves splicing the 13-dimensional front-end MFCCs across 9 frames, followed by applying LDA to reduce the dimension to 40 and then further decorrelation using MLLT. Confirming the results of other groups, we show that speaker adaptation applied on the top of these features using feature-space MLLR is helpful. The fact that the number of parameters of a DNN is not strongly sensitive to the input feature dimension (unlike GMM-based systems) motivated us to investigate ways to increase the dimension of the features. In this paper, we investigate several approaches to derive higher-dimensional features and verify their performance with DNN. Our best result is obtained from splicing our baseline 40-dimensional speaker adapted features again across 9 frames, followed by reducing the dimension to 200 or 300 using another LDA. Our final result is about 3% absolute better than our best GMM system, which is a discriminatively trained model.

/pdf/improved-feature-processing-for-deep-neural-networks-5634bdgc21.pdf

Improved feature processing for Deep Neural Networks

Recently there has been increased interest in Automatic Speech Recognition (ASR) and Key Word Spotting (KWS) systems for low resource languages. One of the driving forces for this research direction is the IARPA Babel project. This paper describes some of the research funded by this project at Cambridge University, as part of the Lorelei team co-ordinated by IBM. A range of topics are discussed including: deep neural network based acoustic models; data augmentation; and zero acoustic model resource systems. Performance for all approaches is evaluated using the Limited (approximately 10 hours) and/or Full (approximately 80 hours) language packs distributed by IARPA. Both KWS and ASR performance figures are given. Though absolute performance varies from language to language, and keyword list, the approaches described show consistent trends over the languages investigated to date. Using comparable systems over the five Option Period 1 languages indicates a strong correlation between ASR performance and KWS performance.

/pdf/speech-recognition-and-keyword-spotting-for-low-resource-334xmaxzpo.pdf

Speech recognition and keyword spotting for low-resource languages : Babel project research at CUED

Recently there has been interest in the approaches for training speech recognition systems for languages with limited resources. Under the IARPA Babel program such resources have been provided for a range of languages to support this research area. This paper examines a particular form of approach, data augmentation, that can be applied to these situations. Data augmentation schemes aim to increase the quantity of data available to train the system, for example semi-supervised training, multilingual processing, acoustic data perturbation and speech synthesis. To date the majority of work has considered individual data augmentation schemes, with few consistent performance contrasts or examination of whether the schemes are complementary. In this work two data augmentation schemes, semisupervised training and vocal tract length perturbation, are examined and combined on the Babel limited language pack configuration. Here only about 10 hours of transcribed acoustic data are available. Two languages are examined, Assamese and Zulu, which were found to be the most challenging of the Babel languages released for the 2014 Evaluation. For both languages consistent speech recognition performance gains can be obtained using these augmentation schemes. Furthermore the impact of these performance gains on a down-stream keyword spotting task are also described.

/pdf/data-augmentation-for-low-resource-languages-1z4jg8vx1q.pdf

Data augmentation for low resource languages

The development of high-performance speech processing systems for low-resource languages is a challenging area. One approach to address the lack of resources is to make use of data from multiple languages. A popular direction in recent years is to use bottleneck features, or hybrid systems, trained on multilingual data for speech-to-text (STT) systems. This paper presents an investigation into the application of these multilingual approaches to spoken term detection. Experiments were run using the IARPA Babel limited language pack corpora (~10 hours/language) with 4 languages for initial multilingual system development and an additional held-out target language. STT gains achieved through using multilingual bottleneck features in a Tandem configuration are shown to also apply to keyword search (KWS). Further improvements in both STT and KWS were observed by incorporating language questions into the Tandem GMM-HMM decision trees for the training set languages. Adapted hybrid systems performed slightly worse on average than the adapted Tandem systems. A language independent acoustic model test on the target language showed that retraining or adapting of the acoustic models to the target language is currently minimally needed to achieve reasonable performance.

/pdf/investigation-of-multilingual-deep-neural-networks-for-1n3vhi83zh.pdf

Investigation of multilingual deep neural networks for spoken term detection

Developing high-performance speech processing systems for low-resource languages is very challenging. One approach to address the lack of resources is to make use of data from multiple languages. A popular direction in recent years is to train a multi-language bottleneck DNN. Language dependent and/or multi-language (all training languages) Tandem acoustic models (AM) are then trained. This work considers a particular scenario where the target language is unseen in multi-language training and has limited language model training data, a limited lexicon, and acoustic training data without transcriptions. A zero acoustic resources case is first described where a multilanguage AM is directly applied, as a language independent AM (LIAM), to an unseen language. Secondly, in an unsupervised approach a LIAM is used to obtain hypotheses for the target language acoustic data transcriptions which are then used in training a language dependent AM. 3 languages from the IARPA Babel project are used for assessment: Vietnamese, Haitian Creole and Bengali. Performance of the zero acoustic resources system is found to be poor, with keyword spotting at best 60% of language dependent performance. Unsupervised language dependent training yields performance gains. For one language (Haitian Creole) the Babel target is achieved on the in-vocabulary data.

/pdf/language-independent-and-unsupervised-acoustic-models-for-4iaqqyrtvc.pdf

Shakti P. Rath

Papers

Improved feature processing for Deep Neural Networks

Speech recognition and keyword spotting for low-resource languages : Babel project research at CUED

Data augmentation for low resource languages

Investigation of multilingual deep neural networks for spoken term detection

Language independent and unsupervised acoustic models for speech recognition and keyword spotting