The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper constructs speech features based on a generative model using a deep latent Gaussian model (DLGM), which is trained using stochastic gradient variational Bayes (SGVB) algorithm and performs efficient approximate inference and learning with a directed probabilistic graphical model. The trained DLGM then generate latent variables based on Gaussian distribution, which is used as new features...
Novelty detection is the task of recognising events the differ from a model of normality. This paper proposes an acoustic novelty detector based on neural networks trained with an adversarial training strategy. The proposed approach is composed of a feature extraction stage that calculates Log-Mel spectral features from the input signal. Then, an autoencoder network, trained on a corpus of “normal”...
With the completion of the IARPA Babel program, it is possible to systematically analyze the performance of speech recognition systems across a wide variety of languages. We select 16 languages from the dataset and compare performance using a deep neural network-based acoustic model. The focus is on keyword spotting using the actual term-weighted value (ATWV) metric. We demonstrate that ATWV is keyword...
This paper advances the design of CTC-based all-neural (or end-to-end) speech recognizers. We propose a novel symbol inventory, and a novel iterated-CTC method in which a second system is used to transform a noisy initial output into a cleaner version. We present a number of stabilization and initialization methods we have found useful in training these networks. We evaluate our system on the commonly...
When using connectionist temporal classification (CTC) based acoustic models (AMs) for large vocabulary continuous speech recognition (LVCSR), most previous studies have used a naive interpolation of the CTC-AM score and an additional language model score, although there is no theoretical justification for such an approach. On the other hand, we recently proposed a theoretically more sound decoding...
In this paper we present an extension of our previously described neural machine translation based system for punctuated transcription. This extension allows the system to map from per frame acoustic features to word level representations by replacing the traditional encoder in the encoder-decoder architecture with a hierarchical encoder. Furthermore, we show that a system combining lexical and acoustic...
In recent years, so-called, “end-to-end” speech recognition systems have emerged as viable alternatives to traditional ASR frameworks. Keyword search, localizing an orthographic query in a speech corpus, is typically performed by using automatic speech recognition (ASR) to generate an index. Previous work has evaluated the use of end-to-end systems for ASR on well known corpora (WSJ, Switchboard,...
Adapting acoustic models to speakers have shown to greatly improve performance for many tasks. Among the adaptation approaches, exploiting auxiliary features characterizing speakers or environments has received great attention because they allow rapid adaptation, i.e. adaptation with limited amount of speech data such as a single utterance. However, the auxiliary features are usually computed in batch...
Recently, there has been an increasing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. One approach is the attention-based encoder-decoder framework that learns a mapping between variable-length input and output sequences in one step using a purely data-driven method. The attention model has often been shown to improve the performance...
Bidirectional long short-term memory (BLSTM) recurrent neural networks are powerful acoustic models in terms of recognition accuracy. When BLSTM acoustic models are used in decoding, the speech decoder needs to wait until the end of a whole sentence is reached, such that forward-propagation in the backward direction can then be performed. The nature of BLSTM acoustic models makes them inappropriate...
Automatic speech recognition (ASR) in noisy environments remains a challenging goal. Recently, the idea of estimating the uncertainty about the features obtained after speech enhancement and propagating it to dynamically adapt deep neural network (DNN) based acoustic models has raised some interest. However, the results in the literature were reported on simulated noisy datasets for a limited variety...
In this paper, we introduce a multimodal speech recognition scenario, in which an image provides contextual information for a spoken caption to be decoded. We investigate a lattice rescoring algorithm that integrates information from the image at two different points: the image is used to augment the language model with the most likely words, and to rescore the top hypotheses using a word-level RNN...
Large-scale monitoring of the child language environment through measuring the amount of speech directed to the child by other children and adults during a vocal communication is an important task. Using the audio extracted from a recording unit worn by a child within a childcare center, at each point in time our proposed diarization system can determine the content of the child's language environment,...
In this paper we propose a framework for building a full-fledged acoustic unit recognizer in a zero resource setting, i.e., without any provided labels. For that, we combine an iterative Dirichlet process Gaussian mixture model (DPGMM) clustering framework with a standard pipeline for supervised GMM-HMM acoustic model (AM) and n-gram language model (LM) training, enhanced by a scheme for iterative...
In this paper, we investigate a DNN tone-based extended recognition network (ERN) approach to Mandarin tone recognition and tone mispronunciation detection. Given a toneless syllable sequence, a tone-based ERN is constructed by assigning five different tones to each toneless syllable, obtaining a fully expanded tonal syllable network. Next, Viterbi decoding is carried out on the tone-based ERN to...
Over the last years, many advances have been made in the field of Automatic Speech Recognition (ASR). However, the persistent presence of ASR errors is limiting the widespread adoption of speech technology in real life applications. This motivates the attempts to find alternative techniques to automatically detect and correct ASR errors, which can be very effective and especially when the user does...
In this paper, we propose a cluster-based senone selection method to speed up the computation of deep neural networks (DNN) at the decoding time of speech recognition. In DNN-based acoustic models, the large number of senones at the output layer is one of the main causes that lead to the high computation complexity of DNNs. Inspired by the mixture selection method designed for the Gaussian mixture...
Conditional random fields (CRF) can generate high-quality confidence measure scores (CMS) for speech recognition systems. However, like many other real-world machine learning tasks, there are only limited annotated data for training but always abundant unlabeled data, which requires too much human efforts and expertise to annotate. To address this issue, we use a scheme of CRF training for ASR confidence...
As improvements on acoustic modeling have rapidly progressed in recent years thanks to the impressive gains in performance obtained using deep neural networks (DNNs), language modeling remains a bottleneck for high performance large vocabulary continuous speech recognition (LVCSR) systems. In this paper an algorithm for automatic words extraction from a stream of phones is suggested to be used in...
We investigate techniques based on deep neural networks (DNNs) for attacking the single-channel multi-talker speech recognition problem. Our proposed approach contains five key ingredients: a multi-style training strategy on artificially mixed speech data, a separate DNN to estimate senone posterior probabilities of the louder and softer speakers at each frame, a weighted finite-state transducer (WFST)-based...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.