We present Mockingjay as a new speech representation learning approach, where bidirectional Transformer encoders are pre-trained on a large amount of unlabeled speech. Previous speech representation methods learn through conditioning on past frames and predicting information about future frames. Whereas Mockingjay is designed to predict the current frame through jointly conditioning on both past and future contexts. The Mockingjay representation improves performance for a wide range of downstream tasks, including phoneme classification, speaker recognition, and sentiment classification on spoken content, while outperforming other approaches. Mockingjay is empirically powerful and can be fine-tuned with downstream models, with only 2 epochs we further improve performance dramatically. In a low resource setting with only 0.1% of labeled data, we outperform the result of Mel-features that uses all 100% labeled data.

Forecasting of multivariate time series data, for instance the prediction of electricity consumption, solar power production, and polyphonic piano pieces, has numerous valuable applications. However, complex and non-linear interdependencies between time steps and series complicate this task. To obtain accurate prediction, it is crucial to model long-term dependency in time series data, which can be achieved by recurrent neural networks (RNNs) with an attention mechanism. The typical attention mechanism reviews the information at each previous time step and selects relevant information to help generate the outputs; however, it fails to capture temporal patterns across multiple time steps. In this paper, we propose using a set of filters to extract time-invariant temporal patterns, similar to transforming time series data into its "frequency domain". Then we propose a novel attention mechanism to select relevant time series, and use its frequency domain information for multivariate forecasting. We apply the proposed model on several real-world tasks and achieve state-of-the-art performance in all of these with a single exception. Our source code is available at https://github.com/gantheory/TPA-LSTM.* indicates equal contribution.

The vector representations of fixed dimensionality for words (in text) offered by Word2Vec have been shown to be very useful in many application scenarios, in particular due to the semantic information they carry. This paper proposes a parallel version, the Audio Word2Vec. It offers the vector representations of fixed dimensionality for variable-length audio segments. These vector representations are shown to describe the sequential phonetic structures of the audio segments to a good degree, with very attractive real world applications such as query-by-example Spoken Term Detection (STD). In this STD application, the proposed approach significantly outperformed the conventional Dynamic Time Warping (DTW) based approaches at significantly lower computation requirements. We propose unsupervised learning of Audio Word2Vec from audio data without human annotation using Sequence-to-sequence Autoencoder (SA). SA consists of two RNNs equipped with Long Short-Term Memory (LSTM) units: the first RNN (encoder) maps the input audio sequence into a vector representation of fixed dimensionality, and the second RNN (decoder) maps the representation back to the input audio sequence. The two RNNs are jointly trained by minimizing the reconstruction error. Denoising Sequence-to-sequence Autoencoder (DSA) is further proposed offering more robust learning.

No abstract

Recently, voice conversion (VC) without parallel data has been successfully adapted to multi-target scenario in which a single model is trained to convert the input voice to many different speakers. However, such model suffers from the limitation that it can only convert the voice to the speakers in the training data, which narrows down the applicable scenario of VC. In this paper, we proposed a novel one-shot VC approach which is able to perform VC by only an example utterance from source and target speaker respectively, and the source and target speaker do not even need to be seen during training. This is achieved by disentangling speaker and content representations with instance normalization (IN). Objective and subjective evaluation shows that our model is able to generate the voice similar to target speaker. In addition to the performance measurement, we also demonstrate that this model is able to learn meaningful speaker representations without any supervision.