Related papers: CNN-LSTM models for Multi-Speaker Source Separatio…
In this paper, we propose a sequential neural encoder with latent structured description (SNELSD) for modeling sentences. This model introduces latent chunk-level representations into conventional sequential neural encoders, i.e., recurrent…
Machine learning is widely used to analyze biological sequence data. Non-sequential models such as SVMs or feed-forward neural networks are often used although they have no natural way of handling sequences of varying length. Recurrent…
Because of their superior ability to preserve sequence information over time, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have obtained strong results on a variety of…
This paper presents a model for disfluency detection in spontaneous speech transcripts called LSTM Noisy Channel Model. The model uses a Noisy Channel Model (NCM) to generate n-best candidate disfluency analyses and a Long Short-Term Memory…
Casual conversations involving multiple speakers and noises from surrounding devices are common in everyday environments, which degrades the performances of automatic speech recognition systems. These challenging characteristics of…
Semantic Textual Similarity (STS) is the basis of many applications in Natural Language Processing (NLP). Our system combines convolution and recurrent neural networks to measure the semantic similarity of sentences. It uses a convolution…
Recurrent Neural Networks (RNN) have obtained excellent result in many natural language processing (NLP) tasks. However, understanding and interpreting the source of this success remains a challenge. In this paper, we propose Recurrent…
The performance of automatic speech recognition (ASR) systems severely degrades when multi-talker speech overlap occurs. In meeting environments, speech separation is typically performed to improve the robustness of ASR systems. Recently,…
Despite the significant progress in automatic speech recognition (ASR), distant ASR remains challenging due to noise and reverberation. A common approach to mitigate this issue consists of equipping the recording devices with multiple…
Acquiring the parameters of neural networks (NNs) has been one of the most important problems in machine learning since the inception of NNs. Traditional approaches, such as backpropagation and forward-only optimization, acquire parameters…
Recurrent Neural Networks (RNNs) have become the standard modeling technique for sequence data, and are used in a number of novel text-to-speech models. However, training a TTS model including RNN components has certain requirements for GPU…
This thesis studies how the segmentation results, produced by convolutional neural networks (CNN), is different from each other when applied to small biomedical datasets. We use different architectures, parameters and hyper-parameters,…
In speech recognition problems, data scarcity often poses an issue due to the willingness of humans to provide large amounts of data for learning and classification. In this work, we take a set of 5 spoken Harvard sentences from 7 subjects…
There exist several data-driven approaches that enable us model time series data including traditional regression-based modeling approaches (i.e., ARIMA). Recently, deep learning techniques have been introduced and explored in the context…
Acoustic models based on long short-term memory recurrent neural networks (LSTM-RNNs) were applied to statistical parametric speech synthesis (SPSS) and showed significant improvements in naturalness and latency over those based on hidden…
Connectionist temporal classification (CTC) is a popular sequence prediction approach for automatic speech recognition that is typically used with models based on recurrent neural networks (RNNs). We explore whether deep convolutional…
We present a multi-channel database of overlapping speech for training, evaluation, and detailed analysis of source separation and extraction algorithms: SMS-WSJ -- Spatialized Multi-Speaker Wall Street Journal. It consists of artificially…
In this paper, we propose a novel neural approach for paraphrase generation. Conventional para- phrase generation methods either leverage hand-written rules and thesauri-based alignments, or use statistical machine learning principles. To…
Decoding the speech signal that a person is listening to from the human brain via electroencephalography (EEG) can help us understand how our auditory system works. Linear models have been used to reconstruct the EEG from speech or vice…
Recurrent neural networks (RNN) are at the core of modern automatic speech recognition (ASR) systems. In particular, long-short term memory (LSTM) recurrent neural networks have achieved state-of-the-art results in many speech recognition…