It is today acknowledged that neural network language models outperform backoff language models in applications like speech recognition or statistical machine translation. However, training these models on large amounts of data can take several days. We present efficient techniques to adapt a neural network language model to new data. Instead of training a completely new model or relying on mixture approaches, we propose two new methods: continued training on resampled data or insertion of adaptation layers. We present experimental results in an CAT environment where the post-edits of professional translators are used to improve an SMT system. Both methods are very fast and achieve significant improvements without overfitting the small adaptation data.
Stanford typed dependencies are a widely desired representation of natural language sentences, but parsing is one of the major computational bottlenecks in text analysis systems. In light of the evolving definition of the Stanford dependencies and developments in statistical dependency parsing algorithms, this paper revisits the question of Cer et al. (2010): what is the tradeoff between accuracy and speed in obtaining Stanford dependencies in particular? We also explore the effects of input representations on this tradeoff: part-of-speech tags, the novel use of an alternative dependency representation as input, and distributional representaions of words. We find that direct dependency parsing is a more viable solution than it was found to be in the past. An accompanying software release can be found at: http://www.ark.cs.cmu.edu/TBSD
In this paper, we propose a novel family of windowing technique to compute Mel Frequency Cepstral Coefficient (MFCC) for automatic speaker recognition from speech. The proposed method is based on fundamental property of discrete time Fourier transform (DTFT) related to differentiation in frequency domain. Classical windowing scheme such as Hamming window is modified to obtain derivatives of discrete time Fourier transform coefficients. It has been mathematically shown that the slope and phase of power spectrum are inherently incorporated in newly computed cepstrum. Speaker recognition systems based on our proposed family of window functions are shown to attain substantial and consistent performance improvement over baseline single tapered Hamming window as well as recently proposed multitaper windowing technique.
We describe an implemented system for robust domain-independent syntactic parsing of English, using a unification-based grammar of part-of-speech and punctuation labels coupled with a probabilistic LR parser. We present evaluations of the system's performance along several different dimensions; these enable us to assess the contribution that each individual part is making to the success of the system as a whole, and thus prioritise the effort to be devoted to its further enhancement. Currently, the system is able to parse around 80% of sentences in a substantial corpus of general text containing a number of distinct genres. On a random sample of 250 such sentences the system has a mean crossing bracket rate of 0.71 and recall and precision of 83% and 84% respectively when evaluated against manually-disambiguated analyses.
Recent work has considered corpus-based or statistical approaches to the problem of prepositional phrase attachment ambiguity. Typically, ambiguous verb phrases of the form {v np1 p np2} are resolved through a model which considers values of the four head words (v, n1, p and n2). This paper shows that the problem is analogous to n-gram language models in speech recognition, and that one of the most common methods for language modeling, the backed-off estimate, is applicable. Results on Wall Street Journal data of 84.5% accuracy are obtained using this method. A surprising result is the importance of low-count events - ignoring events which occur less than 5 times in training data reduces performance to 81.6%.
RNN-Transducer has been one of promising architectures for end-to-end automatic speech recognition. Although RNN-Transducer has many advantages including its strong accuracy and streaming-friendly property, its high memory consumption during training has been a critical problem for development. In this work, we propose to apply sampled softmax to RNN-Transducer, which requires only a small subset of vocabulary during training thus saves its memory consumption. We further extend sampled softmax to optimize memory consumption for a minibatch, and employ distributions of auxiliary CTC losses for sampling vocabulary to improve model accuracy. We present experimental results on LibriSpeech, AISHELL-1, and CSJ-APS, where sampled softmax greatly reduces memory consumption and still maintains the accuracy of the baseline model.
In this paper we introduce "Federated Learning Utilities and Tools for Experimentation" (FLUTE), a high-performance open source platform for federated learning research and offline simulations. The goal of FLUTE is to enable rapid prototyping and simulation of new federated learning algorithms at scale, including novel optimization, privacy, and communications strategies. We describe the architecture of FLUTE, enabling arbitrary federated modeling schemes to be realized, we compare the platform with other state-of-the-art platforms, and we describe available features of FLUTE for experimentation in core areas of active research, such as optimization, privacy and scalability. We demonstrate the effectiveness of the platform with a series of experiments for text prediction and speech recognition, including the addition of differential privacy, quantization, scaling and a variety of optimization and federation approaches.
Death by suicide is the seventh of the leading death cause worldwide. The recent advancement in Artificial Intelligence (AI), specifically AI application in image and voice processing, has created a promising opportunity to revolutionize suicide risk assessment. Subsequently, we have witnessed fast-growing literature of researches that applies AI to extract audiovisual non-verbal cues for mental illness assessment. However, the majority of the recent works focus on depression, despite the evident difference between depression signs and suicidal behavior non-verbal cues. In this paper, we review the recent works that study suicide ideation and suicide behavior detection through audiovisual feature analysis, mainly suicidal voice/speech acoustic features analysis and suicidal visual cues.
Recurrent Neural Networks are powerful machine learning frameworks that allow for data to be saved and referenced in a temporal sequence. This opens many new possibilities in fields such as handwriting analysis and speech recognition. This paper seeks to explore current research being conducted on RNNs in four very important areas, being biometric authentication, expression recognition, anomaly detection, and applications to aircraft. This paper reviews the methodologies, purpose, results, and the benefits and drawbacks of each proposed method below. These various methodologies all focus on how they can leverage distinct RNN architectures such as the popular Long Short-Term Memory (LSTM) RNN or a Deep-Residual RNN. This paper also examines which frameworks work best in certain situations, and the advantages and disadvantages of each pro-posed model.
With the development of deep learning and artificial intelligence, audio synthesis has a pivotal role in the area of machine learning and shows strong applicability in the industry. Meanwhile, significant efforts have been dedicated by researchers to handle multimodal tasks at present such as audio-visual multimodal processing. In this paper, we conduct a survey on audio synthesis and audio-visual multimodal processing, which helps understand current research and future trends. This review focuses on text to speech(TTS), music generation and some tasks that combine visual and acoustic information. The corresponding technical methods are comprehensively classified and introduced, and their future development trends are prospected. This survey can provide some guidance for researchers who are interested in the areas like audio synthesis and audio-visual multimodal processing.
Add to Chrome
Add to Firefox