We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple softmax activation allows to train a more generalized discriminative speaker embedding extractor. Cosine similarity is an effective metric for speaker verification in this embedding space. We also address the problem of choosing an architecture for the extractor. We found that deep networks with residual frame level connections outperform wide but relatively shallow architectures. This paper also proposes several improvements for previous DNN-based extractor systems to increase the speaker recognition accuracy. We show that the discriminatively trained similarity metric learning approach outperforms the standard LDA-PLDA method as an embedding backend. The results obtained on Speakers in the Wild and NIST SRE 2016 evaluation sets demonstrate robustness of the proposed systems when dealing with close to real-life conditions.

Even with today's frequent technological breakthroughs in speech-interactive devices (think Siri and Alexa), few companies have tried their hand at enabling multi-user profiles. Google Home has been the most ambitious in this area, allowing up to six user profiles. The recent boom of this technology is what made the potential for this project very exciting to our team. We also wanted to engage in a project that is still a hot topic in deep-learning research, create interesting tools, learn more about neural network architectures, and make original contributions where possible. We sought to create a system able to quickly add user profiles and accurately identify their voices with very little training data, a few sentences as most! This learning from one to only a few samples is known as One Shot Learning.

We propose a theoretical framework for thinking about score normalization, which confirms that normalization is not needed under (admittedly fragile) ideal conditions. If, however, these conditions are not met, e.g. under data-set shift between training and runtime, our theory reveals dependencies between scores that could be exploited by strategies such as score normalization. Indeed, it has been demonstrated over and over experimentally, that various ad-hoc score normalization recipes do work. We present a first attempt at using probability theory to design a generative score-space normalization model which gives similar improvements to ZT-norm on the text-dependent RSR 2015 database.

This paper presents the Intelligent Voice (IV) system submitted to the NIST 2016 Speaker Recognition Evaluation (SRE). The primary emphasis of SRE this year was on developing speaker recognition technology which is robust for novel languages that are much more heterogeneous than those used in the current state-of-the-art, using significantly less training data, that does not contain meta-data from those languages. The system is based on the state-of-the-art i-vector/PLDA which is developed on the fixed training condition, and the results are reported on the protocol defined on the development set of the challenge.

Although highly correlated, speech and speaker recognition have been regarded as two independent tasks and studied by two communities. This is certainly not the way that people behave: we decipher both speech content and speaker traits at the same time. This paper presents a unified model to perform speech and speaker recognition simultaneously and altogether. The model is based on a unified neural network where the output of one task is fed to the input of the other, leading to a multi-task recurrent network. Experiments show that the joint model outperforms the task-specific models on both the two tasks.

We present the recent advances along with an error analysis of the IBM speaker recognition system for conversational speech. Some of the key advancements that contribute to our system include: a nearest-neighbor discriminant analysis (NDA) approach (as opposed to LDA) for intersession variability compensation in the i-vector space, the application of speaker and channel-adapted features derived from an automatic speech recognition (ASR) system for speaker recognition, and the use of a DNN acoustic model with a very large number of output units (~10k senones) to compute the frame-level soft alignments required in the i-vector estimation process. We evaluate these techniques on the NIST 2010 SRE extended core conditions (C1-C9), as well as the 10sec-10sec condition. To our knowledge, results achieved by our system represent the best performances published to date on these conditions. For example, on the extended tel-tel condition (C5) the system achieves an EER of 0.59%. To garner further understanding of the remaining errors (on C5), we examine the recordings associated with the low scoring target trials, where various issues are identified for the problematic recordings/trials. Interestingly, it is observed that correcting the pathological recordings not only improves the scores for the target trials but also for the nontarget trials.

In this paper we describe the recent advancements made in the IBM i-vector speaker recognition system for conversational speech. In particular, we identify key techniques that contribute to significant improvements in performance of our system, and quantify their contributions. The techniques include: 1) a nearest-neighbor discriminant analysis (NDA) approach that is formulated to alleviate some of the limitations associated with the conventional linear discriminant analysis (LDA) that assumes Gaussian class-conditional distributions, 2) the application of speaker- and channel-adapted features, which are derived from an automatic speech recognition (ASR) system, for speaker recognition, and 3) the use of a deep neural network (DNN) acoustic model with a large number of output units (~10k senones) to compute the frame-level soft alignments required in the i-vector estimation process. We evaluate these techniques on the NIST 2010 speaker recognition evaluation (SRE) extended core conditions involving telephone and microphone trials. Experimental results indicate that: 1) the NDA is more effective (up to 35% relative improvement in terms of EER) than the traditional parametric LDA for speaker recognition, 2) when compared to raw acoustic features (e.g., MFCCs), the ASR speaker-adapted features provide gains in speaker recognition performance, and 3) increasing the number of output units in the DNN acoustic model (i.e., increasing the senone set size from 2k to 10k) provides consistent improvements in performance (for example from 37% to 57% relative EER gains over our baseline GMM i-vector system). To our knowledge, results reported in this paper represent the best performances published to date on the NIST SRE 2010 extended core tasks.

A novel approach for comparing sequences of observations using an explicit-expansion kernel is demonstrated. The kernel is derived using the assumption of the independence of the sequence of observations and a mean-squared error training criterion. The use of an explicit expansion kernel reduces classifier model size and computation dramatically, resulting in model sizes and computation one-hundred times smaller in our application. The explicit expansion also preserves the computational advantages of an earlier architecture based on mean-squared error training. Training using standard support vector machine methodology gives accuracy that significantly exceeds the performance of state-of-the-art mean-squared error training for a speaker recognition task.

A novel approach for comparing sequences of observations using an explicit-expansion kernel is demonstrated. The kernel is derived using the assumption of the independence of the sequence of observations and a mean-squared error training criterion.

A new classifier is presented for text-independent speaker recognition. The new classifier is called the modified neural tree network (MNTN). The NTN is a hierarchical classifier that combines the properties of decision trees and feed-forward neural networks. The MNTN differs from the standard NTNin that a new learning rule based on discriminant learning is used, which minimizes the classification error as opposed to a norm of the approximation error. The MNTN also uses leaf probability measures inaddition to the class labels.