In this paper we investigate the use of deep neural networks (DNNs) for a small footprint text-dependent speaker verification task. At development stage, a DNN is trained to classify speakers at the framelevel. During speaker enrollment, the trained DNN is used to extract speaker specific features from the last hidden layer. The average of these speaker features, or d-vector, is taken as the speaker model. At evaluation stage, a d-vector is extracted for each utterance and compared to the enrolled speaker model to make a verification decision. Experimental results show the DNN based speaker verification system achieves good performance compared to a popular i-vector system on a small footprint text-dependent speaker verification task. In addition, the DNN based system is more robust to additive noise and outperforms the i-vector system at low False Rejection operating points. Finally the combined system outperforms the i-vector system by 14% and 25% relative in equal error rate (EER) for clean and noisy conditions respectively.Index Terms-Deep neural networks, speaker verification.

In this paper we present an end-to-end speech recognition model with Transformer encoders that can be used in a streaming speech recognition system. Transformer computation blocks based on selfattention are used to encode both audio and label sequences independently. The activations from both audio and label encoders are combined with a feed-forward layer to compute a probability distribution over the label space for every combination of acoustic frame position and label history. This is similar to the Recurrent Neural Network Transducer (RNN-T) model, which uses RNNs for information encoding instead of Transformer encoders. The model is trained with the RNN-T loss well-suited to streaming decoding. We present results on the LibriSpeech dataset showing that limiting the left context for self-attention in the Transformer layers makes decoding computationally tractable for streaming, with only a slight degradation in accuracy. We also show that the full attention version of our model beats the-state-of-the art accuracy on the LibriSpeech benchmarks. Our results also show that we can bridge the gap between full attention and limited attention versions of our model by attending to a limited number of future frames.

YouTube is a highly visited video sharing website where over one billion people watch six billion hours of video every month. Improving accessibility to these videos for the hard of hearing and for search and indexing purposes is an excellent application of automatic speech recognition. However, YouTube videos are extremely challenging for automatic speech recognition systems. Standard adapted Gaussian Mixture Model (GMM) based acoustic models can have word error rates above 50%, making this one of the most difficult reported tasks. Since 2009 YouTube has provided automatic generation of closed captions for videos detected to have English speech; the service now supports ten different languages. This article describes recent improvements to the original system, in particular the use of owner-uploaded video transcripts to generate additional semisupervised training data and deep neural networks acoustic models with large state inventories. Applying an "island of confidence" filtering heuristic to select useful training segments, and increasing the model size by using 44,526 context dependent states with a lowrank final layer weight matrix approximation, improved performance by about 13% relative compared to previously reported sequence trained DNN results for this task.Index Terms-Large vocabulary speech recognition, deep neural networks, deep learning, audio indexing.

Although much is known about how speech is produced, and research into speech production has resulted in measured articulatory data, feature systems of different kinds and numerous models, speech production knowledge is almost totally ignored in current mainstream approaches to automatic speech recognition. Representations of speech production allow simple explanations for many phenomena observed in speech which cannot be easily analyzed from either acoustic signal or phonetic transcription alone. In this article, we provide a survey of a growing body of work in which such representations are used to improve automatic speech recognition.PACS numbers: 43.72.Ne (Automatic speech recognition systems); 43.70.Jt (Instrumentation and methodology for speech production research); 43.70.Bk (Models and theories of speech production)

This paper describes the technical and system building advances made to the Google Home multichannel speech recognition system, which was launched in November 2016. Technical advances include an adaptive dereverberation frontend, the use of neural network models that do multichannel processing jointly with acoustic modeling, and Grid-LSTMs to model frequency variations. On the system level, improvements include adapting the model using Google Home specific data. We present results on a variety of multichannel sets. The combination of technical and system advances result in a reduction of WER of 8-28% relative compared to the current production system.